Climate Change AI Workshop Papers

On this page, we show accepted works from all our workshops on "Tackling Climate Change with Machine Learning."

Venue Title Subject Areas
NeurIPS 2021 Flood Segmentation on Sentinel-1 SAR Imagery with Semi-Supervised Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Floods wreak havoc throughout the world, causing billions of dollars in damages, and uprooting communities, ecosystems and economies. The NASA Impact Emerging Techniques in Computational Intelligence (ETCI) competition on Flood Detection tasked participants with predicting flooded pixels after training with synthetic aperture radar (SAR) images in a supervised setting. We propose a semi-supervised learning pseudo-labeling scheme that derives confidence estimates from U-Net ensembles, thereby progressively improving accuracy. Concretely, we use a cyclical approach involving multiple stages (1) training an ensemble model of multiple U-Net architectures with the provided high confidence hand-labeled data and, generated pseudo labels or low confidence labels on the entire unlabeled test dataset, and then, (2) filter out quality generated labels and, (3) combine the generated labels with the previously available high confidence hand-labeled dataset. This assimilated dataset is used for the next round of training ensemble models. This cyclical process is repeated until the performance improvement plateaus. Additionally, we post process our results with Conditional Random Fields. Our approach sets a high score, and a new state-of-the-art on the Sentinel-1 dataset for the ETCI competition with 0.7654 IoU, an impressive improvement over the 0.60 IOU baseline. Our method, which we release with all the code including trained models, can also be used as an open science benchmark for the Sentinel-1 released dataset.

Authors: Siddha Ganju (Nvidia Corporation); Sayak Paul (Carted)

Unsupervised and semi-supervised learning Disaster prediction, management, and relief Earth science and monitoring Computer vision and remote sensing
NeurIPS 2021 Short-term Solar Irradiance Prediction from Sky Images (Papers Track)
Abstract and authors: (click to expand)

Abstract: Solar irradiance forecasting is essential for the integration of the solar power into the power grid system while maintaining its stability. This paper focuses on short-term solar irradiance forecasting (upto 4-hour ahead-of-time prediction) from a past sky image sequence. Most existing work aims for the prediction of the most likely future of the solar irradiance. While it is likely deterministic for intra-hourly prediction, the future solar irradiance is naturally diverse over a relatively long-term horizon (>1h). We therefore introduce approaches to deterministic and stochastic predictions to capture the most likely as well as the diverse future of the solar irradiance. To enable the autoregressive prediction capability of the model, we proposed deep neural networks to predict the future sky images in a deterministic as well as stochastic manner. We evaluate our approaches on benchmark datasets and demonstrate that our approaches achieve superior performance.

Authors: Hoang Chuong Nguyen (Australia National University); Miaomiao Liu (The Australian National University)

Computer vision and remote sensing Power and energy systems
NeurIPS 2021 Towards Representation Learning for Atmospheric Dynamics (Papers Track)
Abstract and authors: (click to expand)

Abstract: The prediction of future climate scenarios under anthropogenic forcing is critical to understand climate change and to assess the impact of potentially counter-acting technologies. Machine learning and hybrid techniques for this prediction rely on informative metrics that are sensitive to pertinent but often subtle influences. For atmospheric dynamics, a critical part of the climate system, the ``eyeball metric'', i.e. a visual inspection by an expert, is currently still the gold standard. However, it cannot be used as metric in machine learning systems where an algorithmic description is required. Motivated by the success of intermediate neural network activations as basis for learned metrics, e.g. in computer vision, we present a novel, self-supervised representation learning approach specifically designed for atmospheric dynamics. Our approach, called AtmoDist, trains a neural network on a simple, auxiliary task: predicting the temporal distance between elements of a shuffled sequence of atmospheric fields (e.g. the components of the wind field from a reanalysis or simulation). The task forces the network to learn important intrinsic aspects of the data as activations in its layers and from these hence a discriminative metric can be obtained. We demonstrate this by using AtmoDist to define a metric for GAN-based super resolution of vorticity and divergence. Our upscaled data matches closely the true statistics of a high resolution reference and it significantly outperform the state-of-the-art based on mean squared error. Since AtmoDist is unsupervised, only requires a temporal sequence of fields, and uses a simple auxiliary task, it can be used in a wide range of applications that aim to understand and mitigate climate change.

Authors: Sebastian Hoffmann (University of Magdeburg); Christian Lessig (Otto-von-Guericke-Universitat Magdeburg)

Climate and Earth science Earth science and monitoring Generative modeling Time-series analysis
NeurIPS 2021 Addressing Deep Learning Model Uncertainty in Long-Range Climate Forecasting with Late Fusion (Papers Track)
Abstract and authors: (click to expand)

Abstract: Global warming leads to the increase in frequency and intensity of climate extremes that cause tremendous loss of lives and property. Accurate long-range climate prediction allows more time for preparation and disaster risk management for such extreme events. Although machine learning approaches have shown promising results in long-range climate forecasting, the associated model uncertainties may reduce their reliability. To address this issue, we propose a late fusion approach that systematically combines the predictions from multiple models to reduce the expected errors of the fused results. We also propose a network architecture with the novel denormalization layer to gain the benefits of data normalization without actually normalizing the data. The experimental results on long-range 2m temperature forecasting show that the framework outperforms the 30-year climate normals, and the accuracy can be improved by increasing the number of models.

Authors: Ken C. L. Wong (IBM Research – Almaden Research Center); Hongzhi Wang (IBM Almaden Research Center); Etienne E Vos (IBM); Bianca Zadrozny (IBM Research); Campbell D Watson (IBM Reserch); Tanveer Syeda-Mahmood (IBM Research)

Uncertainty quantification and robustness Climate and Earth science Classification, regression, and supervised learning Time-series analysis
NeurIPS 2021 Predicting Discharge in Catchment Outlet Using Deep Learning: Case Study of the Ansongo-Niamey Basin (Papers Track)
Abstract and authors: (click to expand)

Abstract: Hydrological models are one of the key challenges in hydrology. Their goal is to understand, predict and manage water resources. Most of the hydrological models so far were either physical or conceptual models. But in the past two decades, fully data-driven (empirical) models started to emerge with the breakthroughs of novel deep learning methods in runoff prediction. These breakthroughs were mostly favored by the large volume, variety and velocity of water-related data. Long Short-Term Memory and Gated Recurrent Unit neural networks, particularly achieved the outstanding milestone of outperforming classic hydrological models in less than a decade. Moreover, they have the potential to change the way hydrological modeling is performed. In this study, precipitation, minimal and maximum temperature at the Ansongo-Niamey basin combined with the discharge at Ansongo and Kandadji were used to predict the discharge at Niamey using artificial neural networks. After data preprocessing and hyperparameter optimization, the deep learning models performed well with the LSTM and GRU respectively scoring a Nash-Sutcliffe Efficiency of 0.933 and 0.935. This performance matches those of well-known physically-based models used to simulate Niamey’s discharge and therefore demonstrates the efficiency of deep learning methods in a West African context, especially in Niamey which has been facing severe floods due to climate change.

Authors: Peniel J. Y. Adounkpe (WASCAL); Eric Alamou (Université d'Abomey-Calavi); Belko Diallo (WASCAL); Abdou Ali (AGRHYMET Regional Centre)

Disaster prediction, management, and relief Causal and Bayesian methods Classification, regression, and supervised learning Time-series analysis
NeurIPS 2021 Accurate and Timely Forecasts of Geologic Carbon Storage using Machine Learning Methods (Papers Track)
Abstract and authors: (click to expand)

Abstract: Carbon capture and storage is one strategy to reduce greenhouse gas emissions. One approach to storing the captured CO2 is to inject it into deep saline aquifers. However, dynamics of the injected CO2 plume is uncertain and the potential for leakage back to the atmosphere must be assessed. Thus, accurate and timely forecasts of CO2 storage via real-time measurements integration becomes very crucial. This study proposes a learning-based, inverse-free prediction method that can accurately and rapidly forecast CO2 movement and distribution with uncertainty quantification based on limited simulation and observation data. The machine learning techniques include dimension reduction, multivariate data analysis, and Bayesian learning. The outcome is expected to provide CO2 storage site operators with an effective tool for real-time decision making.

Authors: Dan Lu (Oak Ridge National Laboratory); Scott Painter (Oak Ridge National Laboratory); Nicholas Azzolina (University of North Dakota); Matthew Burton-Kelly (University of North Dakota)

Carbon capture and sequestration Uncertainty quantification and robustness
NeurIPS 2021 Towards debiasing climate simulations using unsuperviserd image-to-image translation networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate models form the basis of a vast portion of earth system research, and inform our climate policy. Due to the complex nature of our climate system, and the approximations which must necessarily be made in simulating it, these climate models may not perfectly match observations. For further research, these outputs must be bias corrected against observations, but current methods of debiasing do not take into account spatial correlations. We evaluate unsupervised image-to-image translation networks, specifically the UNIT model architecture, for their ability to produce more spatially realistic debiasing than the standard techniques used in the climate community.

Authors: James Fulton (University of Edinburgh); Ben Clarke (Oxford University)

Climate and Earth science Generative modeling
NeurIPS 2021 Using Non-Linear Causal Models to StudyAerosol-Cloud Interactions in the Southeast Pacific (Papers Track)
Abstract and authors: (click to expand)

Abstract: Aerosol-cloud interactions include a myriad of effects that all begin when aerosol enters a cloud and acts as cloud condensation nuclei (CCN). An increase in CCN results in a decrease in the mean cloud droplet size (r$_{e}$). The smaller droplet size leads to brighter, more expansive, and longer lasting clouds that reflect more incoming sunlight, thus cooling the earth. Globally, aerosol-cloud interactions cool the Earth, however the strength of the effect is heterogeneous over different meteorological regimes. Understanding how aerosol-cloud interactions evolve as a function of the local environment can help us better understand sources of error in our Earth system models, which currently fail to reproduce the observed relationships. In this work we use recent non-linear, causal machine learning methods to study the heterogeneous effects of aerosols on cloud droplet radius.

Authors: Andrew Jesson (University of Oxford); Peter Manshausen (University of Oxford); Alyson Douglas (University of Oxford); Duncan Watson-Parris (University of Oxford); Yarin Gal (University of Oxford); Philip Stier (University of Oxford)

Climate and Earth science Causal and Bayesian methods
NeurIPS 2021 Memory to Map: Improving Radar Flood Maps With Temporal Context and Semantic Segmentation (Papers Track)
Abstract and authors: (click to expand)

Abstract: Global flood risk has increased due to worsening extreme weather events and human migration into growing flood-prone areas. Accurate, high-resolution, and near-real time flood maps can address flood risk by reducing financial loss and damage. We propose Model to Map, a novel machine learning approach that utilizes bi-temporal context to improve flood water segmentation performance for Sentinel-1 imagery. We show that the inclusion of unflooded context for the area, or "memory," allows the model to tap into a "prior state" of pre-flood conditions, increasing performance in geographic regions in which single-image radar-based flood mapping methods typically underperform (e.g. deserts). We focus on accuracy across different biomes to ensure global performance. Our experiments and novel data processing technique show that the confluence of pre-flood and permanent water context provides a 21% increase in mIoU over the baseline overall, and over 87% increase in deserts.

Authors: Veda Sunkara (Cloud to Street); Nicholas Leach (Cloud to Street); Siddha Ganju (Nvidia)

Computer vision and remote sensing Climate justice Earth science and monitoring
NeurIPS 2021 Hurricane Forecasting: A Novel Multimodal Machine Learning Framework (Papers Track)
Abstract and authors: (click to expand)

Abstract: This paper describes a machine learning (ML) framework for tropical cyclone intensity and track forecasting, combining multiple distinct ML techniques and utilizing diverse data sources. Our framework, which we refer to as Hurricast (HURR), is built upon the combination of distinct data processing techniques using gradient-boosted trees and novel encoder-decoder architectures, including CNN, GRU and Transformers components. We propose a deep-learning feature extractor methodology to mix spatial-temporal data with statistical data efficiently. Our multimodal framework unleashes the potential of making forecasts based on a wide range of data sources, including historical storm data, and visual data such as reanalysis atmospheric images. We evaluate our models with current operational forecasts in North Atlantic (NA) and Eastern Pacific (EP) basins on 2016-2019 for 24-hour lead time, and show our models consistently outperform statistical-dynamical models and compete with the best dynamical models. Furthermore, the inclusion of Hurricast into an operational forecast consensus model leads to a significant improvement of 5% - 15% over NHC's official forecast, thus highlighting the complementary properties with existing approaches.

Authors: Léonard Boussioux (MIT, CentraleSupélec); Cynthia Zeng (MIT); Dimitris Bertsimas (MIT); Théo J Guenais (Harvard University)

Hybrid physical models Climate and Earth science Disaster prediction, management, and relief Classification, regression, and supervised learning Computer vision and remote sensing Time-series analysis Unsupervised and semi-supervised learning
NeurIPS 2021 Improved Drought Forecasting Using Surrogate Quantile And Shape (SQUASH) Loss (Papers Track)
Abstract and authors: (click to expand)

Abstract: Droughts are amongst the most damaging natural hazard with cascading impacts across multiple sectors of the economy and society. Improved forecasting of drought conditions ahead of time can significantly improve strategic planning to mitigate the impacts and enhance resilience. Though significant progress in forecasting approaches has been made, the current approaches focus on the overall improvement of the forecast, with less attention on the extremeness of drought events. In this paper, we focus on improving the accuracy of forecasting extreme and severe drought events by introducing a novel loss function Surrogate Quantile and Shape loss (SQUASH) that combines weighted quantile loss and dynamic time-warping-based shape loss. We show the effectiveness of the proposed loss functions for imbalanced time-series drought forecasting tasks on two regions in India and the USA.

Authors: Devyani Lambhate Lambhate (Indian Institute of Science); Smit Marvaniya (IBM Research India); Jitendra Singh (IBM Research - India); David Gold (IBM)

Disaster prediction, management, and relief Agriculture, forestry and other land use Climate and Earth science Time-series analysis
NeurIPS 2021 Global ocean wind speed estimation with CyGNSSnet (Papers Track)
Abstract and authors: (click to expand)

Abstract: The CyGNSS (Cyclone Global Navigation Satellite System) satellite system measures GNSS signals reflected off the Earth's surface. A global ocean wind speed dataset is derived, which fills a gap in Earth observation data, will improve cyclone forecasting, and could be used to mitigate effects of climate change. We propose CyGNSSnet, a deep learning model for predicting wind speed from CyGNSS observables, and evaluate its potential for operational use. With CyGNSSnet, performance improves by 29\% over the current operational model. We further introduce a hierarchical model, that combines an extreme value classifier and a specialized CyGNSSnet and slightly improves predictions for high winds.

Authors: Caroline Arnold (German Climate Computing Center); Milad Asgarimehr (German Research Centre for Geosciences)

Computer vision and remote sensing Disaster prediction, management, and relief Earth science and monitoring Classification, regression, and supervised learning
NeurIPS 2021 Predicting Critical Biogeochemistry of the Southern Ocean for Climate Monitoring (Papers Track)
Abstract and authors: (click to expand)

Abstract: The Biogeochemical-Argo (BGC-Argo) program is building a network of globally distributed, sensor-equipped robotic profiling floats, improving our understanding of the climate system and how it is changing. These floats, however, are limited in the number of variables measured. In this study, we train neural networks to predict silicate and phosphate values in the Southern Ocean from temperature, pressure, salinity, oxygen, nitrate, and location and apply these models to earth system model (ESM) and BGC-Argo data to expand the utility of this ocean observation network. We trained our neural networks on observations from the Global Ocean Ship-Based Hydrographic Investigations Program (GO-SHIP) and use dropout regularization to provide uncertainty bounds around our predicted values. Our neural network significantly improves upon linear regression but shows variable levels of uncertainty across the ranges of predicted variables. We explore the generalization of our estimators to test data outside our training distribution from both ESM and BGC-Argo data. Our use of out-of-distribution test data to examine shifts in biogeochemical parameters and calculate uncertainty bounds around estimates advance the state-of-the-art in oceanographic data and climate monitoring. We make our data and code publicly available.

Authors: Ellen Park (MIT); Jae Deok Kim (MIT-WHOI); Nadege Aoki (MIT); Yumeng Cao (MIT); Yamin Arefeen (Massachusetts Institute of Technology); Matthew Beveridge (Massachusetts Institute of Technology); David P Nicholson (Woods Hole Oceanographic Institution); Iddo Drori (MIT)

Earth science and monitoring Ecosystems and natural systems Classification, regression, and supervised learning Other
NeurIPS 2021 On the Generalization of Agricultural Drought Classification from Climate Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change is expected to increase the likelihood of drought events, with severe implications for food security. Unlike other natural disasters, droughts have a slow onset and depend on various external factors, making drought detection in climate data difficult. In contrast to existing works that rely on simple relative drought indices as ground-truth data, we build upon soil moisture index (SMI) obtained from a hydrological model. This index is directly related to insufficiently available water to vegetation. Given ERA5-Land climate input data of six months with land use information from MODIS satellite observation, we compare different models with and without sequential inductive bias in classifying droughts based on SMI. We use PR-AUC as the evaluation measure to account for the class imbalance and obtain promising results despite a challenging time-based split. We further show in an ablation study that the models retain their predictive capabilities given input data of coarser resolutions, as frequently encountered in climate models.

Authors: Julia S Gottfriedsen (DLR); Max Berrendorf (Ludwig-Maximilians-Universität München); Pierre Gentine (Columbia University); Markus Reichstein (Max Planck Institute for Biogeochemistry, Jena; Michael Stifel Center Jena for Data-Driven and Simulation Science, Jena); Katja Weigel (niversity of Bremen, Institute of Environmental Physics (IUP), Bremen, Germany); Birgit Hassler (Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), Institut für Physik der Atmosphäre, Oberpfaffenhofen, Germany); Veronika Eyring (Deutsches Zentrum für Luft- und Raumfahrt e.V. (DLR), Institut für Physik der Atmosphäre, Oberpfaffenhofen, Germany; University of Bremen, Institute of Environmental Physics (IUP), Bremen, Germany)

Climate and Earth science Agriculture, forestry and other land use Disaster prediction, management, and relief
NeurIPS 2021 Mapping Post-Climate Change Biogeographical Regions with Deep Latent Variable Models (Papers Track)
Abstract and authors: (click to expand)

Abstract: Forecasting future changes to biodiversity due to shifts in climate is challenging due to nonlinear interactions between species as recorded in their presence/absence data. This work proposes using variational autoencoders with environmental covariates to identify low-dimensional structure in species’ joint co-occurrence patterns and leveraging this simplified representation to provide multivariate predictions of their habitat extent under future climate scenarios. We pursue a latent space clustering approach to map biogeographical regions of frequently co-occurring species and apply this methodology to a dataset from northern Belgium, generating predictive maps illustrating how these regions may expand or contract with changing temperature under a future climate scenario.

Authors: Christopher Krapu (Oak Ridge National Lab - Oak Ridge, TN)

Generative modeling Agriculture, forestry and other land use Causal and Bayesian methods
NeurIPS 2021 Rotation Equivariant Deforestation Segmentation and Driver Classification (Papers Track)
Abstract and authors: (click to expand)

Abstract: Deforestation has become a significant contributing factor to climate change and, due to this, both classifying the drivers and predicting segmentation maps of deforestation has attracted significant interest. In this work, we develop a rotation equivariant convolutional neural network model to predict the drivers and generate segmentation maps of deforestation events from Landsat 8 satellite images. This outperforms previous methods in classifying the drivers and predicting the segmentation map of deforestation, offering a 9% improvement in classification accuracy and a 7% improvement in segmentation map accuracy. In addition, this method predicts stable segmentation maps under rotation of the input image, which ensures that predicted regions of deforestation are not dependent upon the rotational orientation of the satellite.

Authors: Joshua Mitton (University of Glasgow); Roderick Murray-Smith (University of Glasgow)

Computer vision and remote sensing Classification, regression, and supervised learning
NeurIPS 2021 WiSoSuper: Benchmarking Super-Resolution Methods on Wind and Solar Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: The transition to green energy grids depends on detailed wind and solar forecasts to optimize the siting and scheduling of renewable energy generation. Operational forecasts from numerical weather prediction models, however, only have a spatial resolution of 10 to 20-km, which leads to sub-optimal usage and development of renewable energy farms. Weather scientists have been developing super-resolution methods to increase the resolution, but often rely on simple interpolation techniques or computationally expensive differential equation-based models. Recently, machine learning-based models, specifically the physics-informed resolution-enhancing generative adversarial network (PhIREGAN), have outperformed traditional downscaling methods. We provide a thorough and extensible benchmark of leading deep learning-based super-resolution techniques, including the enhanced super-resolution generative adversarial network (ESRGAN) and an enhanced deep super-resolution (EDSR) network, on wind and solar data. We accompany the benchmark with a novel public, processed, and machine learning-ready dataset for benchmarking super-resolution methods on wind and solar data.

Authors: Rupa Kurinchi-Vendhan (Caltech); Björn Lütjens (MIT); Ritwik Gupta (University of California, Berkeley); Lucien D Werner (California Institute of Technology); Dava Newman (MIT); Steven Low (California Institute of Technology)

Computer vision and remote sensing Climate and Earth science Earth science and monitoring Power and energy systems Classification, regression, and supervised learning Generative modeling
NeurIPS 2021 Meta-Learned Bayesian Optimization for Calibrating Building Simulation Models with Multi-Source Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Well-calibrated building simulation models are key to reducing greenhouse gas emissions and optimizing building performance. Current calibration algorithms do not leverage data collected during previous calibration tasks. In this paper, we employ attentive neural processes (ANP) to meta-learn a distribution using multi-source data acquired during previously seen calibration tasks. The ANP informs a meta-learned Bayesian optimizer to accelerate calibration of new, unseen tasks. The few-shot nature of our proposed algorithm is demonstrated on a library of residential buildings validated by the United States Department of Energy (USDoE).

Authors: Sicheng Zhan (NUS); Gordon Wichern (Mitsubishi Electric Research Laboratories (MERL)); Christopher Laughman (Mitsubishi Electric Research Laboratories); Ankush Chakrabarty (Mitsubishi Electric Research Labs)

Buildings and cities Meta- and transfer learning
NeurIPS 2021 MS-nowcasting: Operational Precipitation Nowcasting with Convolutional LSTMs at Microsoft Weather (Papers Track)
Abstract and authors: (click to expand)

Abstract: We present the encoder-forecaster convolutional long short-term memory (LSTM) deep-learning model that powers Microsoft Weather's operational precipitation nowcasting product. This model takes as input a sequence of weather radar mosaics and deterministically predicts future radar reflectivity at lead times up to 6 hours. By stacking a large input receptive field along the feature dimension and conditioning the model's forecaster with predictions from the physics-based High Resolution Rapid Refresh (HRRR) model, we are able to outperform optical flow and HRRR baselines by 20-25% on multiple metrics averaged over all lead times.

Authors: Sylwester Klocek (Microsoft Corporation); Haiyu Dong (Microsoft); Matthew Dixon (Microsoft Corporation); Panashe Kanengoni (Microsoft Corporation); Najeeb Kazmi (Microsoft); Pete Luferenko (Microsoft Corporation); Zhongjian Lv (Microsoft Corporation); Shikhar Sharma (); Jonathan Weyn (Microsoft); Siqi Xiang (Microsoft Corporation)

Computer vision and remote sensing Climate and Earth science Disaster prediction, management, and relief Earth science and monitoring Classification, regression, and supervised learning Hybrid physical models
NeurIPS 2021 SunCast: Solar Irradiance Nowcasting from Geosynchronous Satellite Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: When cloud layers cover photovoltaic (PV) panels, the amount of power the panels produce fluctuates rapidly. Therefore, to maintain enough energy on a power grid to match demand, utilities companies rely on reserve power sources that typically come from fossil fuels and therefore pollute the environment. Accurate short-term PV power prediction enables operators to maximize the amount of power obtained from PV panels and safely reduce the reserve energy needed from fossil fuel sources. While several studies have developed machine learning models to predict solar irradiance at specific PV generation facilities, little work has been done to model short-term solar irradiance on a global scale. Furthermore, models that have been developed are proprietary and have architectures that are not publicly available or rely on computationally demanding Numerical Weather Prediction (NWP) models. Here, we propose a Convolutional Long Short-Term Memory Network model that treats solar nowcasting as a next frame prediction problem, is more efficient than NWP models and has a straightforward, reproducible architecture. Our models can predict solar irradiance for entire North America for up to 3 hours in under 60 seconds on a single machine without a GPU and has a RMSE of 120 W/m^2 when evaluated on 2 months of data.

Authors: Dhileeban Kumaresan (UC Berkeley); Richard Wang (UC Berkeley); Ernesto A Martinez (UC Berkeley); Richard Cziva (UC Berkeley); Alberto Todeschini (UC Berkeley); Colorado J Reed (University of California, Berkeley); Puya Vahabi (UC Berkeley)

Power and energy systems Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2021 Synthetic Imagery Aided Geographic Domain Adaptation for Rare Energy Infrastructure Detection in Remotely Sensed Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Object detection in remotely sensed data is frequently stymied by applications in geographies that are different from that of the training data. When objects are rare, the problem is exacerbated further. This is true of assessments of energy infrastructure such as generation, transmission, and end-use consumption; key to electrification planning as well as for effective assessment of natural disaster impacts which are varying in frequency and intensity due to climate change. We propose an approach to domain adaptation that requires only unlabeled samples from the target domain and generates synthetic data to augment training data for targeted domain adaptation. This approach is shown to work consistently across four geographically diverse domains, improving object detection average precision by 15.5\% on average for small sample sizes.

Authors: Wei Hu (Duke University); Tyler Feldman (Duke University); Eddy Lin (Duke University); Jose Luis Moscoso (Duke); Yanchen J Ou (Duke University); Natalie Tarn (Duke University); Baoyan Ye (Duke University); Wendy Zhang (Duke University); Jordan Malof (Duke University); Kyle Bradbury (Duke University)

Computer vision and remote sensing Earth science and monitoring Power and energy systems Classification, regression, and supervised learning
NeurIPS 2021 Being the Fire: A CNN-Based Reinforcement Learning Method to Learn How Fires Behave Beyond the Limits of Physics-Based Empirical Models (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wildland fires pose an increasing threat in light of anthropogenic climate change. Fire-spread models play an underpinning role in many areas of research across this domain, from emergency evacuation to insurance analysis. We study paths towards advancing such models through deep reinforcement learning. Aggregating 21 fire perimeters from the Western United States in 2017, we construct 11-layer raster images representing the state of the fire area. A convolution neural network based agent is trained offline on one million sub-images to create a generalizable baseline for predicting the best action - burn or not burn - given the then-current state on a particular fire edge. A series of online, TD(0) Monte Carlo Q-Learning based improvements are made with final evaluation conducted on a subset of holdout fire perimeters. We examine the performance of the learned agent/model against the FARSITE fire-spread model. We also make available a novel data set and propose more informative evaluation metrics for future progress.

Authors: William L Ross (Stanford)

Disaster prediction, management, and relief Societal adaptation Computer vision and remote sensing Reinforcement learning and control
NeurIPS 2021 Subseasonal Solar Power Forecasting via Deep Sequence Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: To help mitigate climate change, power systems need to integrate renewable energy sources, such as solar, at a rapid pace. Widespread integration of solar energy into the power system requires major improvements in solar irradiance forecasting, in order to reduce the uncertainty associated with solar power output. While recent works have addressed short lead-time forecasting (minutes to hours ahead), week(s)-ahead and longer forecasts, coupled with uncertainty estimates, will be extremely important for storage applications in future power systems. In this work, we propose machine learning approaches for these longer lead-times as an important new application area in the energy domain. We demonstrate the potential of several deep sequence learning techniques for both point predictions and probabilistic predictions at these longer lead-times. We compare their performance for subseasonal forecasting (forecast lead-times of roughly two weeks) using the SURFRAD data set for 7 stations across the U.S. in 2018. The results are encouraging; the deep sequence learning methods outperform the current benchmark for machine learning-based probabilistic predictions (previously applied at short lead-times in this domain), along with relevant baselines.

Authors: Saumya Sinha (University of Colorado, Boulder); Bri-Mathias S Hodge (University of Colorado Boulder); Claire Monteleoni (University of Colorado Boulder)

Power and energy systems Time-series analysis
NeurIPS 2021 A Transfer Learning-Based Surrogate Model for Geological Carbon Storage with Multi-Fidelity Training Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Geologic carbon storage (GCS) entails injecting large volumes of carbon dioxide (CO2) in deep geologic formations to prevent its release to the atmosphere. Reservoir simulation is widely used in GCS applications to predict subsurface pressure and CO2 saturation. High fidelity numerical models are prohibitively expensive for data assimilation and uncertainty quantification, which require a large number of simulation runs. Deep learning-based surrogate models have shown a great promise to alleviate the high computational cost. However, the training cost is high as thousands of high-fidelity simulations are often necessary for generating the training data. In this work, we explore the use of a transfer learning approach to reduce the training cost. Compared with the surrogate model trained with high-fidelity simulations, our new transfer learning-based model shows comparable accuracy but reduces the training cost by 80%.

Authors: Su Jiang (Stanford University)

Carbon capture and sequestration Computer vision and remote sensing
NeurIPS 2021 National Cropland Classification with Agriculture Census Information and EO Datasets (Papers Track)
Abstract and authors: (click to expand)

Abstract: National cropland classification is critical to monitor food security, comprehend environmental circumstances and climate change, and participate in agricultural policy development. The increasing earth observation datasets, especially the free available Sentinel and Landsat, open unprecedented large-scale mapping opportunities. However, most applied machine learning techniques have relied on substantial training datasets, which are not always available and may be expensive to create or collect. Focusing on Japan, this work indicates what kinds of information can be extracted from agriculture census information then used for mapping different crop types. Different classification approaches of pixel-based and parcel-based are compared. Then, the efficient method is used to generate Japan's first national cropland classification with Sentinel-1 C-band and Landsat-8 time series. For 2015, the overall accuracies for the prefectures range between 71\% and 94\%. This national cropland classification map, which particularly succeeds in extracting high-precision rice products for the whole of Japan and other classes for different prefectures, can be treated as the base map of Japan for future studies related to agriculture, environment, and climate change.

Authors: Junshi Xia (RIKEN); Naoto Yokoya (The University of Tokyo); Bruno Adriano (RIKEN Center for Advanced Intelligence Project (AIP))

Agriculture, forestry and other land use Classification, regression, and supervised learning
NeurIPS 2021 FIgLib & SmokeyNet: Dataset and Deep Learning Model for Real-Time Wildland Fire Smoke Detection (Papers Track)
Abstract and authors: (click to expand)

Abstract: The size and frequency of wildland fires in the western United States have increased in recent years. On high fire-risk days, a small fire ignition can rapidly grow and get out of control. Early detection of fire ignitions from initial smoke can help the response to such fires before they become difficult to manage. Prior work explored deep learning methods for accurate wildfire smoke detection, but many studies suffer from small or unreliable datasets that make it difficult to extrapolate performance to real-world scenarios. In this work, we present the Fire Ignition Library (FIgLib), a publicly-available dataset of nearly 25,000 annotated wildfire smoke images as seen from fixed-view cameras deployed in Southern California. We also introduce SmokeyNet, a novel deep learning architecture using spatio-temporal information from camera imagery for real-time wildfire smoke detection. When trained on the FIgLib dataset, SmokeyNet outperforms comparable baselines. We hope that the availability of the FIgLib dataset and the SmokeyNet architecture will inspire further research into deep learning methods for wildfire smoke detection, leading towards a potential automated notification system to reduce the time to wildfire response.

Authors: Anshuman Dewangan (University of California, San Diego); Mai Nguyen (University of California, San Diego); Garrison Cottrell (UC San Diego)

Disaster prediction, management, and relief Computer vision and remote sensing
NeurIPS 2021 Multitask Learning for Estimating Power Plant Greenhouse Gas Emissions from Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: The burning of fossil fuels produces large amounts of carbon dioxide (CO2), a major Greenhouse Gas (GHG) and a main driver of Climate Change. Quantifying GHG emissions is crucial for accurate predictions of climate effects and to enforce emission trading schemes. The reporting of such emissions is only required in some countries, resulting in insufficient global coverage. In this work, we propose an end-to-end method to predict power generation rates for fossil fuel power plants from satellite images based on which we estimate GHG emission rates. We present a multitask deep learning approach able to simultaneously predict: (i) the pixel-area covered by plumes from a single satellite image of a power plant, (ii) the type of fired fuel, and (iii) the power generation rate. We then convert the predicted power generation rate into estimates for the rate at which CO2 is being emitted. Experimental results show that our model approach allows us to estimate the power generation rate of a power plant to within 139 MW (MAE, for a mean sample power plant capacity of 1177 MW) from a single satellite image and CO2 emission rates to within 311 t/h. This multitask learning approach improves the power generation estimation MAE by 39 % compared to a single-task network trained on the same dataset.

Authors: Joëlle Hanna (University of St. Gallen); Michael Mommert (University of St. Gallen); Linus M. Scheibenreif (University of St. Gallen); Damian Borth (University of St. Gallen)

Computer vision and remote sensing Power and energy systems
NeurIPS 2021 ClimART: A Benchmark Dataset for Emulating Atmospheric Radiative Transfer in Weather and Climate Models (Papers Track)
Abstract and authors: (click to expand)

Abstract: Numerical simulations of Earth's weather and climate require substantial amounts of computation. This has led to a growing interest in replacing subroutines that explicitly compute physical processes with approximate machine learning (ML) methods that are fast at inference time. Within weather and climate models, atmospheric radiative transfer (RT) calculations are especially expensive. This has made them a popular target for neural network-based emulators. However, prior work is hard to compare due to the lack of a comprehensive dataset and standardized best practices for ML benchmarking. To fill this gap, we introduce the \climart dataset, with more than \emph{10 million samples from present, pre-industrial, and future climate conditions}. ClimART poses several methodological challenges for the ML community, such as multiple out-of-distribution test sets, underlying domain physics, and a trade-off between accuracy and inference speed. We also present several novel baselines that indicate shortcomings of the datasets and network architectures used in prior work.

Authors: Salva Rühling Cachay (Technical University of Darmstadt); Venkatesh Ramesh (MILA); Jason N. S. Cole (Environment and Climate Change Canada); Howard Barker (Environment and Climate Change Canada); David Rolnick (McGill University, Mila)

Climate and Earth science Classification, regression, and supervised learning
NeurIPS 2021 A GNN-RNN Approach for Harnessing Geospatial and Temporal Information: Application to Crop Yield Prediction (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change poses new challenges to agricultural production, as crop yields are extremely sensitive to climatic variation. Accurately predicting the effects of weather patterns on crop yield is crucial for addressing issues such as food insecurity, supply stability, and economic planning. Recently, there have been many attempts to use machine learning models for crop yield prediction. However, these models either restrict their tasks to a relatively small region or a short time-period (e.g. a few years), which makes them hard to generalize spatially and temporally. They also view each location as an i.i.d sample, ignoring spatial correlations in the data. In this paper, we introduce a novel graph-based recurrent neural network for crop yield prediction, which incorporates both geographical and temporal structure. Our method is trained, validated, and tested on over 2000 counties from 41 states in the US mainland, covering years from 1981 to 2019. As far as we know, this is the first machine learning method that embeds geographical knowledge in crop yield prediction and predicts crop yields at the county level nationwide. Experimental results show that our proposed method consistently outperforms a wide variety of existing state-of-the-art methods, validating the effectiveness of geospatial and temporal information.

Authors: Joshua Fan (Cornell University); Junwen Bai (Cornell University); Zhiyun Li (Cornell University); Ariel Ortiz-Bobea (Cornell); Carla P Gomes (Cornell University)

Agriculture, forestry and other land use Classification, regression, and supervised learning Time-series analysis
NeurIPS 2021 Learned Benchmarks for Subseasonal Forecasting (Papers Track)
Abstract and authors: (click to expand)

Abstract: We develop a subseasonal forecasting toolkit of simple learned benchmark models that outperform both operational practice and state-of-the-art machine learning and deep learning methods. Our new models include (a) Climatology++, an adaptive alternative to climatology that, for precipitation, is 9% more accurate and 250\% more skillful than the United States operational Climate Forecasting System (CFSv2); (b) CFSv2++, a learned CFSv2 correction that improves temperature and precipitation accuracy by 7-8% and skill by 50-275%; and (c) Persistence++, an augmented persistence model that combines CFSv2 forecasts with lagged measurements to improve temperature and precipitation accuracy by 6-9% and skill by 40-130%. Across the contiguous U.S., these models consistently outperform standard meteorological baselines, state-of-the-art learning methods, and the European Centre for Medium-Range Weather Forecasts ensemble. Overall, we find that augmenting traditional forecasting approaches with learned enhancements yields an effective and computationally inexpensive strategy for building the next generation of subseasonal forecasting benchmarks.

Authors: Soukayna Mouatadid (University of Toronto); Paulo Orenstein (IMPA); Genevieve E Flaspohler (MIT); Miruna Oprescu (Microsoft Research); Judah Cohen (AER); Franklyn Wang (Harvard University); Sean Knight (MIT); Maria Geogdzhayeva (MIT); Sam Levang (Salient Predictions Inc.); Ernest Fraenkel (MIT); Lester Mackey (Microsoft Research)

Climate and Earth science Classification, regression, and supervised learning
NeurIPS 2021 Emissions-aware electricity network expansion planning via implicit differentiation (Papers Track)
Abstract and authors: (click to expand)

Abstract: We consider a variant of the classical problem of designing or expanding an electricity network. Instead of minimizing only investment and production costs, however, we seek to minimize some mixture of cost and greenhouse gas emissions, even if the underlying dispatch model does not tax emissions. This enables grid planners to directly minimize consumption-based emissions, when expanding or modifying the grid, regardless of whether or not the carbon market incorporates a carbon tax. We solve this problem using gradient descent with implicit differentiation, a technique recently popularized in machine learning. To demonstrate the method, we optimize transmission and storage resources on the IEEE 14-bus test network and compare our solution to one generated by standard planning with a carbon tax. Our solution significantly reduces emissions for the same levelized cost of electricity.

Authors: Anthony Degleris (Stanford University); Lucas Fuentes (Stanford); Abbas El Gamal (Stanford University); Ram Rajagopal (Stanford University)

Power and energy systems Climate policy Other
NeurIPS 2021 Amortized inference of Gaussian process hyperparameters for improved concrete strength trajectory prediction (Papers Track)
Abstract and authors: (click to expand)

Abstract: Designing and utilizing alternative concrete formulations which supplant the use of ordinary portland cement with alternative binders have been identified as central goals in reducing the greenhouse gas impact of the concrete industry. Given the variability in availability and quality of alternatives, these goals call for an optimal design of experiment approach to designing formulations, which can be adapted to local needs. The realization of this goal hinges on an ability to predict key properties. Here, we present and benchmark a Gaussian process (GP) model for predicting the trajectory of concrete strength, an essential performance measure. GPs are a desirable model class for the application because of their ability to estimate uncertainty and update predictions given additional data. In this work, rather than manually tuning hyperparameters for different concrete mix models, we propose a new method based on amortized inference leveraging mixture attributes, leading to models which are better fit for use in Bayesian optimization of concrete formulation. We demonstrate the success of the approach using a large, industrial concrete dataset.

Authors: Kristen Severson (Microsoft Research); Olivia Pfeiffer (MIT); Jie Chen (IBM Research); Kai Gong (MIT); Jeremy Gregory (Massachusetts Institute of Technology); Richard Goodwin (IBM Research); Elsa Olivetti (Massachusetts Institute of Technology)

Causal and Bayesian methods Heavy industry and manufacturing
NeurIPS 2021 A data integration pipeline towards reliable monitoring of phytoplankton and early detection of harmful algal blooms (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change is making oceans warmer and more acidic. Under these conditions phytoplankton can produce harmful algal blooms which cause rapid oxygen depletion and consequent death of marine plants and animals. Some species are even capable of releasing toxic substances endangering water quality and human health. Monitoring of phytoplankton and early detection of harmful algal blooms is essential for protection of marine flaura and fauna. Recent technological advances have enabled in-situ plankton image capture in real-time at low cost. However, available phytoplankton image databases have several limitations that prevent the practical usage of artificial intelligent models. We present a pipeline for integration of heterogeneous phytoplankton image datasets from around the world into a unified database that can ultimately serve as a benchmark dataset for phytoplankton research and therefore act as an important tool in building versatile machine learning models for climate adaptation planning. A machine learning model for early detection of harmful algal blooms is part of ongoing work.

Authors: Bruna Guterres (Universidade Federal do Rio Grande - FURG); Sara khalid (University of Oxford); Marcelo Pias (Federal University of Rio Grande); Silvia Botelho (Federal University of Rio Grande)

Disaster prediction, management, and relief Ecosystems and natural systems Classification, regression, and supervised learning
NeurIPS 2021 Identifying Distributional Differences in Convective Evolution Prior to Rapid Intensification in Tropical Cyclones (Papers Track)
Abstract and authors: (click to expand)

Abstract: Tropical cyclone (TC) intensity forecasts are issued by human forecasters who evaluate spatio-temporal observations (e.g., satellite imagery) and model output (e.g., numerical weather prediction, statistical models) to produce forecasts every 6 hours. Within these time constraints, it can be challenging to draw insight from such data. While high-capacity machine learning methods are well suited for prediction problems with complex sequence data, extracting interpretable scientific information with such methods is difficult. Here we leverage powerful AI prediction algorithms and classical statistical inference to identify patterns in the evolution of TC convective structure leading up to the rapid intensification of a storm, hence providing forecasters and scientists with key insight into TC behavior.

Authors: Irwin H McNeely (Carnegie Mellon University); Galen Vincent (Carnegie Mellon University); Rafael Izbicki (UFSCar); Kimberly Wood (Mississippi State University); Ann B. Lee (Carnegie Mellon University)

Disaster prediction, management, and relief Interpretable ML
NeurIPS 2021 Predicting Atlantic Multidecadal Variability (Papers Track)
Abstract and authors: (click to expand)

Abstract: Atlantic Multidecadal Variability (AMV) describes variations of North Atlantic sea surface temperature with a typical cycle of between 60 and 70 years. AMV strongly impacts local climate over North America and Europe, therefore prediction of AMV, especially the extreme values, is of great societal utility for understanding and responding to regional climate change. This work tests multiple machine learning models to improve the state of AMV prediction from maps of sea surface temperature, salinity, and sea level pressure in the North Atlantic region. We use data from the Community Earth System Model 1 Large Ensemble Project, a state-of-the-art climate model with 3,440 years of data. Our results demonstrate that all of the models we use outperform the traditional persistence forecast baseline. Predicting the AMV is important for identifying future extreme temperatures and precipitation as well as hurricane activity, in Europe and North America up to 25 years in advance.

Authors: Glenn Liu (Massachusetts Institute of Technology); Peidong Wang (MIT); Matthew Beveridge (Massachusetts Institute of Technology); Young-Oh Kwon (Woods Hole Oceanographic Institution); Iddo Drori (MIT)

Climate and Earth science Classification, regression, and supervised learning Other
NeurIPS 2021 Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach (Papers Track)
Abstract and authors: (click to expand)

Abstract: Europe was hit by several, disastrous heat and drought events in recent summers. Besides thermodynamic influences, such hot and dry extremes are driven by certain atmospheric situations including anticyclonic conditions. Effects of climate change on atmospheric circulations are complex and many open research questions remain in this context, e.g., on future trends of anticyclonic conditions. Based on the combination of a catalog of labeled circulation patterns and spatial atmospheric variables, we propose a smoothed convolutional neural network classifier for six types of anticyclonic circulations that are associated with drought and heat. Our work can help to identify important drivers of hot and dry extremes in climate simulations, which allows to unveil the impact of climate change on these drivers. We address various challenges inherent to circulation pattern classification that are also present in other climate patterns, e.g., subjective labels and unambiguous transition periods.

Authors: Magdalena Mittermeier (Ludwig-Maximilians-Universität München); Maximilian Weigert (Ludwig-Maximilians-Universität München); David Ruegamer (LMU Munich)

Climate and Earth science Classification, regression, and supervised learning
NeurIPS 2021 Learning to identify cracks on wind turbine blade surfaces using drone-based inspection images (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wind energy is expected to be one of the leading ways to achieve the goals of the Paris Agreement but it in turn heavily depends on effective management of its operations and maintenance (O&M) costs. Blade failures account for one-third of all O&M costs thus making accurate detection of blade damages, especially cracks, very important for sustained operations and cost savings. Traditionally, damage inspection has been a completely manual process thus making it subjective, error-prone, and time-consuming. Hence in this work, we bring more objectivity, scalability, and repeatability in our damage inspection process, using deep learning, to miss fewer cracks. We build a deep learning model trained on a large dataset of blade damages, collected by our drone-based inspection, to correctly detect cracks. Our model is already in production and has processed more than a million damages with a recall of 0.96. We also focus on model interpretability using class activation maps to get a peek into the model workings. The model not only performs as good as human experts but also better in certain tricky cases. Thus, in this work, we aim to increase wind energy adoption by decreasing one of its major hurdles - the O&M costs resulting from missing blade failures like cracks.

Authors: Akshay B Iyer (SkySpecs, Inc.); Linh V Nguyen (SkySpecs Inc); Shweta Khushu (SkySpecs Inc.)

Power and energy systems Climate finance and economics Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2021 Evaluating Pretraining Methods for Deep Learning on Geophysical Imaging Datasets (Papers Track)
Abstract and authors: (click to expand)

Abstract: Machine learning has the potential to automate the analysis of vast amounts of raw geophysical data, allowing scientists to monitor changes in key aspects of our climate such as cloud cover in real-time and at fine spatiotemporal scales. However, the lack of large labeled training datasets poses a significant barrier for effectively applying machine learning to these applications. Transfer learning, which involves first pretraining a neural network on an auxiliary “source” dataset and then finetuning on the “target” dataset, has been shown to improve accuracy for machine learning models trained on small datasets. Across prior work on machine learning for geophysical imaging, different choices are made about what data to pretrain on, and the impact of these choices on model performance is unclear. To address this, we systematically explore various settings of transfer learning for cloud classification, cloud segmentation, and aurora classification. We pretrain on different source datasets, including the large ImageNet dataset as well as smaller geophysical datasets that are more similar to the target datasets. We also experiment with multiple transfer learning steps where we pretrain on more than one source dataset. Despite the smaller source datasets’ similarity to the target datasets, we find that pretraining on the large, general-purpose ImageNet dataset yields significantly better results across all of our experiments. Transfer learning is especially effective for smaller target datasets, and in these cases, using multiple source datasets can give a marginal added benefit.

Authors: James Chen (Kirby School)

Computer vision and remote sensing Earth science and monitoring Meta- and transfer learning
NeurIPS 2021 An Automated System for Detecting Visual Damages of Wind Turbine Blades (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wind energy’s ability to compete with fossil fuels on a market level depends on lowering wind’s high operational costs. Since damages on wind turbine blades are the leading cause for these operational problems, identifying blade damages is critical. However, recent works in visual identification of blade damages are still experimental and focus on optimizing the traditional machine learning metrics such as IoU. In this paper, we argue that pushing models to production long before achieving the "optimal" model performance can still generate real value for this use case. We discuss the performance of Blue, our damage’s suggestion model in production and how this system works in coordination with humans as part of a commercialized product and how it can contribute towards lowering wind energy’s operational costs.

Authors: Linh V Nguyen (SkySpecs Inc); Shweta Khushu (SkySpecs Inc.); Akshay B Iyer (SkySpecs, Inc.)

Computer vision and remote sensing Climate finance and economics Classification, regression, and supervised learning
NeurIPS 2021 Power System Dynamic Simulation Using Fourier Neural Operators (Papers Track)
Abstract and authors: (click to expand)

Abstract: With the ambition of reducing carbon emissions and mitigating climate change, many regions have set up the goal to generate electricity with close to 100% renewables. However, actual renewable generations are often curtailed by operators because it is too hard to check the dynamic stability of electric grid under the high uncertainties introduced by the renewables. The dynamics of a power grid are governed by a large number of nonlinear ordinary differential equations (ODEs). To safely operate the system, operators need to check that the states described by this set of ODEs stay within prescribed limits after various potential faults. But solving these ODEs are very time-consuming using current numerical solvers and machine learning approaches have been proposed to reduce the computational time. Current methods generally suffer from overfitting and failures to predict unstable behaviors. This paper proposes a novel framework for power system dynamic simulation using Fourier neural operator to learn in the frequency domain. The system topology and fault information are encoded through a 3D Fourier transform. We show that the proposed approach can speed up the computation by orders of magnitude while also remain high accuracy for different fault types.

Authors: Wenqi Cui (University of Washington); Weiwei Yang (Microsoft Research); Baosen Zhang (University of Washington)

Power and energy systems Classification, regression, and supervised learning
NeurIPS 2021 HyperionSolarNet: Solar Panel Detection from Aerial Images (Papers Track)
Abstract and authors: (click to expand)

Abstract: With the effects of global climate change impacting the world, collective efforts are needed to reduce greenhouse gas emissions. The energy sector is the single largest contributor to climate change and many efforts are focused on reducing dependence on carbon-emitting power plants and moving to renewable energy sources, such as solar power. A comprehensive database of the location of solar panels is important to assist analysts and policymakers in defining strategies for further expansion of solar energy. In this paper we focus on creating a world map of solar panels. We identify locations and total surface area of solar panels within a given geographic area. We use deep learning methods for automated detection of solar panel locations and their surface area using aerial imagery. The framework, which consists of a two-branch model using an image classifier in tandem with a semantic segmentation model, is trained on our created dataset of satellite images. Our work provides an efficient and scalable method for detecting solar panels, achieving an accuracy of 0.96 for classification and an IoU score of 0.82 for segmentation performance.

Authors: Poonam Parhar (UCBerkeley); Ryan Sawasaki (UCBerkeley); Alberto Todeschini (UC Berkeley); Colorado Reed (UC Berkeley); Hossein Vahabi (University California Berkeley); Nathan Nusaputra (UC Berkeley); Felipe Vergara (UC Berkeley)

Power and energy systems Buildings and cities Climate policy Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2021 Prediction of Household-level Heat-Consumption using PSO enhanced SVR Model (Papers Track)
Abstract and authors: (click to expand)

Abstract: In combating climate change, an effective demand-based energy supply operation of the district energy system (DES) for heating or cooling is indispensable. As a consequence, an accurate forecast of heat consumption on the consumer side poses an important first step towards an optimal energy supply. However, due to the non-linearity and non-stationarity of heat consumption data, the prediction of the thermal energy demand of DES remains challenging. In this work, we propose a forecasting framework for thermal energy consumption within a district heating system (DHS) based on kernel Support Vector Regression (kSVR) using real-world smart meter data. Particle Swarm Optimization (PSO) is employed to find the optimal hyper-parameter for the kSVR model which leads to the superiority of the proposed methods when compared to a state-of-the-art ARIMA model. The average MAPE is reduced to 2.07% and 2.64% for the individual meter-specific forecasting and for forecasting of societal consumption, respectively.

Authors: Satyaki Chatterjee (Pattern Recognition Lab, FAU Erlangen-Nuremberg); Siming Bayer (Pattern Recognition Lab, Friedrich-Alexander University); Andreas K Maier (Pattern Recognition Lab, FAU Erlangen-Nuremberg)

Classification, regression, and supervised learning Power and energy systems Other Time-series analysis
NeurIPS 2021 EcoLight: Reward Shaping in Deep Reinforcement Learning for Ergonomic Traffic Signal Control (Papers Track)
Abstract and authors: (click to expand)

Abstract: Mobility, the environment, and human health are all harmed by sub-optimal control policies in transportation systems. Intersection traffic signal controllers are a crucial part of today's transportation infrastructure, as sub-optimal policies may lead to traffic jams and as a result increased levels of air pollution and wasted time. Many adaptive traffic signal controllers have been proposed in the literature, but research on their relative performance differences is limited. On the other hand, to the best of our knowledge there has been no work that directly targets CO2 emission reduction, even though pollution is currently a critical issue. In this paper, we propose a reward shaping scheme for various RL algorithms that not only produces lowers CO2 emissions, but also produces respectable outcomes in terms of other metrics such as travel time. We compare multiple RL algorithms --- sarsa, and A2C --- as well as diverse scenarios with a mix of different road users emitting varied amounts of pollution.

Authors: Pedram Agand (Simon Fraser University); Alexey Iskrov (Breeze Labs Inc.); Mo Chen (Simon Fraser University)

Transportation Power and energy systems Reinforcement learning and control
NeurIPS 2021 Data Driven Study of Estuary Hypoxia (Papers Track)
Abstract and authors: (click to expand)

Abstract: This paper presents a data driven study of dissolved oxygen times series collected in Atlantic Canada. The main motivation of presented work was to evaluate if machine learning techniques could help to understand and anticipate hypoxic episodes in nutrient-impacted estuaries, a phenomenon that is exacerbated by increasing temperature expected to arise due to changes in climate. A major constraint was to limit ourselves to the use of dissolved oxygen time series only. Our preliminary findings shows that recurring neural networks and in particular LSTM may be suitable to predict short horizon levels while traditional results could benefit in longer range hypoxia prevention.

Authors: Monwer Hussain (University of New-Brunswick); Guillaume Durand (National Research Council Canada); Michael Coffin (Department of Fisheries and Oceans Canada); Julio J Valdés (National Research Council Canada); Luke Poirier (Department of Fisheries and Oceans Canada)

Ecosystems and natural systems Time-series analysis
NeurIPS 2021 Safe Learning for Voltage Control (Papers Track)
Abstract and authors: (click to expand)

Abstract: Inverter-based distributed energy resources provide the possibility for fast time-scale voltage control by quickly adjusting their reactive power. The power-electronic interfaces allow these resources to follow almost arbitrary control law, while designing these decentralized controllers is nontrivial. Reinforcement learning (RL) approaches are becoming increasingly popular to search for policy parameterized by neural networks. But it is difficult to enforce that the learned controllers stabilize the system. This paper proposes a safe learning approach for voltage control with stability guarantees. Using Lyapunov stability theory, we explicitly derive the structure of neural network-based controllers such that they guarantee system stability by design. A decentralized RL framework is constructed to train local neural network controller at each bus in a model-free setting.

Authors: Wenqi Cui (University of Washington); Jiayi Li (University of Washington); Baosen Zhang (University of Washington)

Power and energy systems Reinforcement learning and control
NeurIPS 2021 NoFADE: Analyzing Diminishing Returns on CO2 Investment (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change continues to be a pressing issue that currently affects society at-large. It is important that we as a society, including the Computer Vision (CV) community take steps to limit our impact on the environment. In this paper, we (a) analyze the effect of diminishing returns on CV methods, and (b) propose a ``NoFADE'': a novel entropy-based metric to quantify model--dataset--complexity relationships. We show that some CV tasks are reaching saturation, while others are almost fully saturated. In this light, NoFADE allows the CV community to compare models and datasets on a similar basis, establishing an agnostic platform.

Authors: Andre Fu (University of Toronto); Justin B Tran (University of Toronto); Andy Xie (University of Toronto); Jonathan T Spraggett (University of Toronto); Elisa Ding (University of Toronto); Chang-Won Lee (University of Toronto); Kanav Singla (University of Toronto); Mahdi S. Hosseini (University of New Brunswick); Konstantinos N Plataniotis (UofT)

Carbon capture and sequestration Computer vision and remote sensing
NeurIPS 2021 High-resolution rainfall-runoff modeling using graph neural network (Papers Track)
Abstract and authors: (click to expand)

Abstract: Time-series modeling has shown great promise in recent studies using the latest deep learning algorithms such as LSTM (Long Short-Term Memory). These studies primarily focused on watershed-scale rainfall-runoff modeling or streamflow forecasting, but the majority of them only considered a single watershed as a unit. Although this simplification is very effective, it does not take into account spatial information, which could result in significant errors in large watersheds. Several studies investigated the use of GNN (Graph Neural Networks) for data integration by decomposing a large watershed into multiple sub-watersheds, but each sub-watershed is still treated as a whole, and the geoinformation contained within the watershed is not fully utilized. In this paper, we propose the GNRRM (Graph Neural Rainfall-Runoff Model), a novel deep learning model that makes full use of spatial information from high-resolution precipitation data, including flow direction and geographic information. When compared to baseline models, GNRRM has less over-fitting and significantly improves model performance. Our findings support the importance of hydrological data in deep learning-based rainfall-runoff modeling, and we encourage researchers to include more domain knowledge in their models.

Authors: Zhongrun Xiang (University of Iowa); Ibrahim Demir (The University of Iowa)

Time-series analysis Agriculture, forestry and other land use Climate and Earth science Disaster prediction, management, and relief Earth science and monitoring Ecosystems and natural systems Classification, regression, and supervised learning Data mining
NeurIPS 2021 Machine Learning for Snow Stratigraphy Classification (Papers Track)
Abstract and authors: (click to expand)

Abstract: Snow-layer segmentation and classification is an essential diagnostic task for a wide variety of cryospheric science and climate research applications. To this end a Snow Micro Pen (SMP) can be used - a portable high-resolution snow penetrometer. However, the penetration-force measurements of the SMP must be labeled manually, which is a time-intensive task that requires training and becomes infeasible for large datasets. Here, we evaluate how well machine learning models can automatically segment and classify SMP profiles. Fourteen different models are trained on the MOSAiC SMP dataset, a unique and large SMP dataset of snow on Arctic sea-ice profiles. Depending on the user's task and needs, the long short-term memory neural network and the random forests are performing the best. The findings presented here facilitate and accelerate SMP data analysis and in consequence, help scientists to analyze the effects of climate change on the cryosphere more efficiently.

Authors: Julia Kaltenborn (McGill University)

Other Earth science and monitoring Classification, regression, and supervised learning Time-series analysis
NeurIPS 2021 DEM Super-Resolution with EfficientNetV2 (Papers Track)
Abstract and authors: (click to expand)

Abstract: Efficient climate change monitoring and modeling rely on high-quality geospatial and environmental datasets. Due to limitations in technical capabilities or resources, the acquisition of high-quality data for many environmental disciplines is costly. Digital Elevation Model (DEM) datasets are such examples whereas their low-resolution versions are widely available, high-resolution ones are scarce. In an effort to rectify this problem, we propose and assess an EfficientNetV2 based model. The proposed model increases the spatial resolution of DEMs up to 16 times without additional information.

Authors: Bekir Z Demiray (University of Iowa); Muhammed A Sit (The University of Iowa); Ibrahim Demir (The University of Iowa)

Computer vision and remote sensing Disaster prediction, management, and relief Earth science and monitoring Classification, regression, and supervised learning
NeurIPS 2021 Learning to Dissipate Traffic Jams with Piecewise Constant Control (Papers Track)
Abstract and authors: (click to expand)

Abstract: Greenhouse gases (GHGs), particularly carbon dioxide, are a key contributor to climate change. The transportation sector makes up 35% of CO2 emissions in the US and more than 70% of it is due to land transport. Previous work shows that simple driving interventions have the ability to significantly improve traffic flow on the road. Recent work shows that 5% of vehicles using piecewise constant controllers, designed to be compatible to the reaction times of human drivers, can prevent the formation of stop-and-go traffic congestion on a single-lane circular track, thereby mitigating land transportation emissions. Our work extends these results to consider more extreme traffic settings, where traffic jams have already formed, and environments with limited cooperation. We show that even with the added realism of these challenges, piecewise constant controllers, trained using deep reinforcement learning, can essentially eliminate stop-and-go traffic when actions are held fixed for up to 5 seconds. Even up to 10-second action holds, such controllers show congestion benefits over a human driving baseline. These findings are a stepping-stone for near-term deployment of vehicle-based congestion mitigation.

Authors: Mayuri Sridhar (MIT); Cathy Wu ()

Transportation Reinforcement learning and control
NeurIPS 2021 Multi-objective Reinforcement Learning Controller for Multi-Generator Industrial Wave Energy Converter (Papers Track)
Abstract and authors: (click to expand)

Abstract: Waves are one of the greatest sources of renewable energy and are a promising resource to tackle climate challenges by decarbonizing energy generation. Lowering the Levelized Cost of Energy (LCOE) for wave energy converters is key to competitiveness with other forms of clean energy like wind and solar. Also, the complexity of control has gone up significantly with the state-of-the-art multi-generator multi-legged industrial Wave Energy Converters (WEC). This paper introduces a Multi-Agent Reinforcement Learning controller (MARL) architecture that can handle these multiple objectives for LCOE, helping the increase in energy capture efficiency, boosting revenue, reducing structural stress to limit maintenance and operating cost, and adaptively and proactively protect the wave energy converter from catastrophic weather events, preserving investments and lowering effective capital cost. We use a MARL implementing proximal policy optimization (PPO) with various optimizations to help sustain the training convergence in the complex hyperplane. The MARL is able to better control the reactive forces of the generators on multiple tethers (legs) of WEC than the commonly deployed spring damper controller. The design for trust is implemented to assure the operation of WEC within a safe zone of mechanical compliance and guarantee mechanical integrity. This is achieved through reward shaping for multiple objectives of energy capture and penalty for harmful motions to minimize stress and lower the cost of maintenance. We achieved double-digit gains in energy capture efficiency across the waves of different principal frequencies over the baseline Spring Damper controller with the proposed MARL controllers.

Authors: Soumyendu Sarkar (Hewlett Packard Enterprise); Vineet Gundecha (Hewlett Packard Enterpise); Alexander Shmakov (UC Irvine); Sahand Ghorbanpour (Hewlett Packard Enterprise); Ashwin Ramesh Babu (Hewlett Packard Enterprise Labs); Paolo Faraboschi (HPE); mathieu Cocho (Carnegie Clean Energy); Alexandre Pichard (Carnegie Clean Energy); Jonathan Fievez (Carnegie Clean Energy)

Power and energy systems Reinforcement learning and control
NeurIPS 2021 Resolving Super Fine-Resolution SIF via Coarsely-Supervised U-Net Regression (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change presents challenges to crop productivity, such as increasing the likelihood of heat stress and drought. Solar-Induced Chlorophyll Fluorescence (SIF) is a powerful way to monitor how crop productivity and photosynthesis are affected by changing climatic conditions. However, satellite SIF observations are only available at a coarse spatial resolution (e.g. 3-5km) in most places, making it difficult to determine how individual crop types or farms are doing. This poses a challenging coarsely-supervised regression task; at training time, we only have access to SIF labels at a coarse resolution (3 km), yet we want to predict SIF at a very fine spatial resolution (30 meters), a 100x increase. We do have some fine-resolution input features (such as Landsat reflectance) that are correlated with SIF, but the nature of the correlation is unknown. To address this, we propose Coarsely-Supervised Regression U-Net (CSR-U-Net), a novel approach to train a U-Net for this coarse supervision setting. CSR-U-Net takes in a fine-resolution input image, and outputs a SIF prediction for each pixel; the average of the pixel predictions is trained to equal the true coarse-resolution SIF for the entire image. Even though this is a very weak form of supervision, CSR-U-Net can still learn to predict accurately, due to its inherent localization abilities, plus additional enhancements that facilitate the incorporation of scientific prior knowledge. CSR-U-Net can resolve fine-grained variations in SIF more accurately than existing averaging-based approaches, which ignore fine-resolution spatial variation during training. CSR-U-Net could also be useful for a wide range of "downscaling'" problems in climate science, such as increasing the resolution of global climate models.

Authors: Joshua Fan (Cornell University); Di Chen (Cornell University); Jiaming Wen (Cornell University); Ying Sun (Cornell University); Carla P Gomes (Cornell University)

Agriculture, forestry and other land use Ecosystems and natural systems Computer vision and remote sensing Unsupervised and semi-supervised learning
NeurIPS 2021 PreDisM: Pre-Disaster Modelling With CNN Ensembles for At-Risk Communities (Papers Track)
Abstract and authors: (click to expand)

Abstract: The machine learning community has recently had increased interest in the climate and disaster damage domain due to a marked increased occurrences of natural hazards (e.g., hurricanes, forest fires, floods, earthquakes). However, not enough attention has been devoted to mitigating probable destruction from impending natural hazards. We explore this crucial space by predicting building-level damages on a before-the-fact basis that would allow state actors and non-governmental organizations to be best equipped with resource distribution to minimize or preempt losses. We introduce PreDisM that employs an ensemble of ResNets and fully connected layers over decision trees to capture image-level and meta-level information to accurately estimate weakness of man-made structures to disaster-occurrences. Our model performs well and is responsive to tuning across types of disasters and highlights the space of preemptive hazard damage modelling.

Authors: Vishal Anand (Columbia University); Yuki Miura (Columbia University)

Disaster prediction, management, and relief Buildings and cities Computer vision and remote sensing Interpretable ML
NeurIPS 2021 A hybrid convolutional neural network/active contour approach to segmenting dead trees in aerial imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Dead trees constitute 8% of the global carbon stocks and are decomposed by several natural factors, e.g. climate and insects. Accurate detection and modeling of dead trees is critical to understand forest ecology, the carbon cycle and decomposers. We present a novel method to construct precise shape contours of dead trees from aerial photographs by combining established convolutional neural networks with a novel active contour model in an energy minimization framework. Our approach yields greater accuracy over state-of-the-art in terms of precision, recall, and intersection over union of detected dead trees. This improved performance is essential to meet the emerging challenges caused by climate change (and other man-made perturbations to the systems) and estimate carbon stock decay rates.

Authors: Jacquelyn Shelton (Hong Kong Polytechnic University); Przemyslaw Polewski (TomTom Location Technology Germany GmbH); Drew J Lipman (MITRE corp.); Marco Heurich (Bavarian Forest National Park); Wei Yao (The Hong Kong Polytechnic University)

Computer vision and remote sensing Carbon capture and sequestration Ecosystems and natural systems Agriculture, forestry and other land use
NeurIPS 2021 Semi-Supervised Classification and Segmentation on High Resolution Aerial Images (Papers Track)
Abstract and authors: (click to expand)

Abstract: FloodNet is a high-resolution image dataset acquired by a small UAV platform, DJI Mavic Pro quadcopters, after Hurricane Harvey. The dataset presents a unique challenge of advancing the damage assessment process for post-disaster scenarios using unlabeled and limited labeled dataset. We propose a solution to address their classification and semantic segmentation challenge. We approach this problem by generating pseudo labels for both classification and segmentation during training and slowly incrementing the amount by which the pseudo label loss affects the final loss. Using this semi-supervised method of training helped us improve our baseline supervised loss by a huge margin for classification, allowing the model to generalize and perform better on the validation and test splits of the dataset. In this paper, we compare and contrast the various methods and models for image classification and semantic segmentation on the FloodNet dataset.

Authors: Sahil S Khose (Manipal Institute of Technology); Abhiraj Tiwari (Manipal Institute of Technology); Ankita Ghosh (Manipal Institute of Technology)

Disaster prediction, management, and relief Classification, regression, and supervised learning Meta- and transfer learning Unsupervised and semi-supervised learning
NeurIPS 2021 Reducing the barriers of acquiring species-level ground-truth on passive acoustic monitoring data using neural network assisted intelligent sampling techniques (Papers Track)
Abstract and authors: (click to expand)

Abstract: The potential of passive acoustic monitoring (PAM) as a method to reveal the consequences of climate change on the biodiversity that make up natural soundscapes can be undermined by the discrepancy between the low barrier of entry to acquire large field audio datasets and the higher barrier of acquiring reliable species level training, validation, and test subsets from the field audio. These subsets from a deployment are often required to verify any machine learning models used to assist researchers in understanding the local biodiversity. Especially as many models convey promising results from various sources that may not translate to the collected field audio. Labeling such datasets is a resource intensive process due to the lack of experts capable of identifying bioacoustics at a species level as well as the overwhelming size of many PAM audiosets. To address this challenge, we have tested different sampling techniques on an audio dataset collected over a two-week long August audio array deployment on the Scripps Coastal Reserve (SCR) Biodiversity Trail in La Jolla, California. These sampling techniques involve creating four subsets using stratified random sampling, limiting samples to the daily bird vocalization peaks, and using a hybrid convolutional neural network (CNN) and recurrent neural network (RNN) trained for bird presence/absence audio classification. We found that a stratified random sample baseline only achieved a bird presence rate of 44\% in contrast with a sample that randomly selected clips with high hybrid CNN-RNN predictions that were collected during bird activity peaks at dawn and dusk yielding a bird presence rate of 95\%. The significantly higher bird presence rate demonstrates how intelligent, machine learning-assisted selection of audio data can significantly reduce the amount of time that domain experts listen to audio without vocalizations of interest while building a ground truth for machine learning models.

Authors: Jacob G Ayers (UC San Diego); Ryan Kastner (University of California San Diego)

Ecosystems and natural systems Computer vision and remote sensing
NeurIPS 2021 Two-phase training mitigates class imbalance for camera trap image classification with CNNs (Papers Track)
Abstract and authors: (click to expand)

Abstract: By leveraging deep learning to automatically classify camera trap images, ecologists can monitor biodiversity conservation efforts and the effects of climate change on ecosystems more efficiently. Due to the imbalanced class-distribution of camera trap datasets, current models are biased towards the majority classes. As a result, they obtain good performance for a few majority classes but poor performance for many minority classes. We used two-phase training to increase the performance for these minority classes. We trained, next to a baseline model, four models that implemented a different versions of two-phase training on a subset of the highly imbalanced Snapshot Serengeti dataset. Our results suggest that two-phase training can improve performance for many minority classes, with limited loss in performance for the other classes. We find that two-phase training based on majority undersampling increases class-specific F1-scores up to 3.0\%. We also find that two-phase training outperforms using only oversampling or undersampling by 6.1\% in F1-score on average. Finally, we find that a combination of over- and undersampling leads to a better performance than using them individually.

Authors: Ruben Cartuyvels (KULeuven)

Ecosystems and natural systems Computer vision and remote sensing
NeurIPS 2021 Capturing Electricity Market Dynamics in the Optimal Trading of Strategic Agents using Neural Network Constrained Optimization (Papers Track)
Abstract and authors: (click to expand)

Abstract: In competitive electricity markets the optimal trading problem of an electricity market agent is commonly formulated as a bi-level program, and solved as mathematical program with equilibrium constraints (MPEC). In this paper, an alternative paradigm, labeled as mathematical program with neural network constraint (MPNNC), is developed to incorporate complex market dynamics in the optimal bidding strategy. This method uses input-convex neural networks (ICNNs) to represent the mapping between the upper-level (agent) decisions and the lower-level (market) outcomes, i.e., to replace the lower-level problem by a neural network. In a comparative analysis, the optimal bidding problem of a load agent is formulated via the proposed MPNNC and via the classical bi-level programming method, and compared against each other.

Authors: Mihály Dolányi (KU Leuven); Kenneth Bruninx (KU Leuven); Jean-François Toubeau (Faculté Polytechnique (FPMs), Université de Mons (UMONS)); Erik Delaue (KU Leuven)

Hybrid physical models Climate finance and economics Recommender systems
NeurIPS 2021 Leverage Machine Learning to Predict the Autoconversion Rates from Satellite Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: One way of reducing the uncertainty involved in determining the radiative forcing of the Earth is by understanding the interaction between aerosols, clouds, and precipitation processes, which can be studied using high-resolution simulations such as the ICOsahedral Non-hydrostatic Large-Eddy Model (ICON-LEM). However, due to the extremely high computational cost required, this model can only be run for a limited amount of time within a limited area. To address this, we developed models using emerging machine learning approaches that leverage a plethora of satellite observations which provide long-term global spatial coverage. In particular, we developed machine learning models capable of capturing the key process of precipitation formation which greatly control cloud lifetime, namely autoconversion rates – the term used to describe the collision and coalescence of cloud droplets responsible for raindrop formation. We validate the performance of our models against the simulation data, and the results showed that our models are capable of predicting the autoconversion rate fairly well, with the best model (DNN) achieving an SSIM index of 96.80%.

Authors: Maria C Novitasari (University College London); Johannes Quaas (University of Leipzig); Miguel Rodrigues (University College London)

Classification, regression, and supervised learning Climate and Earth science Computer vision and remote sensing
NeurIPS 2021 Towards Automatic Transformer-based Cloud Classification and Segmentation (Papers Track)
Abstract and authors: (click to expand)

Abstract: Clouds have been demonstrated to have a huge impact on the energy balance, temperature, and weather of the Earth. Classification and segmentation of clouds and coverage factors is crucial for climate modelling, meteorological studies, solar energy industry, and satellite communication. For example, clouds have a tremendous impact on short-term predictions or 'nowcasts' of solar irradiance and can be used to optimize solar power plants and effectively exploit solar energy. However even today, cloud observation requires the intervention of highly-trained professionals to document their findings, which introduces bias. To overcome these issues and contribute to climate change technology, we propose, to the best of our knowledge, the first two transformer-based models applied to cloud data tasks. We use the CCSD Cloud classification dataset and achieve 90.06% accuracy, outperforming all other methods. To demonstrate the robustness of transformers in this domain, we perform Cloud segmentation on SWIMSWG dataset and achieve 83.2% IoU, also outperforming other methods. With this, we signal a potential shift away from pure CNN networks.

Authors: Roshan Roy (Birla Institute of Technology and Science, Pilani); Ahan M R (BITS Pilani); Vaibhav Soni (MANIT Bhopal); Ashish Chittora (BITS Pilani)

Computer vision and remote sensing Climate and Earth science Earth science and monitoring Classification, regression, and supervised learning Data mining
NeurIPS 2021 Scalable coastal inundation mapping using machine learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Coastal flooding is a significant climate hazard with impacts across economic sectors and society. This study provides a proof of concept for data-driven models for coastal flood inundation at the country scale, incorporating storm dynamics and geospatial characteristics to improve upon simpler geomorphological models. The best fit machine learning model scores an AUC of 0.92 in predicting flooded locations. For a case study storm event in December 2013 we find that all models over-predict flood extents, but that the machine learning model extents were closest to those observed.

Authors: Ophelie Meuriot (IBM Research Europe); Anne Jones (IBM Research)

Classification, regression, and supervised learning Climate and Earth science Other
NeurIPS 2021 Machine Learning in Automating Carbon Sequestration Site Assessment (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Carbon capture and sequestration are viewed as an indispensable component to achieve the Paris Agreement climate goal, i.e., keep the global warming within 2 degrees Celsius from pre-industrial levels. Once captured, most CO2 needs to be stored securely for at least decades, preferably in deep underground geological formations. It is economical to inject and store CO2 near/around a depleted gas/oil reservoir or well, where a geological trap for CO2 with good sealing properties and some minimum infrastructure exist. In this proposal, with our preliminary work, it is shown that Machine Learning tools like Optical Character Recognition and Natural Language Processing can aid in screening and selection of injection sites for CO2 storage, facilitate identification of possible CO2 leakage paths in the subsurface, and assist in locating a depleted gas/oil well suitable for CO2 injection and long-term storage. The automated process based on ML tools can also drastically decrease the decision-making cycle time in site selection and assessment phase by reducing human effort. In the longer term, we expect ML tools like Deep Neural Networks to be utilized in CO2 storage monitoring, injection optimization etc. By injecting CO2 into a trapping geological underground formation in a safe and sustainable manner, the Energy industry can contribute substantially to reducing global warming and achieving the goals of the Paris Agreement by the end of this century.

Authors: Jay Chen (Shell); Ligang Lu (Shell); Mohamed Sidahmed (Shell); Taixu Bai (Shell); Ilyana Folmar (Shell); Puneet Seth (Shell); Manoj Sarfare (Shell); Duane Mikulencak (Shell); Ihab Akil (Shell)

Carbon capture and sequestration Climate finance and economics Active learning Computer vision and remote sensing
NeurIPS 2021 A Risk Model for Predicting Powerline-induced Wildfires in Distribution System (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The power grid is one of the most common causes of wildfires that result in tremendous economic loss and significant life risk. In this study, we propose to use machine learning techniques to build a risk model for predicting powerline-induced wildfires in distribution system. We collect weather, vegetation, and infrastructure data for all feeders in Pacific Gas & Electricity territory. This study will contribute to a deeper understanding of powerline-induced wildfire prediction and provide valuable suggestions for wildfire mitigation planning.

Authors: Mengqi Yao (University of California Berkeley)

Disaster prediction, management, and relief Power and energy systems Classification, regression, and supervised learning Data mining
NeurIPS 2021 Detecting Abandoned Oil Wells Using Machine Learning and Semantic Segmentation (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Around the world, there are millions of unplugged abandoned oil and gas wells, leaking methane into the atmosphere. The locations of many of these wells, as well as their greenhouse gas emissions impacts, are unknown. Machine learning methods in computer vision and remote sensing, such as semantic segmentation, have made it possible to quickly analyze large amounts of satellite imagery to detect salient information. This project aims to automatically identify abandoned oil wells in the province of Alberta, Canada to aid in estimating emissions and plugging high-emitting wells.

Authors: Michelle Lin (McGill University); David Rolnick (McGill University, Mila)

Power and energy systems Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2021 Machine learning-enabled model-data integration for predicting subsurface water storage (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Subsurface water storage (SWS) is a key variable of the climate system and a storage component for precipitation and radiation anomalies, inducing persistence in the climate system. It plays a critical role in climate-change projections and can mitigate the impacts of climate change on ecosystems. However, because of the difficult accessibility of the underground, hydrologic properties and dynamics of SWS are poorly known. Direct observations of SWS are limited, and accurate incorporation of SWS dynamics into Earth system land models remains challenging. We propose a machine learning-enabled model-data integration framework to improve the SWS prediction at local to conus scales in a changing climate by leveraging all the available observation and simulation resources, as well as to inform the model development and guide the observation collection. The accurate prediction will enable an optimal decision of water management and land use and improve the ecosystem's resilience to the climate change.

Authors: Dan Lu (Oak Ridge National Laboratory); Eric Pierce (Oak Ridge National Laboratory); Shih-Chieh Kao (Oak Ridge National Laboratory); David Womble (Oak Ridge National Laboratory); LI LI (Pennsylvania State University); Daniella Rempe (The University of Texas at Austin)

Ecosystems and natural systems Earth science and monitoring
NeurIPS 2021 Hybrid physics-based and data-driven modeling with calibrated uncertainty for lithium-ion battery degradation diagnosis and prognosis (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Advancing lithium-ion batteries (LIB) in both design and usage is key to promoting electrification in the coming decades to mitigate human-caused climate change. Inadequate understanding of LIB degradation is an important bottleneck that limits battery durability and safety. Here, we propose hybrid physics-based and data-driven modeling for online diagnosis and prognosis of battery degradation. Compared to existing battery modeling efforts, we aim to build a model with physics as its backbone and statistical learning techniques as enhancements. Such a hybrid model has better generalizability and interpretability together with a well-calibrated uncertainty associated with its prediction, rendering it more valuable and relevant to safety-critical applications under realistic usage scenarios.

Authors: Jing Lin (Institute for Infocomm Research); Yu Zhang (I2R); Edwin Khoo (Institute for Infocomm Research)

Hybrid physical models Power and energy systems Causal and Bayesian methods Classification, regression, and supervised learning Time-series analysis Uncertainty quantification and robustness
NeurIPS 2021 On the use of Deep Generative Models for "Perfect'" Prognosis Climate Downscaling (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Deep Learning has recently emerged as a "perfect" prognosis downscaling technique to compute high-resolution fields from large-scale coarse atmospheric data. Despite their promising results to reproduce the observed local variability, they are based on the estimation of independent distributions at each location, which leads to deficient spatial structures, especially when downscaling precipitation. This study proposes the use of generative models to improve the spatial consistency of the high-resolution fields, very demanded by some sectoral applications (e.g., hydrology) to tackle climate change.

Authors: Jose González-Abad (Institute of Physics of Cantabria); Jorge Baño-Medina (Institute of Physics of Cantabria); Ignacio Heredia (Instituto de Física de Cantabria)

Climate and Earth science Classification, regression, and supervised learning Generative modeling
NeurIPS 2021 A Deep Learning application towards transparent communication for Payment for Forest Environmental Services (PES) (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Deforestation accounts for more than 20% of global emission. Payments for Environmental Services (PES) is seen by both policy makers and practitioners as an effective market-based instrument to provide financial incentives for forest owners, particularly poor and indigenous households in developing countries. It is a critical instrument to protect forests, and ultimately to mitigate climate change and reduce emission from deforestation. However, previous studies have pointed out a key challenge for PES is to ensure transparent payment to local people, due to i) weak monitoring and evaluation and ii) indigenous inaccessibility to e-banking and complying with procedural and administrative paper works to receive payments. Specifically, the amount and the complexity of forms along with the language barriers is a key issue; and most transactions need several intermediaries and transaction costs which reduce the payments reaching landowners. To address these issues, we propose a communication platform that links across the stakeholders and processes. Our proposal will utilize Machine Learning techniques to lower the language barrier and provide technology solutions to help indigenous people to access payments. This would also help improve the effectiveness and transparency of PES schemes. Specifically, we propose the use of Natural Language Processing techniques in providing a speech-to-text and auto translation capability, and the use of Graph Neural Network to provide link predictions of transaction types, volumes and values. The pathway to impact will be forest protection and local livelihood through providing financial incentives, and subsequently contribution to more carbon sequestration and storage – a key issue in climate change mitigation.

Authors: Lan HOANG (IBM Research); Thuy Thu Phan (Center for International Forestry Research (CIFOR))

Agriculture, forestry and other land use Natural language processing
NeurIPS 2021 A NLP-based Analysis of Alignment of Organizations' Climate-Related Risk Disclosures with Material Risks and Metrics (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The Sustainability Accounting Standards Board (SASB) establishes standards to guide the disclosures of material sustainability and ESG (Environment, Social, Governance)-related information across industries. The availability of quality, comparable and decision-useful information is required to assess risks and opportunities later integrated into financial decision-making. Particularly, standardized, industry-specific climate risk metrics and topics can support these efforts. SASB’s latest climate risk technical bulletin introduces three climate-related risks that are financially material - physical, transition and regulatory risks - and maps these across industries. The main objective of this work is to create a framework that can analyze climate related risk disclosures using an AI-based tool that automatically extracts and categorizes climate-related risks and related metrics from company disclosures based on SASB’s latest climate risk guidance. This process will help with automating large-scale analysis and add much-needed transparency vis-a-vis the current state of climate-related disclosures, while also assessing how far along companies are currently disclosing information on climate risks relevant to their industry. As it stands, this much needed type of analysis is made mostly manually or using third-party metrics, often opaque and biased, as proxies. In this work, we will first create a climate risk glossary that will be trained on a large amount of climate risk text. By combining climate risk keywords in this glossary with recent advances in natural language processing (NLP), we will then be able to quantitatively and qualitatively compare climate risk information in different sectors and industries using a novel climate risk score that will be based on SASB standards.

Authors: Elham Kheradmand (University of Montreal); Didier Serre (Clearsum); Manuel Morales (University of Montreal); Cedric B Robert (Clearsum)

Climate finance and economics Classification, regression, and supervised learning Natural language processing
NeurIPS 2021 Unsupervised Machine Learning framework for sensor placement optimization: analyzing methane leaks (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Methane is one of the most potent greenhouse gases, with the global oil and gas industry being the second largest source of anthropogenic methane emissions, accounting for about 63% of the whole energy sector. This underscores the importance of detecting and remediating methane leaks for the entire oil and gas value chain. Methane sensor networks are a promising technology to detect methane leaks in a timely manner. While they provide near-real-time monitoring of an area of interest, the density of the network can be cost prohibitive, and the identification of the source of the leak is not apparent, especially where there could be more than one source. To address these issues, we developed a machine learning framework that leverages various data sources including oil and gas facilities data, historical methane leak rate distribution and meteorological data, to optimize sensor placement. The determination of sensor locations follows the objective to maximize the detection of possible methane leaks with a limited sensor budget.

Authors: Shirui Wang (University of Houston); Sara Malvar (Microsoft); Leonardo Nunes (Microsoft); Kim Whitehall (Microsoft); Yagna Oruganti (Microsoft); Yazeed Alaudah (Microsoft); Anirudh Badam (Microsoft)

Earth science and monitoring Other Unsupervised and semi-supervised learning
NeurIPS 2021 Multi-agent reinforcement learning for renewable integration in the electric power grid (Proposals Track)
Abstract and authors: (click to expand)

Abstract: As part of the fight against climate change, the electric power system is transitioning from fuel-burning generators to renewable sources of power like wind and solar. To allow for the grid to rely heavily on renewables, important operational changes must be done. For example, novel approaches for frequency regulation, i.e., for balancing in real-time demand and generation, are required to ensure the stability of a renewable electric system. Demand response programs in which loads adjust in part their power consumption for the grid's benefit, can be used to provide frequency regulation. In this proposal, we present and motivate a collaborative multi-agent reinforcement learning approach to meet the algorithmic requirements for providing real-time power balancing with demand response.

Authors: Vincent Mai (Mila, Université de Montréal); Tianyu Zhang (Mila, Université de Montréal); Antoine Lesage-Landry (Polytechnique Montréal & GERAD)

Power and energy systems Reinforcement learning and control
NeurIPS 2021 Machine Learning Speeding Up the Development of Portfolio of New Crop Varieties to Adapt to and Mitigate Climate Change (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Climate change poses serious challenges to achieving food security in a time of a need to produce more food to keep up with the world’s increasing demand for food. There is an urgent need to speed up the development of new high yielding varieties with traits of adaptation and mitigation to climate change. Mathematical approaches, including ML approaches, have been used to search for such traits, leading to unprecedented results as some of the traits, including heat traits that have been long sought-for, have been found within a short period of time.

Authors: Abdallah Bari (OperAI Canada - Operational AI); Hassan Ouabbou (INRA); Abderrazek Jilal (INRA); Frederick Stoddard (University of Helsinki); Mikko Sillanpää (University of Oulu); Hamid Khazaei (World Vegetable Center)

Agriculture, forestry and other land use Carbon capture and sequestration Causal and Bayesian methods Classification, regression, and supervised learning Time-series analysis Unsupervised and semi-supervised learning
NeurIPS 2021 Toward Foundation Models for Earth Monitoring: Proposal for a Climate Change Benchmark (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Recent progress in self-supervision shows that pre-training large neural networks on vast amounts of unsupervised data can lead to impressive increases in generalisation for downstream tasks. Such models, recently coined as foundation models, have been transformational to the field of natural language processing. While similar models have also been trained on large corpuses of images, they are not well suited for remote sensing data. To stimulate the development of foundation models for Earth monitoring, we propose to develop a new benchmark comprised of a variety of downstream tasks related to climate change. We believe that this can lead to substantial improvements in many existing applications and facilitate the development of new applications. This proposal is also a call for collaboration with the aim of developing a better evaluation process to mitigate potential downsides of foundation models for Earth monitoring.

Authors: Alexandre Lacoste (ServiceNow); Evan D Sherwin (Stanford University, Energy and Resources Engineering); Hannah R Kerner (University of Maryland); Hamed Alemohammad (Radiant Earth Foundation); Björn Lütjens (MIT); Jeremy A Irvin (Stanford); David Dao (ETH Zurich); Alex Chang (Service Now); Mehmet Gunturkun (Element Ai); Alexandre Drouin (ServiceNow); Pau Rodriguez (Element AI); David Vazquez (ServiceNow)

Computer vision and remote sensing Agriculture, forestry and other land use Climate and Earth science Disaster prediction, management, and relief Ecosystems and natural systems Meta- and transfer learning
NeurIPS 2021 Optimization of Agricultural Management for SoilCarbon Sequestration based on Deep ReinforcementLearning and Large-Scale Simulations (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Soil carbon sequestration in croplands has tremendous potential to help mitigate climate change; however, it is challenging to develop the optimal management practices for maximization of the sequestered carbon as well as the crop yield. This project aims to develop an intelligent agricultural management system using deep reinforcement learning (RL) and large-scale soil and crop simulations. To achieve this, we propose to build a simulator to model and simulate the complex soil-water-plant-atmosphere interaction. By formulating the management decision as an RL problem, we can leverage the state-of-the-art algorithms to train management policies through extensive interactions with the simulated environment. The trained policies are expected to maximize the stored organic carbon while maximizing the crop yield in the presence of uncertain weather conditions. The whole system will be tested using data of soil and crops in both mid-west of the United States and the central region of Portugal. The proposed research will impact food security and climate change, two of the most significant challenges currently facing humanity.

Authors: Jing Wu (University of Illinois Urbana-Champaign); Pan Zhao (University of Illinois Urbana-Champaign); Ran Tao (University of Illinois Urbana-Champaign); Naira Hovakimyan (UIUC); Guillermo Marcillo (University of Illinois at Urbana-Champaign); Nicolas Martin (University of Illinois at Urbana-Champaign); Carla Ferreira (Royal Institute of Technology); Zahra Kalantari (Royal Institute of Technology); Jennifer Hobbs (IntelinAir Inc.)

Reinforcement learning and control Carbon capture and sequestration
NeurIPS 2021 Leveraging machine learning for identify hydrological extreme events under global climate change (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Hydrological extreme events, such as droughts and floods, are highly destructive 1 natural disasters and its occurrence is expected to increase under the future climate change. Accurate and efficient approach to detect such events will provide timely information to assist management strategies for minimizing socio-economic damages. Despite the threshold approach has established to detect extreme events, the missing data from hydroclimate data and accurately identifying these events are still major challenges. The advent of machine learning models can help to identify the occurrence of droughts and floods events accurately and efficiently. Therefore, this proposed study will develop a machine learning model with semi-supervised anomaly detection approach to identify hydrological extreme events with ground-based data. As a test case, we will use 45-years record of hydroclimate data in coastal California, where was the driest region in 2012-2015, following with flash floods events. The expected results will increase communities’ awareness for hydrological extreme events and enable environmental planning and resource management under climate change

Authors: Ying-Jung C Deweese (Georgia Insititute of Technology)

Earth science and monitoring Classification, regression, and supervised learning
NeurIPS 2021 Predicting Cascading Failures in Power Systems using Graph Convolutional Networks (Proposals Track)
Abstract and authors: (click to expand)

Abstract: On the way to combating climate change, decarbonisation of electricity generation is becoming increasingly important. Worldwide targets are set for the increase of renewable power generation in electricity networks. Consequently, a secure power system that can handle the complexities resulted from the increased renewable source integration is crucial. One particular complexity is the possibility of cascading failures -- a quick succession of multiple component failures that takes down the system and might also lead to a blackout. Early detection and containment of such failures is challenging because it is combinatorial in nature and has to contend with the spatial aspects of the power system as well as the temporal evolution of failures. Viewing the prediction of cascading failures as a binary classification task, we explore the efficacy of Graph Convolution Networks (GCNs), to detect the early onset of a cascading failure. We perform experiments based on simulated data from a benchmark IEEE test system. Our preliminary findings show that GCNs achieve higher accuracy scores than other baselines which bodes well for detecting cascading failures. It also motivates a more comprehensive study of graph-based deep learning techniques in this research topic.

Authors: Tabia Ahmad (University of Strathclyde); Yongli Zhu (Texas A&M Universersity); Panagiotis Papadopoulos (University of Strathclyde)

Power and energy systems Carbon capture and sequestration Classification, regression, and supervised learning Data mining Unsupervised and semi-supervised learning
NeurIPS 2021 DeepQuake: Artificial Intelligence for Earthquake Forecasting Using Fine-Grained Climate Data (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Earthquakes are one of the most catastrophic natural disasters, making accurate, fine-grained, and real-time earthquake forecasting extremely important for the safety and security of human lives. In this work, we propose DeepQuake, a deep learning model for fine-grained earthquake forecasting using time-series data of the horizontal displacement of Earth’s surface measured from continuously operating Global Positioning System (cGPS) data between 2007 to 2019. Recent studies using cGPS data have established a link between transient deformation within earth’s crust including Earth’s elastic response to climate variables such as hydrologic loads, temperature gradients, and atmospheric pressure. DeepQuake’s physics-based pre-processing algorithm extracts relevant features including the x,y, and z components of strain in the earth’s crust, feeding it into an LSTM model to predict key earthquake variables such as the time, location, magnitude, and depth of a future earthquake. Initial results across California, including the Napa Valley and Long Valley Caldera regions, show promising correlations between cGPS data and the earthquake catalog ground truth for a given location and time

Authors: Yash Narayan (The Nueva School)

Time-series analysis Climate and Earth science Earth science and monitoring Other
ICML 2021 Examining the nexus of environmental policy, climate physics, and maritime shipping with deep learning models and space-borne data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Ship-tracks are produced by ship exhaust interacting with marine low clouds. They provide an ideal lab for constraining a critical climate forcing. However, no global survey of ship ship-tracks has been made since its discovery 55 years ago, which limits research progress. Here we present the first global map of ship-tracks produced by applying deep segmentation models to large satellite data. Our model generalizes well and is validated against independent data. Large-scale ship-track data are at the nexus of environmental policy, climate physics, and maritime shipping industry: they can be used to study aerosol-cloud interactions, the largest uncertainty source in climate forcing; to evaluate compliance and impacts of environmental policies; and to study the impact of significant socioeconomic events on maritime shipping. Based on twenty years of global data, we show cloud physics responses in ship-tracks strongly depend on the cloud regime. Inter-annual fluctuation in ship-track frequency clearly reflects international trade/economic trends. Emission policies strongly affect the pattern of shipping routes and ship-track occurrence. The combination of stricter fuel standard and the COVID-19 pandemic pushed global ship-track frequency to the lowest level in the record. More applications of our technique and data are envisioned such as detecting illicit shipping activity and checking policy compliance of individual ships.

Authors: Tianle Yuan (University of Maryland, NASA); Hua Song (NASA, SSAI); Chenxi Wang (University of Maryland, NASA); Kerry Meyer (NASA); Siobhan Light (University of Maryland); Sophia von Hippel (University of Arizona); Steven Platnick (NASA); Lazaros Oreopoulos (NASA); Robert Wood (University of Washington); Hans Mohrmann (University of Washington)

Computer vision and remote sensing Policy Meta- and transfer learning
ICML 2021 A human-labeled Landsat-8 contrails dataset (Papers Track)
Abstract and authors: (click to expand)

Abstract: Contrails (condensation trails) are the ice clouds that trail behind aircraft as they fly through cold and moist regions of the atmosphere. Avoiding these regions could potentially be an inexpensive way to reduce over half of aviation's impact on global warming. Development and evaluation of these avoidance strategies greatly benefits from the ability to detect contrails on satellite imagery. Since little to no public data is available to develop such contrail detectors, we construct and release a dataset of several thousand Landsat-8 scenes with pixel-level annotations of contrails. The dataset will continue to grow, but currently contains 4289 scenes (of which 47% have at least one contrail) representing 950+ person-hours of labeling time.

Authors: Kevin McCloskey (Google); Scott Geraedts (Google); Brendan Jackman (Google); Vincent R. Meijer (Laboratory for Aviation and the Environment, Massachusetts Institute of Technology); Erica Brand (Google); Dave Fork (Google); John C. Platt (Google); Carl Elkin (Google); Christopher Van Arsdale (Google)

Computer vision and remote sensing Climate and Earth science
ICML 2021 Urban Tree Species Classification Using Aerial Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Urban trees help regulate temperature, reduce energy consumption, improve urban air quality, reduce wind speeds, and mitigating the urban heat island effect. Urban trees also play a key role in climate change mitigation and global warming by capturing and storing atmospheric carbon-dioxide which is the largest contributor to greenhouse gases. Automated tree detection and species classification using aerial imagery can be a powerful tool for sustainable forest and urban tree management. Hence, This study first offers a pipeline for generating labelled dataset of urban trees using Google Map's aerial images and then investigates how state of the art deep Convolutional Neural Network models such as VGG and ResNet handle the classification problem of urban tree aerial images under different parameters. Experimental results show our best model achieves an average accuracy of 60% over 6 tree species.

Authors: Emily Waters (Anglia Ruskin University); Mahdi Maktabdar Oghaz (Anglia Ruskin University); Lakshmi Babu Saheer (Anglia Ruskin University)

Carbon capture and sequestration Buildings and cities Climate and Earth science Agriculture, forestry and other land use Computer vision and remote sensing
ICML 2021 Estimation of Corporate Greenhouse Gas Emissions via Machine Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: As an important step to fulfill the Paris Agreement and achieve net-zero emissions by 2050, the European Commission adopted the most ambitious package of climate impact measures in April 2021 to improve the flow of capital towards sustainable activities. For these and other international measures to be successful, reliable data is key. The ability to see the carbon footprint of companies around the world will be critical for investors to comply with the measures and hit climate neutrality. However, with only a small portion of companies volunteering to disclose their greenhouse gas (GHG) emissions, it is nearly impossible for investors to align their investment strategies with the measures. By training a machine learning model on disclosed GHG emissions, we are able to estimate the emissions of other companies globally who do not disclose their emissions. In this paper, we show that our model provides accurate estimates of corporate GHG emissions to investors such that they are able to align their investments with the regulatory measures and achieve net-zero goals.

Authors: You Han (Bloomberg L.P.); Achintya Gopal (Bloomberg LP); Liwen Ouyang (Bloomberg L.P.); Aaron Key (Bloomberg LP)

Climate finance Industry Policy Classification, regression, and supervised learning Generative modeling Uncertainty quantification and robustness Unsupervised and semi-supervised learning
ICML 2021 ANP-BBO: Attentive Neural Processes and Batch Bayesian Optimization for Scalable Calibration of Physics-Informed Digital Twins (Papers Track)
Abstract and authors: (click to expand)

Abstract: Physics-informed dynamical system models form critical components of digital twins of the built environment. These digital twins enable the design of energy-efficient infrastructure, but must be properly calibrated to accurately reflect system behavior for downstream prediction and analysis. Dynamical system models of modern buildings are typically described by a large number of parameters and incur significant computational expenditure during simulations. To handle large-scale calibration of digital twins without exorbitant simulations, we propose ANP-BBO: a scalable and parallelizable batch-wise Bayesian optimization (BBO) methodology that leverages attentive neural processes (ANPs).

Authors: Ankush Chakrabarty (Mitsubishi Electric Research Labs); Gordon Wichern (Mitsubishi Electric Research Laboratories (MERL)); Christopher Laughman (Mitsubishi Electric Research Laboratories (MERL))

Buildings and cities Bayesian optimization
ICML 2021 Seasonal Sea Ice Presence Forecasting of Hudson Bay using Seq2Seq Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Accurate and timely forecasts of sea ice conditions are crucial for safe shipping operations in the Canadian Arctic and other ice-infested waters. Given the advancement of machine-learning methods and the recent observations on the declining trend of Arctic sea ice extent over the past decades due to global warming, new machine learning approaches are deployed to provide additional sea ice forecasting products. This study is novel in comparison with previous machine learning (ML) approaches in the sea-ice forecasting domain as it provides a daily spatial map of probability of ice presence in the domain up to 90 days. The predictions are further used to predict freeze-up/breakup dates and show their capability to capture both the variability and the increasing trend of open water season in the domain over the past decades.

Authors: Nazanin Asadi (University of Waterloo); K Andrea Scott (University of Waterloo); Philippe Lamontagne (National Research Council Canada)

Climate and Earth science Classification, regression, and supervised learning Computer vision and remote sensing Time-series analysis
ICML 2021 Semantic Segmentation on Unbalanced Remote Sensing Classes for Active Fire (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wildfires generate considerable research interest due to their high frequency of occurrence along with global climate change. Future wildfire detection sensors would equip an on-orbit processing module that filters the useless raw images before data transmission. To efficiently detect heat anomalies from the single large scene, we need to handle the unbalanced sample sets between small active fire pixels and large-size complex background information. In this study, we contribute to solving this problem by enhancing the target feature representation in three ways. We first preprocess training images by constraining sampling ranges and removing background patches. Then we use the object-contextual representation (OCR) module to strengthen the active fire pixel representation based on the self-attention unit. The HRNet backbone provides multi-scale pixel representation as input to the OCR module. Finally, the combined loss of weighted cross-entropy loss and Lovasz hinge loss improve the segmentation accuracy further by optimizing the IoU of the foreground class. The performance is tested on the aerial FLAME dataset, whose ratio between labeled active fire and background pixels is 5.6%. The proposed framework improves the mIoU from 83.10% (baseline U-Net) to 90.81%. Future research will expand the technique for active fire detection using satellite images.

Authors: Xikun Hu (KTH Royal Institute of Technology); Alberto Costa Nogueira Junior (IBM Research Brazil); Tian Jin (College of Electronic Science, National University of Defense Technology)

Disaster prediction, management, and relief Computer vision and remote sensing
ICML 2021 Improving Image-Based Characterization of Porous Media with Deep Generative Models (Papers Track)
Abstract and authors: (click to expand)

Abstract: Micro- and nanoscale imaging are important for characterizing subsurface formations for carbon sequestration, shale gas recovery, and hydrogen storage. Common imaging techniques, however, are often sample-destructive, expensive, require high levels of expertise, or only acquire planar data. The resulting image datasets therefore may not allow for a representative estimation of rock properties. In this work, we address these challenges in image-based characterization of porous media using deep generative models. We present a machine learning workflow for characterizing porous media from limited imaging data. We develop methods for 3D image volume translation and synthesis from 2D training data, apply this method to grayscale and multimodal image datasets of sandstones and shales, and simulate flow through the generated volumes. Results show that the proposed image reconstruction and generation approaches produce realistic pore-scale 3D representations of rock samples using only 2D training data. The models proposed here expand our capabilities for characterization of rock samples and enable new understanding of pore-scale storage and recovery processes.

Authors: Timothy Anderson (Stanford University); Kelly Guan (Stanford University); Bolivia Vega (Stanford University); Laura Froute (Stanford University); Anthony Kovscek (Stanford University)

Generative modeling Carbon capture and sequestration
ICML 2021 Forest Terrain Identification using Semantic Segmentation on UAV Images (Papers Track)
Abstract and authors: (click to expand)

Abstract: Beavers' habitat is known to alter the terrain, providing biodiversity in the area, and recently their lifestyle is linked to climatic changes by reducing greenhouse gases levels in the region. To analyse the impact of beavers’ habitat on the region, it is, therefore, necessary to estimate the terrain alterations caused by beaver actions. Furthermore, such terrain analysis can also play an important role in domains like wildlife ecology, deforestation, land-cover estimations, and geological mapping. Deep learning models are known to provide better estimates on automatic feature identification and classification of a terrain. However, such models require significant training data. Pre-existing terrain datasets (both real and synthetic) like CityScapes, PASCAL, UAVID, etc, are mostly concentrated on urban areas and include roads, pathways, buildings, etc. Such datasets, therefore, are unsuitable for forest terrain analysis. This paper contributes, by providing a finely labelled novel dataset of forest imagery around beavers’ habitat, captured from a high-resolution camera on an aerial drone. The dataset consists of 100 such images labelled and classified based on 9 different classes. Furthermore, a baseline is established on this dataset using state-of-the-art semantic segmentation models based on performance metrics including Intersection Over Union (IoU), Overall Accuracy (OA), and F1 score.

Authors: Muhammad Umar (Anglia Ruskin University); Lakshmi Babu Saheer (Anglia Ruskin University); Javad Zarrin (Anglia Ruskin University)

Agriculture, forestry and other land use Ecosystems and natural resources Classification, regression, and supervised learning Computer vision and remote sensing
ICML 2021 Climate-based ensemble machine learning model to forecast Dengue epidemics (Papers Track)
Abstract and authors: (click to expand)

Abstract: Dengue fever is one of the most common and rapidly spreading arboviral diseases in the world, with major public health and economic consequences in tropical and sub-tropical regions. Countries such as Peru, 17.143 cases of dengue were reported in 2019, where 81.4% of cases concentrated in five of the 25 departments. When predicting infectious disease outbreaks, it is crucial to model the long-term dependency in time series data. However, this is challenging when performed on a countrywide level since dengue incidence varies across administrative areas. Therefore, this study developed and applied a climate-based ensemble model using multiple machine learning (ML) approaches to forecast dengue incidence rate (DIR) by department. The ensemble combined the outputs from Long Short-Term Memory (LSTM) recurrent neural network and Categorical Boosting (CatBoost) methods to predict DIR one month ahead for each department in Peru. Monthly dengue cases stratified by Peruvian departments were analysed in conjunction with associated demographic, geographic, and satellite-based meteorological data for the period January 2010–December 2019. The results demonstrated that the ensemble model was able to forecast DIR in low-transmission departments, while the model was less able to detect sudden DIR peaks in some departments. Air temperature and wind components demonstrated to be the significant predictors for DIR predictions. This dengue forecast model is timely and can help local governments to implement effective control measures and mitigate the effects of the disease. This study advances the state-of-the-art of climate services for the public health sector, by informing what are the key climate factors responsible for triggering dengue transmission. Finally, this project summarises how important it is to perform collaborative work with complementary expertise from intergovernmental organizations and public health universities to advance knowledge and address societal challenges.

Authors: Rochelle Schneider (European Space Agency); Alessandro Sebastianelli (European Space Agency); Dario Spiller (Italian Space Agency); James Wheeler (European Space Agency); Raquel Carmo (European Space Agency); Artur Nowakowski (Warsaw University of Technology); Manuel Garcia-Herranz (UNICEF); Dohyung Kim (UNICEF); Hanoch Barlevi (UNICEF LACRO); Zoraya El Raiss Cordero (UNICEF LACRO); Silvia Liberata Ullo (University of Sannio); Pierre-Philippe Mathieu (European Space Agency); Rachel Lowe (London School of Hygiene & Tropical Medicine)

Societal adaptation Climate Change and Health
ICML 2021 Physics-Informed Graph Neural Networks for Robust Fault Location in Power Grids (Papers Track) Best Paper: ML Innovation
Abstract and authors: (click to expand)

Abstract: The reducing cost of renewable energy resources, such as solar photovoltaics (PV) and wind farms, is accelerating global energy transformation to mitigate climate change. However, a high level of intermittent renewable energy causes power grids to have more stability issues. This accentuates the need for quick location of system failures and follow-up control actions. In recent events such as in California, line failures have resulted in large-scale wildfires leading to loss of life and property. In this article, we propose a two-stage graph learning framework to locate power grid faults in the challenging but practical regime characterized by (a) sparse observations, (b) low label rates, and (c) system variability. Our approach embeds the geometrical structure of power grids into the graph neural networks (GNN) in stage I for fast fault location, and then stage II further enhances the location accuracy by employing the physical similarity of the labeled and unlabeled data samples. We compare our approach with three baselines in the IEEE 123-node benchmark system and show that it outperforms the others by significant margins in various scenarios.

Authors: Wenting Li (Los Alamos National Laboratory); Deepjyoti Deka (Los Alamos National Laboratory)

Power and energy Classification, regression, and supervised learning Hybrid physical models Interpretable ML Uncertainty quantification and robustness Unsupervised and semi-supervised learning
ICML 2021 Prediction of Boreal Peatland Fires in Canada using Spatio-Temporal Methods (Papers Track)
Abstract and authors: (click to expand)

Abstract: Peat fires are the largest fires on earth in terms of fuel consumption and are responsible for a significant portion of global carbon emissions. Predicting fires in the peatlands can help decision-makers and researchers monitor and prevent peat fires. Despite this, research on predicting peatland fires remains largely understudied as compared to the prediction of other forms of fires. However, peatland fires are unique among fires and therefore require datasets and architectures attuned to their particular characteristics. In this paper, we present a new dataset, PeatSet, designed specifically for the problem of peatland fire prediction. In addition, we propose several models to tackle the problem of fire prediction for the peatlands. We develop novel neural architectures for peatland fire prediction, PeatNet, and PT-Net, with a graph-based and a transformer-based architecture, respectively. Our results indicate that these new deep-learning architectures outperform a regression baseline from existing peatland research. Among all the tested models, PT-Net achieves the highest F1 score of 0.1006 and an overall accuracy of 99.84%.

Authors: Shreya Bali (Carnegie Mellon University); Sydney Zheng (Carnegie Mellon University); Akshina Gupta (Carnegie Mellon University); Yue Wu (None); Blair Chen (Carnegie Mellon University); Anirban Chowdhury (Carnegie Mellon University); Justin Khim (Carnegie Mellon University)

Disaster prediction, management, and relief Climate and Earth science Classification, regression, and supervised learning
ICML 2021 Revealing the impact of global warming on climate modes using transparent machine learning and a suite of climate models (Papers Track)
Abstract and authors: (click to expand)

Abstract: The ocean is key to climate through its ability to store and transport heat and carbon. From studies of past climates, it is clear that the ocean can exhibit a range of dramatic variability that could have catastrophic impacts on society, such as changes in rainfall, severe weather, sea level rise and large scale climate patterns. The mechanisms of change remain obscure, but are explored using a transparent machine learning method, Tracking global Heating with Ocean Regimes (THOR) presented here. We investigate two future scenarios, one where CO2 is increased by 1% per year, and one where CO2 is abruptly quadrupled. THOR is engineered combining interpretable and explainable methods to reveal its source of predictive skill. At the core of THOR, is the identification of dynamically coherent regimes governing the circulation, a fundamental question within oceanography. Three key regions are investigated here. First, the North Atlantic circulation that delivers heat to the higher latitudes is seen to weaken and we identify associated dynamical changes. Second, the Southern Ocean circulation, the strongest circulation on earth, is seen to intensify where we reveal the implications for interactions with the ice on Antarctica. Third, shifts in ocean circulation regimes are identified in the tropical Pacific region, with potential impacts on the El Nino Southern Oscillation, Earth’s dominant source of year-to-year climate variations affecting weather extremes, ecosystems, agriculture, and fisheries. Together with revealing these climatically relevant ocean dynamics, THOR also constitutes a step towards trustworthy machine learning called for within oceanography and beyond because its predictions are physically tractable. We conclude with by highlighting open questions and potentially fruitful avenues of further machine learning applications to climate research.

Authors: Maike Sonnewald (Princeton University); Redouane Lguensat (LSCE-IPSL); Aparna Radhakrishnan (Geophysical Fluid Dynamics Laboratory); Zoubero Sayibou (Bronx Community College); Venkatramani Balaji (Princeton University); Andrew Wittenberg (NOAA)

Climate and Earth science Interpretable ML
ICML 2021 Challenges in Applying Audio Classification Models to Datasets Containing Crucial Biodiversity Information (Papers Track)
Abstract and authors: (click to expand)

Abstract: The acoustic signature of a natural soundscape can reveal consequences of climate change on biodiversity. Hardware costs, human labor time, and expertise dedicated to labeling audio are impediments to conducting acoustic surveys across a representative portion of an ecosystem. These barriers are quickly eroding away with the advent of low-cost, easy to use, open source hardware and the expansion of the machine learning field providing pre-trained neural networks to test on retrieved acoustic data. One consistent challenge in passive acoustic monitoring (PAM) is a lack of reliability from neural networks on audio recordings collected in the field that contain crucial biodiversity information that otherwise show promising results from publicly available training and test sets. To demonstrate this challenge, we tested a hybrid recurrent neural network (RNN) and convolutional neural network (CNN) binary classifier trained for bird presence/absence on two Peruvian bird audiosets. The RNN achieved an area under the receiver operating characteristics (AUROC) of 95% on a dataset collected from Xeno-canto and Google’s AudioSet ontology in contrast to 65% across a stratified random sample of field recordings collected from the Madre de Dios region of the Peruvian Amazon. In an attempt to alleviate this discrepancy, we applied various audio data augmentation techniques in the network’s training process which led to an AUROC of 77% across the field recordings.

Authors: Jacob G Ayers (UC San Diego); Yaman Jandali (University of California, San Diego); Yoo-Jin Hwang (Harvey Mudd College); Erika Joun (University of California, San Diego); Gabriel Steinberg (Binghampton University); Mathias Tobler (San Diego Zoo Wildlife Alliance); Ian Ingram (San Diego Zoo Wildlife Alliance); Ryan Kastner (University of California San Diego); Curt Schurgers (University of California San Diego)

Ecosystems and natural resources Natural language processing
ICML 2021 Learning Optimal Power Flow with Infeasibility Awareness (Papers Track)
Abstract and authors: (click to expand)

Abstract: Optimal power flow provides an energy-efficient operating point for power grids and therefore supports climate change mitigation. This function has to be run every few minutes day and night, thus a reliable and computationally efficient solution method is of vital importance. Deep learning seems a promising direction, and related works have emerged recently. However, considering feasible scenarios only during the learning process, existing works will mislead system operators in infeasible scenarios and pose a new threat to system resilience. Paying attention to infeasibility in the decision making process, this paper tackles this emerging threat with multi-task learning. Case studies on the IEEE test system validate the effectiveness of the proposed method.

Authors: Gang Huang (Zhejiang Lab); Longfei Liao (Zhejiang Lab); Lechao Cheng (Zhejiang Lab); Wei Hua (Zhejiang Lab)

Power and energy
ICML 2021 Reconstructing Aerosol Vertical Profiles with Aggregate Output Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Aerosol-cloud interactions constitute the largest source of uncertainty in assessments of the anthropogenic climate change. This uncertainty arises in part from the inability to observe aerosol amounts at the cloud formation levels, and, more broadly, the vertical distribution of aerosols. Hence, we often have to settle for less informative two-dimensional proxies, i.e. vertically aggregated data. In this work, we formulate the problem of disaggregation of vertical profiles of aerosols. We propose some initial solutions for such aggregate output regression problem and demonstrate their potential on climate model data.

Authors: Sofija Stefanovic (University of Oxford); Shahine Bouabid (University of Oxford); Philip Stier (University of Oxford); Athanasios Nenes (EPFL); Dino Sejdinovic (University of Oxford)

Climate and Earth science Classification, regression, and supervised learning Unsupervised and semi-supervised learning
ICML 2021 Self-Attentive Ensemble Transformer: Representing Ensemble Interactions in Neural Networks for Earth System Models (Papers Track)
Abstract and authors: (click to expand)

Abstract: Ensemble data from Earth system models has to be calibrated and post-processed. I propose a novel member-by-member post-processing approach with neural networks. I bridge ideas from ensemble data assimilation with self-attention, resulting into the self-attentive ensemble transformer. Here, interactions between ensemble members are represented as additive and dynamic self-attentive part. As proof-of-concept, I regress global ECMWF ensemble forecasts to 2-metre-temperature fields from the ERA5 reanalysis. I demonstrate that the ensemble transformer can calibrate the ensemble spread and extract additional information from the ensemble. As it is a member-by-member approach, the ensemble transformer directly outputs multivariate and spatially-coherent ensemble members. Therefore, self-attention and the transformer technique can be a missing piece for a non-parametric post-processing of ensemble data with neural networks.

Authors: Tobias S Finn (Universität Hamburg)

Climate and Earth science Classification, regression, and supervised learning
ICML 2021 DeepOPF-NGT: A Fast Unsupervised Learning Approach for Solving AC-OPF Problems without Ground Truth (Papers Track)
Abstract and authors: (click to expand)

Abstract: AC optimal power flow (AC-OPF) problems need to be solved more frequently in the future to maintain the reliable and cost-effective operation of power systems. Recently, supervised-learning approaches have been developed to speed up the solving time of AC-OPF problems without incurring infeasibility or much optimality loss by learning the load-solution mapping embedded in the training dataset. However, it is non-trivial and computationally expensive to prepare the training dataset with single embedded mapping, due to that AC-OPF problems are non-convex and may admit multiple optimal solutions. In this paper, we develop an unsupervised learning approach (DeepOPF-NGT) for solving AC-OPF problems, which does not require training datasets with ground truth to operate. Instead, it uses a properly designed loss function to guide the tuning of the neural network parameters to directly learn one load-solution mapping. Preliminary results on the IEEE 30-bus test system show that the unsupervised DeepOPF-NGT approach can achieve comparable optimality, feasibility, and speedup performance against an existing supervised learning approach.

Authors: Wanjun Huang (City University of Hong Kong); Minghua Chen (City University of Hong Kong)

Power and energy Unsupervised and semi-supervised learning
ICML 2021 Commercial Vehicle Traffic Detection from Satellite Imagery with Deep Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Road freight traffic is a major greenhouse gas emitter: commercial vehicles (CVs) contribute ∼7% to the global CO 2 emission budget, a fraction that is likely to increase in the future. The quantitative monitoring of CV traffic rates, while essential for the implementation of targeted road emission regulations, is costly and as such only available in developed regions. In this work, we investigate the feasibility of estimating hourly CV traffic rates from freely available Sentinel-2 satellite imagery. We train a modified Faster R-CNN object detection model to detect individual CVs in satellite images and feed the resulting counts into a regression model to predict hourly CV traffic rates. This architecture, when trained on ground-truth data for Switzerland, is able to estimate hourly CV traffic rates for any freeway section within 58% (MAPE) of the actual value; for freeway sections with historic information on CV traffic rates, we can predict hourly CV traffic rates up to within 4% (MAPE). We successfully apply our model to freeway sections in other coun tries and show-case its utility by quantifying the change in traffic patterns as a result of the first CoVID-19 lockdown in Switzerland. Our results show that it is possible to estimate hourly CV traffic rates from satellite images, which can guide civil engineers and policy makers, especially in developing countries, in monitoring and reducing greenhouse gas emissions from CV traffic.

Authors: Moritz Blattner (University of St. Gallen); Michael Mommert (University of St. Gallen); Damian Borth (University of St. Gallen)

Computer vision and remote sensing Transportation
ICML 2021 Probabilistic Short-Term Low-Voltage Load Forecasting using Bernstein-Polynomial Normalizing Flows (Papers Track)
Abstract and authors: (click to expand)

Abstract: The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level. However, high fluctuations and increasing electrification cause huge forecast errors with traditional point estimates. Probabilistic load forecasts take future uncertainties into account and thus enables various applications in low-carbon energy systems. We propose an approach for flexible conditional density forecasting of short-term load based on Bernstein-Polynomial Normalizing Flows where a neural network controls the parameters of the flow. In an empirical study with 363 smart meter customers, our density predictions compare favorably against Gaussian and Gaussian mixture densities and also outperform a non-parametric approach based on the pinball loss for 24h-ahead load forecasting for two different neural network architectures.

Authors: Marcel Arpogaus (Konstanz University of Applied Sciences); Marcus Voß (Technische Universität Berlin (DAI-Labor)); Beate Sick (ZHAW and University of Zurich); Mark Nigge-Uricher (Bosch.IO GmbH); Oliver Dürr (Konstanz University of Applied Sciences)

Power and energy Buildings and cities Industry Classification, regression, and supervised learning Generative modeling Interpretable ML Time-series analysis Uncertainty quantification and robustness
ICML 2021 Guided A* Search for Scheduling Power Generation Under Uncertainty (Papers Track)
Abstract and authors: (click to expand)

Abstract: Increasing renewables penetration motivates the development of new approaches to operating power systems under uncertainty. We apply a novel approach combining self-play reinforcement learning (RL) and traditional planning to solve the unit commitment problem, an essential power systems scheduling task. Applied to problems with stochastic demand and wind generation, our results show significant cost reductions and improvements to security of supply as compared with an industry-standard mixed-integer linear programming benchmark. Applying a carbon price of \$50/tCO$_2$ achieves carbon emissions reductions of up to 10\%. Our results demonstrate scalability to larger problems than tackled in existing literature, and indicate the potential for RL to contribute to decarbonising power systems.

Authors: Patrick de Mars (UCL); Aidan O'Sullivan (UCL)

Power and energy Reinforcement learning and control
ICML 2021 DroughtED: A dataset and methodology for drought forecasting spanning multiple climate zones (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change exacerbates the frequency, duration and extent of extreme weather events such as drought. Previous attempts to forecast drought conditions using machine learning have focused on regional models which have two major limitations for national drought management: (i) they are trained on localised climate data and (ii) their architectures prevent them from being applied to new heterogeneous regions. In this work, we present a new large-scale dataset for training machine learning models to forecast national drought conditions, named DroughtED. The dataset consists of globally available meteorological features widely used for drought prediction, paired with location meta-data which has not previously been utilised for drought forecasting. Here we also establish a baseline on DroughtED and present the first research to apply deep learning models - Long Short-Term Memory (LSTMs) and Transformers - to predict county-level drought conditions across the full extent of the United States. Our results indicate that DroughtED enables deep learning models to learn cross-region patterns in climate data that contribute to drought conditions and models trained on DroughtED compare favourably to state-of-the-art drought prediction models trained on individual regions.

Authors: Christoph D Minixhofer (The University of Edinburgh); Mark Swan (The University of Edinburgh); Calum McMeekin (The University of Edinburgh); Pavlos Andreadis (The University of Edinburgh)

Disaster prediction, management, and relief Agriculture, forestry and other land use Climate and Earth science Classification, regression, and supervised learning Data mining Meta- and transfer learning Time-series analysis
ICML 2021 Estimation of Air Pollution with Remote Sensing Data: Revealing Greenhouse Gas Emissions from Space (Papers Track)
Abstract and authors: (click to expand)

Abstract: Air pollution is a major driver of climate change. Anthropogenic emissions from the burning of fossil fuels for transportation and power generation emit large amounts of problematic air pollutants, including Greenhouse Gases (GHGs). Despite the importance of limiting GHG emissions to mitigate climate change, detailed information about the spatial and temporal distribution of GHG and other air pollutants is difficult to obtain. Existing models for surface-level air pollution rely on extensive land-use datasets which are often locally restricted and temporally static. This work proposes a deep learning approach for the prediction of ambient air pollution that only relies on remote sensing data that is globally available and frequently updated. Combining optical satellite imagery with satellite-based atmospheric column density air pollution measurements enables the scaling of air pollution estimates (in this case NO2) to high spatial resolution (up to ~10m) at arbitrary locations and adds a temporal component to these estimates. The proposed model performs with high accuracy when evaluated against air quality measurements from ground stations (mean absolute error <6 microgram/m^3). Our results enable the identification and temporal monitoring of major sources of air pollution and GHGs.

Authors: Linus M. Scheibenreif (University of St. Gallen); Michael Mommert (University of St. Gallen); Damian Borth (University of St. Gallen)

Computer vision and remote sensing Climate and Earth science
ICML 2021 Emulating Aerosol Microphysics with a Machine Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Aerosol particles play an important role in the climate system by absorbing and scattering radiation and influencing cloud properties. They are also one of the biggest sources of uncertainty for climate modeling. Many climate models do not include aerosols in sufficient detail. In order to achieve higher accuracy, aerosol microphysical properties and processes have to be accounted for. This is done in the ECHAM-HAM global climate aerosol model using the M7 microphysics model, but increased computational costs make it very expensive to run at higher resolutions or for a longer time. We aim to use machine learning to approximate the microphysics model at sufficient accuracy and reduce the computational cost by being fast at inference time. The original M7 model is used to generate data of input-output pairs to train a neural network on it. By using a special logarithmic transform we are able to learn the variables tendencies achieving an average $R^2$ score of $89\%$. On a GPU we achieve a speed-up of 120 compared to the original model.

Authors: Paula Harder (Fraunhofer ITWM); Duncan Watson-Parris (University of Oxford); Dominik Strassel (Fraunhofer ITWM); Nicolas Gauger (TU Kaiserslautern); Philip Stier (University of Oxford); Janis Keuper (hs-offenburg)

Climate and Earth science Classification, regression, and supervised learning
ICML 2021 Automated Identification of Climate Risk Disclosures in Annual Corporate Reports (Papers Track)
Abstract and authors: (click to expand)

Abstract: It is important for policymakers to understand which financial policies are effective in increasing climate risk disclosure in corporate reporting. We use machine learning to automatically identify disclosures of five different types of climate-related risks. For this purpose, we have created a dataset of over 120 manually-annotated annual reports by European firms. Applying our approach to reporting of 337 firms over the last 20 years, we find that risk disclosure is increasing. Disclosure of transition risks grows more dynamically than physical risks, and there are marked differences across industries. Country-specific dynamics indicate that regulatory environments potentially have an important role to play for increasing disclosure.

Authors: David Friederich (University of Bern); Lynn Kaack (ETH Zurich); Sasha Luccioni (Mila); Bjarne Steffen (ETH Zurich)

Climate finance Natural language processing
ICML 2021 Forecasting Black Sigatoka Infection Risks with Latent Neural ODEs (Papers Track)
Abstract and authors: (click to expand)

Abstract: Black Sigatoka is the most widely-distributed and destructive disease affecting banana plants. Due to the heavy financial burden of managing this infectious disease, farmers in developing countries face significant banana crop losses. The spread of black Sigatoka is highly dependent on weather conditions and though scientists have produced mathematical models of infectious diseases, adapting these models to incorporate climate effects is difficult. We present MR. NODE (Multiple predictoR Neural ODE), a neural network that models the dynamics of black Sigatoka infection learnt directly from data via Neural Ordinary Differential Equations. Our method encodes external predictor factors into the latent space in addition to the variable that we infer, and it can also predict the infection risk at an arbitrary point in time. Empirically, we demonstrate on historical climate data that our method has superior generalization performance on time points up to one month in the future and unseen irregularities. We believe that our method can be a useful tool to control the spread of black Sigatoka.

Authors: Yuchen Wang (University of Toronto); Matthieu Chan Chee (University of Toronto); Ziyad Edher (University of Toronto); Minh Duc Hoang (University of Toronto); Shion Fujimori (University of Toronto); Jesse Bettencourt (University of Toronto)

Agriculture, forestry and other land use Time-series analysis
ICML 2021 A Reinforcement Learning Approach to Home Energy Management for Modulating Heat Pumps and Photovoltaic Systems (Papers Track)
Abstract and authors: (click to expand)

Abstract: Efficient sector coupling in residential buildings plays a key role in supporting the energy transition. In this study, we analyze the potential of using reinforcement learning (RL) to control a home energy management system. We conduct this study by modeling a representative building with a modulating air-sourced heat pump, a photovoltaic system, a battery, and thermal storage systems for floor heating and hot-water supply. In our numerical analysis, we benchmark our reinforcement learning results using DDPG with the optimal solution generated with model predictive control using a mixed-integer linear model under full information. Our input data, models, and the RL environment, developed using the Julia programming language, will be available in an open-source manner.

Authors: Lissy Langer (TU Berlin)

Buildings and cities Reinforcement learning and control
ICML 2021 Reinforcement Learning for Optimal Frequency Control: A Lyapunov Approach (Papers Track)
Abstract and authors: (click to expand)

Abstract: Renewable energy resources play a vital role in reducing carbon emissions and are becoming increasingly common in the grid. On one hand, they are challenging to integrate into a power system because the lack of rotating mechanical inertia can lead to frequency instabilities. On the other hand, these resources have power electronic interfaces that are capable of implementing almost arbitrary control laws. To design these controllers, reinforcement learning has emerged as a popular method to search for policy parameterized by neural networks. The key challenge with learning based approaches is enforcing the constraint that the learned controller need to be stabilizing. Through a Lyapunov function, we explicitly identify the structure of neural network-based controllers such that they guarantee system stability by design. A recurrent RL architecture is used to efficiently train the controllers and they outperform other approaches as demonstrated by simulations.

Authors: Wenqi Cui (University of Washington); Baosen Zhang (University of Washington)

Power and energy Reinforcement learning and control
ICML 2021 Modeling Bird Migration by Disaggregating Population Level Observations (Papers Track)
Abstract and authors: (click to expand)

Abstract: Birds are shifting migratory routes and timing in response to climate change, but modeling migration to better understand these changes is difficult. Some recent work leverages fluid dynamics models, but this requires individual flight speed and directional data which may not be readily available. We developed an alternate modeling method which only requires population level positional data and use it to model migration routes of the American Woodcock (Scolopax minor). We use our model to sample simulated bird trajectories and compare them to real trajectories in order to evaluate the model.

Authors: Miguel Fuentes (University of Massachusetts, Amherst); Benjamin Van Doren (Cornell University); Daniel Sheldon (University of Massachusetts, Amherst)

Ecosystems and natural resources Other
ICML 2021 Power Grid Cascading Failure Mitigation by Reinforcement Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: This paper proposes a cascading failure mitigation strategy based on Reinforcement Learning (RL) method. Firstly, the principles of RL are introduced. Then, the Multi-Stage Cascading Failure (MSCF) problem is formulated, and its challenges are investigated. The problem is then tackled by the RL based on DCOPF (Direct Current Optimal Power Flow). Designs of the RL framework (rewards, states, etc.) are illustrated in detail. Experiments on the IEEE 118-bus system by the proposed RL method demonstrate promising performance in reducing system collapses.

Authors: Yongli Zhu (Texas A&M University)

Disaster prediction, management, and relief Power and energy
ICML 2021 Decadal Forecasts with ResDMD: a residual DMD neural network (Papers Track)
Abstract and authors: (click to expand)

Abstract: Significant investment is being made by operational forecasting centers to produce decadal (1-10 year) forecasts that can support long-term decision making for a more climate-resilient society. One method that has been employed for this task is the Dynamic Mode Decomposition (DMD) algorithm – also known as the Linear Inverse Model– which is used to fit linear dynamical models to data. While the DMD usually approximates non-linear terms in the true dynamics as a linear system with random noise, we investigate an extension to the DMD to explicitly represent the non-linear terms as a neural network. Our weight initialization allows the network to produce sensible results before training and then improve the prediction after training as data becomes available. In this short paper, we evaluate the proposed architecture for simulating global sea surface temperatures and compare the results with the standard DMD and seasonal forecasts produced by the state-of-the-art dynamical model, CFSv2.

Authors: EDUARDO ROCHA RODRIGUES (IBM Research); Campbell Watson (IBM Reserch); Bianca Zadrozny (IBM Research); David Gold (IBM Global Business Services)

Classification, regression, and supervised learning Climate and Earth science Time-series analysis
ICML 2021 TweetDrought: A Deep-Learning Drought Impacts Recognizer based on Twitter Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Acquiring a better understanding of drought impacts becomes increasingly vital under a warming climate. Traditional drought indices describe mainly biophysical variables and not impacts on social, economic, and environmental systems. We utilized natural language processing and bidirectional encoder representation from Transformers (BERT) based transfer learning to fine-tune the model on the data from the news-based Drought Impact Report (DIR) and then apply it to recognize seven types of drought impacts based on the filtered Twitter data from the United States. Our model achieved a satisfying macro-F1 score of 0.89 on the DIR test set. The model was then applied to California tweets and validated with keyword-based labels. The macro-F1 score was 0.58. However, due to the limitation of keywords, we also spot-checked tweets with controversial labels. 83.5% of BERT labels were correct compared to the keyword labels. Overall, the fine-tuned BERT-based recognizer provided proper predictions and valuable information on drought impacts. The interpretation and analysis of the model were consistent with experiential domain expertise.

Authors: Beichen Zhang (University of Nebraska-Lincoln); Frank Schilder (Thomson Reuters); Kelly Smith (National Drought Mitigation Center); Michael Hayes (University of Nebraska-Lincoln); Sherri Harms (University of Nebraska-Kearney); Tsegaye Tadesse (University of Nebraska-Lincoln)

Disaster prediction, management, and relief Natural language processing
ICML 2021 Graph Neural Networks for Learning Real-Time Prices in Electricity Market (Papers Track)
Abstract and authors: (click to expand)

Abstract: Solving the optimal power flow (OPF) problem in real-time electricity market improves the efficiency and reliability in the integration of low-carbon energy resources into the power grids. To address the scalability and adaptivity issues of existing end-to-end OPF learning solutions, we propose a new graph neural network (GNN) framework for predicting the electricity market prices from solving OPFs. The proposed GNN-for-OPF framework innovatively exploits the locality property of prices and introduces physics-aware regularization, while attaining reduced model complexity and fast adaptivity to varying grid topology. Numerical tests have validated the learning efficiency and adaptivity improvements of our proposed method over existing approaches.

Authors: Shaohui Liu (University of Texas at Austin); Chengyang Wu (University of Texas at Austin); Hao Zhu (University of Texas at Austin)

Power and energy Classification, regression, and supervised learning
ICML 2021 Learning Granger Causal Feature Representations (Papers Track)
Abstract and authors: (click to expand)

Abstract: Tackling climate change needs to understand the complex phenomena occurring on the Planet. Discovering teleconnection patterns is an essential part of the endeavor. Events like El Niño Southern Oscillation (ENSO) impact essential climate variables at large distances, and influence the underlying Earth system dynamics. However, their automatic identification from the wealth of observational data is still unresolved. Nonlinearities, nonstationarities and the (ab)use of correlation analyses hamper the discovery of true causal patterns. We here introduce a deep learning methodology that extracts nonlinear latent functions from spatio-temporal Earth data and that are Granger causal with the index altogether. We illustrate its use to study the impact of ENSO on vegetation, which allows for a more rigorous study of impacts on ecosystems globally.

Authors: Gherardo Varando (Universitat de València); Miguel-Ángel Fernández-Torres (Universitat de València); Gustau Camps-Valls (Universitat de València)

Climate and Earth science Interpretable ML Unsupervised and semi-supervised learning
ICML 2021 DeepPolicyTracker: Tracking Changes In Environmental Policy In The Brazilian Federal Official Gazette With Deep Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Even though most of its energy generation comes from renewable sources, Brazil is one of the largest emitters of greenhouse gases in the world, due to intense farming and deforestation of biomes, such as the Amazon Rainforest, whose preservation is essential for compliance with the Paris Agreement. Still, regardless of lobbies or prevailing political orientation, all government legal actions are published daily in the Federal Official Gazette. However, with hundreds of decrees issued every day by the authorities, it is absolutely burdensome to manually analyze all these processes and find out which ones can pose serious environmental hazards. In this paper, we propose the DeepPolicyTracker, a promising deep learning model that uses a state-of-the-art pre-trained natural language model to classify government acts and track harmful changes in the environmental policies. We also provide the used dataset annotated by domain experts and show some results already obtained. In the future, this system should serve to scale up the high-quality tracking of all oficial documents with a minimum of human supervision and contribute to increasing society's awareness of every government action.

Authors: Flávio N Cação (University of Sao Paulo); Anna Helena Reali Costa (Universidade de São Paulo); Natalie Unterstell (Política por Inteiro); Liuca Yonaha (Política por Inteiro); Taciana Stec (Política por Inteiro); Fábio Ishisaki (Política por Inteiro)

Natural language processing Agriculture, forestry and other land use Classification, regression, and supervised learning
ICML 2021 Fast-Slow Streamflow Model Using Mass-Conserving LSTM (Papers Track)
Abstract and authors: (click to expand)

Abstract: Streamflow forecasting is key to effectively managing water resources and preparing for the occurrence of natural calamities being exacerbated by climate change. Here we use the concept of fast and slow flow components to create a new mass-conserving Long Short-Term Memory (LSTM) neural network model. It uses hydrometeorological time series and catchment attributes to predict daily river discharges. Preliminary results evidence improvement in skills for different scores compared to the recent literature.

Authors: Miguel Paredes Quinones (IBM Research); Maciel Zortea (IBM Research); Leonardo Martins (IBM Research)

Climate and Earth science Time-series analysis
ICML 2021 Attention For Damage Assessment (Papers Track)
Abstract and authors: (click to expand)

Abstract: Due to climate change the hurricanes are getting stronger and having longer impacts. To reduce the detrimental effects of these hurricanes faster and accurate assessments of damages are essential to the rescue teams. Like other computer vision techniques semantic segmentation can identify the damages and help in proper and prompt damage assessment. Current segmentation methods can be classified into attention and non-attention based methods. Existing non-attention based methods suffers from low accuracy and therefore attention based methods are becoming popular. Self-attention based methods can map the mutual relationship and dependencies among pixels of an image and thus improve semantic segmentation accuracy. In this paper, we present a self-attention semantic segmentation method on UAV imageries to assess the damages inflicted by a natural disaster. The proposed method outperforms four state-of-art segmentation methods both quantitatively and qualitatively with a mean IoU score of 84.03 %.

Authors: Tashnim Chowdhury (University of Maryland Baltimore County); Maryam Rahnemoonfar (University of Maryland Baltimore County)

Disaster prediction, management, and relief Buildings and cities Computer vision and remote sensing
ICML 2021 Online LSTM Framework for Hurricane Trajectory Prediction (Papers Track)
Abstract and authors: (click to expand)

Abstract: Hurricanes are high-intensity tropical cyclones that can cause severe damages when the storms make landfall. Accurate long-range prediction of hurricane trajectories is an important but challenging problem due to the complex interactions between the ocean and atmosphere systems. In this paper, we present a deep learning framework for hurricane trajectory forecasting by leveraging the outputs from an ensemble of dynamical (physical) models. The proposed framework employs a temporal decay memory unit for imputing missing values in the ensemble member outputs, coupled with an LSTM architecture for dynamic path prediction. The framework is extended to an online learning setting to capture concept drift present in the data. Empirical results suggest that the proposed framework significantly outperforms various baselines including the official forecasts from U.S. National Hurricane Center (NHC).

Authors: Ding Wang (Michigan State University); Pang-Ning Tan (MSU)

Disaster prediction, management, and relief Data mining
ICML 2021 Controlling Weather Field Synthesis Using Variational Autoencoders (Papers Track)
Abstract and authors: (click to expand)

Abstract: One of the consequences of climate change is an observed increase in the frequency of extreme climate events. That poses a challenge for weather forecast and generation algorithms, which learn from historical data but should embed an often uncertain bias to create correct scenarios. This paper investigates how mapping climate data to a known distribution using variational autoencoders might help explore such biases and control the synthesis of weather fields towards more extreme climate scenarios. We experimented using a monsoon-affected precipitation dataset from southwest India, which should give a roughly stable pattern of rainy days and ease our investigation. We report compelling results showing that mapping complex weather data to a known distribution implements an efficient control for weather field synthesis towards more (or less) extreme scenarios.

Authors: Dario Augusto Borges Oliveira (IBM Research); Jorge Luis Guevara Diaz (IBM Research); Bianca Zadrozny (IBM Research); Campbell Watson (IBM Reserch)

Climate and Earth science Generative modeling
ICML 2021 ForestViT: A Vision Transformer Network for Convolution-free Multi-label Image Classification in Deforestation Analysis (Papers Track)
Abstract and authors: (click to expand)

Abstract: Understanding the dynamics of deforestation as well as land uses of neighboring areas is of vital importance for the design and development of appropriate forest conservation and management policies. In this paper, we approach deforestation as a multi-label classification problem in an endeavor to capture the various relevant land uses from satellite images. To this end, we propose a multi-label vision transformer model, ForestViT, which leverages the benefits of self-attention mechanism, obviating any convolution operations involved in commonly used deep learning models utilized for deforestation detection.

Authors: Maria Kaselimi (National Technical University of Athens); Athanasios Voulodimos (University of West Attica); Ioannis Daskalopoulos (University of West Attica); Nikolaos Doulamis (National Technical University of Athens); Anastasios Doulamis (Technical University of Crete)

Agriculture, forestry and other land use Computer vision and remote sensing
ICML 2021 Reducing Carbon in the Design of Large Infrastructure Scheme with Evolutionary Algorithms (Papers Track)
Abstract and authors: (click to expand)

Abstract: The construction and operations of large infrastructure schemes such as railways, roads, pipelines and power lines account for a significant proportion of global carbon emissions. Opportunities to reduce the embodied and operational carbon emissions of new infrastructure schemes are greatest during the design phase. However, schedule and cost constraints limit designers from assessing a large number of design options in detail to identify the solution with the lowest lifetime carbon emissions using conventional methods. Here, we develop an evolutionary algorithm to rapidly evaluate in detail the lifetime carbon emissions of thousands of possible design options for new water transmission pipeline schemes. Our results show that this approach can help designers in some cases to identify design solutions with more than 10% lower operational carbon emissions compared with conventional methods, saving more than 1 million tonnes in lifetime carbon emissions for a new water transmission pipeline scheme. We also find that this evolutionary algorithm can be applied to design other types of infrastructure schemes such as non-water pipelines, railways, roads and power lines.

Authors: Matt Blythe (Continuum Industries)

Buildings and cities Industry Power and energy Transportation
ICML 2021 An Accurate and Scalable Subseasonal Forecasting Toolkit for the United States (Papers Track)
Abstract and authors: (click to expand)

Abstract: We develop a subseasonal forecasting toolkit of accurate and highly scalable benchmarks that outperform both the United States operational Climate Forecasting System (CFSv2) and state-of-the-art learning methods from the literature. Our new learned benchmarks include (a) Climatology++, an enhanced form of climatology using knowledge of only the day of the year; (b) CFSv2++, a learned correction for CFSv2; and (c) Persistence++, an augmented persistence model that combines lagged measurements with CFSv2forecasts. These methods alone improve upon CFSv2 accuracy by 9% for US precipitation and 6% for US temperature over 2011-2020. Ensembling our benchmarks with diverse forecasting methods leads to even further gains. Overall, we find that augmenting classical forecasting approaches with learned corrections yields an effective, low-cost strategy for building next-generation subseasonal forecasting models.

Authors: Soukayna Mouatadid (University of Toronto); Paulo Orenstein (IMPA); Genevieve E Flaspohler (MIT); Miruna Oprescu (Microsoft Research); Judah Cohen (AER); Franklyn Wang (Harvard); Sean Knight (MIT); Ernest Fraenkel (MIT); Lester Mackey (Microsoft Research)

Classification, regression, and supervised learning
ICML 2021 Self-supervised Contrastive Learning for Irrigation Detection in Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change has caused reductions in river runoffs and aquifer recharge resulting in an increasingly unsustainable crop water demand from reduced freshwater availability. Achieving food security while deploying water in a sustainable manner will continue to be a major challenge necessitating careful monitoring and tracking of agricultural water usage. Historically, monitoring water usage has been a slow and expensive manual process with many imperfections and abuses. Ma-chine learning and remote sensing developments have increased the ability to automatically monitor irrigation patterns, but existing techniques often require curated and labelled irrigation data, which are expensive and time consuming to obtain and may not exist for impactful areas such as developing countries. In this paper, we explore an end-to-end real world application of irrigation detection with uncurated and unlabeled satellite imagery. We apply state-of-the-art self-supervised deep learning techniques to optical remote sensing data, and find that we are able to detect irrigation with up to nine times better precision, 90% better recall and 40% more generalization ability than the traditional supervised learning methods.

Authors: Chitra Agastya (UC Berkeley, IBM); Sirak Ghebremusse (UC Berkeley); Ian Anderson (UC Berkeley); Colorado Reed (UC Berkeley); Hossein Vahabi (University California Berkeley); Alberto Todeschini (UC Berkeley)

Unsupervised and semi-supervised learning Agriculture, forestry and other land use Climate and Earth science Classification, regression, and supervised learning Computer vision and remote sensing Meta- and transfer learning
ICML 2021 Extreme Precipitation Seasonal Forecast Using a Transformer Neural Network (Papers Track)
Abstract and authors: (click to expand)

Abstract: An impact of climate change is the increase in frequency and intensity of extreme precipitation events. However, confidently predicting the likelihood of extreme precipitation at seasonal scales remains an outstanding challenge. Here, we present an approach to forecasting the quantiles of the maximum daily precipitation in each week up to six months ahead using the temporal fusion transformer (TFT) model. Through experiments in two regions, we compare TFT predictions with those of two baselines: climatology and a calibrated ECMWF SEAS5 ensemble forecast (S5). Our results show that, in terms of quantile risk at six month lead time, the TFT predictions significantly outperform those from S5 and show an overall small improvement compared to climatology. The TFT also responds positively to departures from normal that climatology cannot.

Authors: Daniel Salles Civitarese (IBM Research, Brazil); Daniela Szwarcman (IBM Research); Bianca Zadrozny (IBM Research); Campbell Watson (IBM Reserch)

Disaster prediction, management, and relief Climate and Earth science Time-series analysis
ICML 2021 BERT Classification of Paris Agreement Climate Action Plans (Papers Track)
Abstract and authors: (click to expand)

Abstract: As the volume of text-based information on climate policy increases, natural language processing (NLP) tools can distill information from text to better inform decision making on climate policy. We investigate how large pretrained transformers based on the BERT architecture classify sentences on a dataset of climate action plans which countries submitted to the United Nations following the 2015 Paris Agreement. We use the document header structure to assign noisy policy-relevant labels such as mitigation, adaptation, energy, and land use to text elements. Our models provide an improvement in out-of-sample classification over simple heuristics though fall short of the consistency observed between human annotators. We hope to extend this framework to a wider class of textual climate change data such as climate legislation and corporate social responsibility filings and build tools to streamline the extraction of information from these documents for climate change researchers.

Authors: Tom Corringham (Scripps Institution of Oceanography); Daniel Spokoyny (Carnegie Mellon University); Eric Xiao (University of California San Diego); Christopher Cha (University of California San Diego); Colin Lemarchand (University of California San Diego); Mandeep Syal (University of California San Diego); Ethan Olson (University of California San Diego); Alexander Gershunov (Scripps Institution of Oceanography)

Natural language processing Policy
ICML 2021 Quantification of Carbon Sequestration in Urban Forests (Papers Track)
Abstract and authors: (click to expand)

Abstract: Vegetation, trees in particular, sequester carbon by absorbing carbon dioxide from the atmosphere, however, the lack of efficient quantification methods of carbon stored in trees renders it difficult to track the process. Here we present an approach to estimate the carbon storage in trees based on fusing multispectral aerial imagery and LiDAR data to identify tree coverage, geometric shape, and tree species, which are crucial attributes in carbon storage quantification. We demonstrate that tree species information and their three-dimensional geometric shapes can be estimated from remote imagery in order to calculate the tree's biomass. Specifically, for Manhattan, New York City, we estimate a total of 52,000 tons of carbon sequestered in trees.

Authors: Levente Klein (IBM Research); Wang Zhou (IBM Research); Conrad M Albrecht (IBM Research)

Carbon capture and sequestration Climate and Earth science Agriculture, forestry and other land use
ICML 2021 A comparative study of stochastic and deep generative models for multisite precipitation synthesis (Papers Track)
Abstract and authors: (click to expand)

Abstract: Future climate change scenarios are usually hypothesized using simulations from weather generators. However, there only a few works comparing and evaluating multisite weather generators, and there is no existing work contrasting promising deep learning approaches for weather generation against classical stochastic weather generators. This study shows preliminary results evaluating stochastic weather generators and deep generative models for multisite precipitation synthesis. Using a variety of metrics, we compare two open source weather generators: XWeathergen (an extension of the Weathergen library) and RGeneratePrec, and two deep generative models: GAN and VAE. Our preliminary results can serve as a guide for improving the design of deep learning architectures and algorithms for the multisite precipitation synthesis task.

Authors: Jorge Luis Guevara Diaz (IBM Research); Dario Augusto Borges Oliveira (IBM Research); Bianca Zadrozny (IBM Research); Campbell Watson (IBM Reserch)

Generative modeling Other
ICML 2021 Self-Supervised Learning on Multispectral Satellite Data for Near-Term Solar Forecasting (Papers Track)
Abstract and authors: (click to expand)

Abstract: With the unprecedented increase in distributed photovoltaic (PV) capacity across the globe, there is an increasing need for reliable and accurate forecasting of solar power generation. While PV output is affected by many factors, the atmosphere, i.e., cloud cover, plays a dominant role in determining the amount of downwelling solar irradiance that reaches PV modules. This paper demonstrates that self-supervised learning of multispectral satellite data from the recently launched GOES-R series of satellites can improve near-term (15 minutes) solar forecasting. We develop deep auto-regressive models using convolutional neural networks (CNN) and long short-term memory networks (LSTM) that are globally trained across many solar sites on the raw spatio-temporal data from GOES-R satellites. This self-supervised model provides estimates of future solar irradiance that can be fed directly to a regression model trained on smaller site-specific solar data to provide near-term solar PV forecasts at the site. The regression implicitly models site-specific characteristics, such as capacity, panel tilt, orientation, etc, while the self-supervised CNN-LSTM implicitly captures global atmospheric patterns affecting a site's solar irradiation. Results across 25 solar sites show the utility of such self-supervised modeling by providing accurate near-term forecast with errors close to that of a model using current ground-truth observations.

Authors: Akansha Singh Bansal (University of Massachusetts Amherst); Trapit Bansal (University of Massachusetts Amherst); David Irwin (University of Massachusetts Amherst)

Unsupervised and semi-supervised learning Other Time-series analysis
ICML 2021 Refining Ice Layer Tracking through Wavelet combined Neural Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: Rise in global temperatures is resulting in polar ice caps to melt away, which can lead to drastic sea level rise and coastal floods. Accurate calculation of the ice cap reduction is necessary in order to project its climatic impact. Ice sheets are monitored through Snow Radar sensors which give noisy profiles of subsurface ice layers. The sensors take snapshots of the entire ice sheet regularly, and thus result in large datasets. In this work, we use convolutional neural networks (CNNs) for their property of feature extraction and generalizability on large datasets. We also use wavelet transforms and embed them as a layer in the architecture to help in denoising the radar images and refine ice layer detection. Our results show that incorporating wavelets in CNNs helps in detecting the position of deep subsurface ice layers, which can be used to analyse their change overtime.

Authors: Debvrat Varshney (University of Maryland Baltimore County); Masoud Yari (College of Engineering and Information Technology, University of Maryland Balitimore County); Tashnim Chowdhury (University of Maryland Baltimore County); Maryam Rahnemoonfar (University of Maryland Baltimore County)

Computer vision and remote sensing Climate and Earth science
ICML 2021 Forecasting Sea Ice Concentrations using Attention-based Ensemble LSTM (Papers Track)
Abstract and authors: (click to expand)

Abstract: Accurately forecasting Arctic sea ice from sub-seasonal to seasonal scales has been a major scientific effort with fundamental challenges at play. In addition to physics-based earth system models, researchers have been applying multiple statistical and machine learning models for sea ice forecasting. Looking at the potential of data-driven sea ice forecasting, we propose an attention-based Long Short Term Memory (LSTM) ensemble method to predict monthly sea ice extent up to 1 month ahead. Using daily and monthly satellite retrieved sea ice data from NSIDC and atmospheric and oceanic variables from ERA5 reanalysis product for 39 years, we show that our multi-temporal ensemble method outperforms several baseline and recently proposed deep learning models. This will substantially improve our ability in predicting future Arctic sea ice changes, which is fundamental for forecasting transporting routes, resource development, coastal erosion, threats to Arctic coastal communities and wildlife.

Authors: Sahara Ali (University of Maryland, Baltimore County); Yiyi Huang (University of Maryland, Baltimore County); Xin Huang (University of Maryland, Baltimore County); Jianwu Wang (University of Maryland, Baltimore County)

Climate and Earth science Ecosystems and natural resources Classification, regression, and supervised learning Time-series analysis
ICML 2021 Toward efficient calibration of higher-resolution Earth System Models (Papers Track) Best Paper: Pathway to Impact
Abstract and authors: (click to expand)

Abstract: Projections of future climate change to support decision-making require high spatial resolution, but this is computationally prohibitive with modern Earth system models (ESMs). A major challenge is the calibration (parameter tuning) process, which requires running large numbers of simulations to identify the optimal parameter values. Here we train a convolutional neural network (CNN) on simulations from two lower-resolution (and thus much less expensive) versions of the same ESM, and a smaller number of higher-resolution simulations. Cross-validated results show that the CNN's skill exceeds that of a climatological baseline for most variables with as few as 5-10 examples of the higher-resolution ESM, and for all variables (including precipitation) with at least 20 examples. This proof-of-concept study offers the prospect of significantly more efficient calibration of ESMs, by reducing the required CPU time for calibration by 20-40 %.

Authors: Christopher Fletcher (University of Waterloo); William McNally (University of Waterloo); John Virgin (University of Waterloo)

Generative modeling Climate and Earth science
ICML 2021 Visual Question Answering: A Deep Interactive Framework for Post-Disaster Management and Damage Assessment (Papers Track)
Abstract and authors: (click to expand)

Abstract: Each natural disaster has left a trail of destruction and damage, which must be managed very effectively to reduce the disaster's impact. Lack of proper decision making in post-disaster managerial level can increase human suffering and waste a great amount of money. Our objective is to incorporate a deep interactive approach in the decision-making system especially in a rescue mission after any natural disaster for the systematic distribution of the limited resources and accelerating the recovery process. We believe that Visual Question Answering (VQA) is the finest way to address this issue. In visual question answering, a query-based answer regarding the situation of the affected area can add value to the decision-making system. Our main purpose of this study is to develop a Visual Question Answering model for post-disaster damage assessment purposes. With this aim, we collect the images by UAV (Unmanned Aerial Vehicle) after Hurricane Harvey and develop a dataset that includes the questions that are very important in the decision support system after a natural disaster. In addition, We propose a supervised attention-based approach in the modeling segment. We compare our approach with the two other baseline attention-based VQA algorithms namely Multimodal Factorized Bilinear (MFB) and Stacked Attention Network (SAN). Our approach outperforms in providing answers for several types of queries including simple counting, complex counting compares to the baseline models.

Authors: Argho Sarkar (University of Maryland, Baltimore County); Maryam Rahnemoonfar (University of Maryland Baltimore County)

Disaster prediction, management, and relief Computer vision and remote sensing
ICML 2021 Designing Bounded min-knapsack Bandits algorithm for Sustainable Demand Response (Papers Track)
Abstract and authors: (click to expand)

Abstract: Around 40% of global energy produced is consumed by buildings. By using renewable energy resources we can alleviate the dependence on electrical grids. Recent trends focus on incentivizing consumers to reduce their demand consumption during peak hours for sustainable demand response. To minimize the loss, the distributor companies should target the right set of consumers and demand the right amount of electricity reductions. This paper proposes a novel bounded integer min-knapsack algorithm and shows that the algorithm, while allowing for multiple unit reduction, also optimizes the loss to the distributor company within a factor of two (multiplicative) and a problem-dependent additive constant. Existing CMAB algorithms fail to work in this setting due to non-monotonicity of reward function and time-varying optimal sets. We propose a novel algorithm Twin-MinKPDR-CB to learn these compliance probabilities efficiently. Twin-MinKPDR-CB works for non-monotone reward functions bounded min-knapsack constraints and time-varying optimal sets. We find that Twin-MinKPDR-CB achieves sub-linear regret of O(log T) with T being the number of rounds demand response is run.

Authors: Akansha Singh (Indian Institute of Technology, Ropar); Meghana Reddy (Indian Institute of Technology, Ropar); Zoltan Nagy (University of Texas); Sujit P. Gujar (Machine Learning Laboratory, International Institute of Information Technology, Hyderabad); Shweta Jain (Indian Institute of Technology Ropar)

Power and energy Buildings and cities Reinforcement learning and control Uncertainty quantification and robustness
ICML 2021 Sky Image Prediction Using Generative Adversarial Networks for Solar Forecasting (Papers Track)
Abstract and authors: (click to expand)

Abstract: Large-scale integration of solar photovoltaics (PV) is challenged by high variability in its power output, mainly due to local and short-term cloud events. To achieve accurate solar forecasting, it is paramount to accurately predict the movement of clouds. Here, we use generative adversarial networks (GANs) to predict future sky images based on past sky image sequences and show that our trained model can generate realistic future sky images and capture the dynamics of clouds in the context frames. The generated images are then evaluated for a downstream solar forecasting task; results show promising performance.

Authors: Yuhao Nie (Stanford University); Andea Scott (Stanford University); Eric Zelikman (Stanford University); Adam Brandt (Stanford University)

Generative modeling Climate and Earth science Computer vision and remote sensing
ICML 2021 EVGen: Adversarial Networks for Learning Electric Vehicle Charging Loads and Hidden Representations (Papers Track)
Abstract and authors: (click to expand)

Abstract: The nexus between transportation, the power grid, and consumer behavior is much more pronounced than ever before as the race to decarbonize intensifies. Electrification in the transportation sector has led to technology shifts and rapid deployment of electric vehicles (EVs). The potential increase in stochastic and spatially heterogeneous charging load presents a unique challenge that is not well studied, and will have significant impacts on grid operations, emissions, and system reliability if not managed effectively. Realistic scenario generators can help operators prepare, and machine learning can be leveraged to this end. In this work, we develop generative adversarial networks (GANs) to learn distributions of electric vehicle (EV) charging sessions and disentangled representations. We show that this model successfully parameterizes unlabeled temporal and power patterns and is able to generate synthetic data conditioned on these patterns. We benchmark the generation capability of this model with Gaussian Mixture Models (GMMs), and empirically show that our proposed model framework is better at capturing charging distributions and temporal dynamics.

Authors: Robert Buechler (Stanford University); Emmanuel O Balogun (Stanford University); Arun Majumdar (Stanford University); Ram Rajagopal (Stanford University)

Power and energy Transportation Generative modeling Unsupervised and semi-supervised learning
ICML 2021 Reconstruction of Long-Term Historical Electricity Demand Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Long-term planning of a robust power system requires the understanding of changing demand patterns. Electricity demand is highly weather sensitive. Thus, the supply side variation from introducing intermittent renewable sources, juxtaposed with variable demand, will introduce additional challenges in the grid planning process. By understanding the spatial and temporal variability of temperature over the US, the response of demand to natural variability and climate change-related effects on temperature can be separated, especially because the effects due to the former factor are not known. Through this project, we aim to better support the technology& policy development process for power systems by developing machine and deep learning ’back-forecasting’ models to reconstruct multidecadaldemand records and study the natural variabilityof temperature and its influence on demand.

Authors: Reshmi Ghosh (Carnegie Mellon University); Michael Craig (University of Michigan); H.Scott Matthews (Carnegie Mellon University); Laure Berti-Equille (IRD)

Classification, regression, and supervised learning Deep Learning
ICML 2021 A Set-Theoretic Approach to Safe Reinforcement Learning in Power Systems (Papers Track)
Abstract and authors: (click to expand)

Abstract: Reducing the carbon footprint of the energy sector will be a vital part of the fight against climate change, and doing so will require the widespread adoption of renewable energy resources. Optimally integrating a large number of these resources requires new control techniques that can both compensate for the variability of renewables and satisfy hard engineering constraints. Reinforcement learning (RL) is a promising approach to data-driven control, but it is difficult to verify that the policies derived from data will be safe. In this paper, we combine RL with set-theoretic control to propose a computationally efficient approach to safe RL. We demonstrate the method on a simplified power system model and compare it with other RL techniques.

Authors: Daniel Tabas (University of Washington); Baosen Zhang (University of Washington)

Reinforcement learning and control Power and energy
ICML 2021 A study of battery SoC scheduling using machine learning with renewable sources (Papers Track)
Abstract and authors: (click to expand)

Abstract: An open energy system (OES) enables the shared distribution of energy resources within a community autonomously and efficiently. For this distributed system a rooftop solar panel and a battery are installed in each house of the community. The OES system monitors the State of Charge (SoC) of each battery independently, arbitrates energy-exchange requests from each house, and physically controls peer-to-peer energy exchanges. In this study, our goal is to optimize those energy exchanges to maximize the renewable energy penetration within the community using machine learning techniques. Future household electricity consumption is predicted using machine learning from the past time series. The predicted consumption is used to determine the next energy-exchange strategy, i.e. when and how much energy should be exchanged to minimize the surplus of solar energy. The simulation results show that the proposed method can increase the amount of renewable energy penetration within the community.

Authors: Daisuke Kawamoto (Sony Computer Science Laboratories, Inc.); Gopinath Rajendiran (CSIR Central Scientific Instruments Organisation, Chennai)

Power and energy Time-series analysis
ICML 2021 Multivariate climate downscaling with latent neural processes (Papers Track)
Abstract and authors: (click to expand)

Abstract: Statistical downscaling is a vital tool in generating high resolution projections for climate impact studies. This study applies convolutional latent neural processes to multivariate downscaling of maximum temperature and precipitation. In contrast to existing downscaling methods, this model is shown to produce spatially coherent predictions at arbitrary locations specified at test time, regardless of whether training data are available at these points.

Authors: Anna Vaughan (Univeristy of Cambridge); Nic Lane (University of Cambridge); Michael Herzog (University of Cambridge)

Climate and Earth science Causal and Bayesian methods
ICML 2021 FIRE-ML: A Remotely-sensed Daily Wildfire Forecasting Dataset for the Contiguous United States (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wildfires are natural phenomena that can have devastating effects on ecosystems, urban developments, and the environment. Improving the scientific understanding of these events and the ability to forecast how they will evolve in the short- and long-term are ongoing multi-decadal challenges. We present a large-scale dataset, well-suited to machine learning, that aggregates and aligns multiple remotely-sensed and forecasted data products to provide a holistic set of features for forecasting wildfires on daily timescales. This dataset includes 4.2 million unique active fire detections, covers the majority of the contiguous United States from 2012 to 2020, and includes active fire detections, land cover, topography, and meteorology.

Authors: Casey A Graff (UC Irvine)

Computer vision and remote sensing Agriculture, forestry and other land use Classification, regression, and supervised learning
ICML 2021 IowaRain: A Statewide Rain Event Dataset Based on Weather Radars and Quantitative Precipitation Estimation (Papers Track)
Abstract and authors: (click to expand)

Abstract: Effective environmental planning and management to address climate change could be achieved through extensive environmental modeling with machine learning and conventional physical models. In order to develop and improve these models, practitioners and researchers need comprehensive benchmark datasets that are prepared and processed with environmental expertise that they can rely on. This study presents an extensive dataset of rainfall events for the state of Iowa (2016-2019) acquired from the National Weather Service Next Generation Weather Radar (NEXRAD) system and processed by a quantitative precipitation estimation system. The dataset presented in this study could be used for better disaster monitoring, response and recovery by paving the way for both predictive and prescriptive modeling.

Authors: Muhammed A Sit (The University of Iowa); Bongchul Seo (IIHR—Hydroscience & Engineering, The University of Iowa); Ibrahim Demir (The University of Iowa)

Data mining Benchmark Datasets
ICML 2021 Short-term Hourly Streamflow Prediction with Graph Convolutional GRU Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: The frequency and impact of floods are expected to increase due to climate change. It is crucial to predict streamflow, consequently flooding, in order to prepare and mitigate its consequences in terms of property damage and fatalities. This paper presents a Graph Convolutional GRUs based model to predict the next 36 hours of streamflow for a sensor location using the upstream river network. As shown in experiment results, the model presented in this study provides better performance than the persistence baseline and a Convolutional Bidirectional GRU network for the selected study area in short-term streamflow prediction.

Authors: Muhammed A Sit (The University of Iowa); Bekir Demiray (The University of Iowa); Ibrahim Demir (The University of Iowa)

Disaster prediction, management, and relief Climate and Earth science Computer vision and remote sensing Interpretable ML Time-series analysis
ICML 2021 Wildfire Smoke Plume Segmentation Using Geostationary Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wildfires have increased in frequency and severity over the past two decades, especially in the Western United States. Beyond physical infrastructure damage caused by these wildfire events, researchers have increasingly identified harmful impacts of particulate matter generated by wildfire smoke on respiratory, cardiovascular, and cognitive health. This inference is difficult due to the spatial and temporal uncertainty regarding how much particulate matter is specifically attributable to wildfire smoke. One factor contributing to this challenge is the reliance on manually drawn smoke plume annotations, which are often noisy representations limited to the United States. This work uses deep convolutional neural networks to segment smoke plumes from geostationary satellite imagery. We compare the performance of predicted plume segmentations versus the noisy annotations using causal inference methods to estimate the amount of variation each explains in Environmental Protection Agency (EPA) measured surface level particulate matter <2.5μm in diameter (PM2.5).

Authors: Jeffrey L Wen (Stanford University); Marshall Burke (Stanford University)

Computer vision and remote sensing Behavioral and social science Climate and Earth science Disaster prediction, management, and relief Societal adaptation Classification, regression, and supervised learning
ICML 2021 Deep Spatial Temporal Forecasting of Electrical Vehicle Charging Demand (Papers Track)
Abstract and authors: (click to expand)

Abstract: Electric vehicles can offer a low carbon emission solution to reverse rising emission trends. However, this requires that the energy used to meet the demand is green. To meet this requirement, accurate forecasting of the charging demand is vital. Short and long-term charging demand forecasting will allow for better optimisation of the power grid and future infrastructure expansions. In this paper, we propose to use publicly available data to forecast the electric vehicle charging demand. To model the complex spatial-temporal correlations between charging stations, we argue that Temporal Graph Convolution Models are the most suitable to capture the correlations. The proposed Temporal Graph Convolutional Networks provide the most accurate forecasts for short and long-term forecasting compared with other forecasting methods.

Authors: Frederik B Hüttel (Technical University of Denmark (DTU)); Filipe Rodrigues (Technical University of Denmark (DTU)); Inon Peled (Technical University of Denmark (DTU)); Francisco Pereira (DTU)

Transportation Power and energy Classification, regression, and supervised learning Time-series analysis
ICML 2021 Powering Effective Climate Communication with a Climate Knowledge Base (Proposals Track)
Abstract and authors: (click to expand)

Abstract: While many accept climate change and its growing impacts, few converse about it well, limiting the adoption speed of societal changes necessary to address it. In order to make effective climate communication easier, we aim to build a system that presents to any individual the climate information predicted to best motivate and inspire them to take action given their unique set of personal values. To alleviate the cold-start problem, the system relies on a knowledge base (ClimateKB) of causes and effects of climate change, and their associations to personal values. Since no such comprehensive ClimateKB exists, we revisit knowledge base construction techniques and build a ClimateKB from free text. We plan to open source the ClimateKB and associated code to encourage future research and applications.

Authors: Kameron B. Rodrigues (Stanford University); Shweta Khushu (SkySpecs Inc); Mukut Mukherjee (ClimateMind); Andrew Banister (Climate Mind); Anthony Hevia (ClimateMind); Sampath Duddu (ClimateMind); Nikita Bhutani (Megagon Labs)

Natural language processing Knowledge engineering
ICML 2021 Solar PV Maps for Estimation and Forecasting of Distributed Solar Generation (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Rapid uptake of distributed solar PV is starting to make the operation of grids and energy markets more challenging, and better methods are needed for measuring and forecasting distributed solar PV generation across entire regions. We propose a method for converting time series data from a number of point sources (power measurements at individual sites) into 2-dimensional maps that estimate total solar PV generation across large areas. These maps may be used on their own, or in conjunction with additional data sources (such as satellite imagery) in a deep learning framework that enables improved regional solar PV estimation and forecasting. We provide some early validation and results, discuss anticipated benefits of this approach, and argue that this method has the potential to further enable significant uptake of solar PV, assisting a shift away from fossil fuel-based generation.

Authors: Julian de Hoog (The University of Melbourne); Maneesha Perera (The University of Melbourne); Kasun Bandara (The University of Melbourne); Damith Senanayake (The University of Melbourne); Saman Halgamuge (University of Melbourne)

Power and energy Classification, regression, and supervised learning Time-series analysis
ICML 2021 An Iterative Approach to Finding Global Solutions of AC Optimal Power Flow Problems (Proposals Track)
Abstract and authors: (click to expand)

Abstract: To achieve a cleaner energy system, a diverse set of energy resources such as solar PV, battery storage and electric vehicles are entering the electric grid. Their operation is typically controlled by solving a resource allocation problem, called the AC optimal power flow (ACOPF) problem. This problem minimizes the cost of generation subject to supply/demand balance and various other engineering constraints. It is nonlinear and nonconvex, and existing solvers are generally successful in finding local solutions. As the share of renewable energy resources increases, it is becoming increasingly important to find globally optimal solutions to utilize these resources to the full extent. In this paper, we propose a simple iterative approach to find globally optimal solutions to ACOPF problems. First, we call an existing solver for the ACOPF problem and we form a partial Lagrangian from the associated dual variables. This partial Lagrangian has a much better optimization landscape and we use its solution as a warm start for the ACOPF problem. By repeating this process, we can iteratively improve the solution quality, moving from local solutions to global ones. We demonstrate the effectiveness of our algorithm on standard benchmarks. We also show how the dual variables could be found by using a neural network to further speed up the algorithm.

Authors: Ling Zhang (University of Washington); Baosen Zhang (University of Washington)

Power and energy
ICML 2021 Deep learning applied to sea surface semantic segmentation: Filtering sunglint from aerial imagery (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Water waves are an ubiquitous feature of the oceans, which serve as a pathway for interactions with the atmosphere. Wave breaking in particular is crucial in developing better understanding of the exchange of momentum, heat, and gas fluxes between the ocean and the atmosphere. Characterizing the properties of wave breaking using orbital or suborbital imagery of the surface of the ocean can be challenging, due to contamination from sunglint, a persistent feature in certain lighting conditions. Here we propose a supervised learning approach to accurately detect whitecaps from airborne imagery obtained under a broad range of lighting conditions. Finally, we discuss potential applications for improving ocean and climate models.

Authors: Teodor Vrecica (UCSD); Quentin Paletta (University of Cambridge); Luc Lenain (UCSD)

Climate and Earth science Classification, regression, and supervised learning Computer vision and remote sensing
ICML 2021 Technical support project and analysis of the dissemination of carbon dioxide and methane from Lake Kivu in nature and its impact on biodiversity in the Great Lakes region since 2012 (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Straddling the Democratic Republic of the Congo and Rwanda, at an altitude of 1,460 m, Lake Kivu is one of the ten great lakes in Africa, alongside the main ones that are Victoria and Tanganyika. Kivu contains very high concentrations of gases (carbon dioxide and methane in particular), produced by volcanic activity in the region and the decomposition of organic matter. It has 2,700 km2 of this body of water, a depth that approaches 500 meters in places. It is estimated to contain 60 billion cubic meters of dissolved methane and about 300 billion cubic meters of carbon dioxide accumulated over time. Lake Kivu, located north of Lake Tanganyika and contains a very high amount of carbon dioxide and methane. Carbon dioxide (CO2) and methane (CH4) are both greenhouse gases that affect how well the planet works. The first stays in the atmosphere for a hundred years while the second stays there only for a dozen years. The effect of the dissemination of these in nature prompts me to collect as much data as possible on their circulation and to suggest possible solutions that are consistent with the Paris Agreement. In addition, many wastes come from households and/or small industries in the towns of Bukavu, Goma for the DRC and those of Gyangugu and Gisenyi for Rwanda constitute a high source of CH4 emissions which also contribute to global warming. The exploitation of methane expected in the near future is an additional threat to the sustainable development of ecosystem resources. For various reasons, Lake Kivu constitutes an adequate model for studying the responses of large tropical lakes to changes linked to human activity: indeed, despite its physical and biogeochemical peculiarities, the limnological and ecological processes of its pelagic waters are subject to the same forcings as in other large lakes in the same region, as shown by recent studies.

Authors: Bulonze Chibaderhe (FEMAC Asbl)

Reinforcement learning and control Carbon capture and sequestration
ICML 2021 Virtual Screening for Perovskites Discovery (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Re-inventing the global energy harvesting system from fossil fuels to renewables is essential for reducing greenhouse gas emissions in line with current climate targets. Perovskite photovoltaics (PVs), the class of materials with relatively unexplored material configurations, play key role in solar energy generation due to their low manufacturing cost and exceptional optoelectronic properties. Without the efficient utilisation of machine learning, the discovery and manufacturing process could take a dangerously long time. We present a high-throughput computational design that leverages machine learning algorithms at various steps in order to assess the suitability of the organic molecules for the perovskite crystals.

Authors: Andrea Karlova (UCL); Cameron C.L. Underwood (University of Surrey); Ravi Silva (University of Surrey)

Power and energy Photovoltaics
ICML 2021 Leveraging Machine Learning for Equitable Transition of Energy Systems (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Our planet is facing overlapping crises of climate change, global pandemic, and systemic inequality. To respond climate change, the energy system is in the midst of its most foundational transition since its inception, from traditional fuel-based energy sources to clean renewable sources. While the transition to a low-carbon energy system is in progress, there is an opportunity to make the new system more just and equitable than the current one that is inequitable in many forms. Measuring inequity in the energy system is a formidable task since it is large scale and the data is coming from abundant data sources. In this work, we lay out a plan to leverage and develop scalable machine learning (ML) tools to measure the equity of the current energy system and to facilitate a just transition to a clean energy system. We focus on two concrete examples. First, we explore how ML can help to measure the inequity in the energy inefficiency of residential houses in the scale of a town or a country. Second, we explore how deep learning techniques can help to estimate the solar potential of residential buildings to facilitate a just installation and incentive allocation of solar panels. The application of ML for energy equity is much broader than the above two examples and we highlight some others as well. The result of this research could be used by policymakers to efficiently allocate energy assistance subsidies in the current energy systems and to ensure justice in their energy transition plans.

Authors: Enea Dodi (UMass Amherst); Anupama A Sitaraman (University of Massachusetts Amherst); Mohammad Hajiesmaili (UMass Amherst); Prashant Shenoy (University of Massachusetts Amherst)

Classification, regression, and supervised learning Climate justice Time-series analysis
ICML 2021 Long-term Burned Area Reconstruction through Deep Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Wildfire impact studies are significantly hampered by the absence of a global long-term burned area dataset. This prevents conclusive statements on the role of anthropogenic activity on wildfire impacts over the last century. Here, we propose a workflow to construct a 1901-2014 reanalysis of monthly global burned area at a 0.5° by 0.5° scale. A neural network will be trained with weather-related, vegetational, societal and economic input parameters, and burned area as output label for the 1982-2014 time period. This model can then be applied to the whole 1901-2014 time period to create a data-driven, long-term burned area reanalysis. This reconstruction will allow to investigate the long-term effect of anthropogenic activity on wildfire impacts, will be used as basis for detection and attribution studies and could help to reduce the uncertainties in future predictions.

Authors: Seppe Lampe (Vrije Universiteit Brussel); Bertrand Le Saux (European Space Agency (ESA)); Inne Vanderkelen (Vrije Universiteit Brussel); Wim Thiery (Vrije Universiteit Brussel)

Disaster prediction, management, and relief Classification, regression, and supervised learning Computer vision and remote sensing
ICML 2021 Preserving the integrity of the Canadian northern ecosystems through insights provided by reinforcement learning-based Arctic fox movement models (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Realistic modeling of the movement of the Arctic fox, one of the main predators of the circumpolar world, is crucial to understand the processes governing the distribution of the Canadian Arctic biodiversity. Current methods, however, are unable to adequately account for complex behaviors as well as intra- and interspecific relationships. We propose to harness the potential of reinforcement learning to develop innovative models that will address these shortcomings and provide the backbone to predict how vertebrate communities may be affected by environmental changes in the Arctic, an essential step towards the elaboration of rational conservation actions.

Authors: Catherine Villeneuve (Université Laval); Frédéric Dulude-De Broin (Université Laval); Pierre Legagneux (Université Laval); Dominique Berteaux (Université du Québec à Rimouski); Audrey Durand (Université Laval)

Ecosystems and natural resources Reinforcement learning and control
ICML 2021 Street2Sat: A Machine Learning Pipeline for Generating Ground-truth Geo-referenced Labeled Datasets from Street-Level Images (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Ground-truth labels on crop type and other variables are critically needed to develop machine learning methods that use satellite observations to combat climate change and food insecurity. These labels difficult and costly to obtain over large areas, particularly in Sub-Saharan Africa where they are most scarce. We propose Street2Sat, a new framework for obtaining large data sets of geo-referenced crop type labels obtained from vehicle-mounted cameras that can be extended to other applications. Using preliminary data from Kenya, we present promising results from this approach and identify future to improve the method before operational use in 5 countries.

Authors: Madhava Paliyam (University of Maryland); Catherine L Nakalembe (University of Maryland); Kevin Liu (University of Maryland); Richard Nyiawung (University of Guelph); Hannah R Kerner (University of Maryland)

Agriculture, forestry and other land use Classification, regression, and supervised learning Computer vision and remote sensing
ICML 2021 From Talk to Action with Accountability: Monitoring the Public Discussion of Policy Makers with Deep Neural Networks and Topic Modelling (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Decades of research on climate have provided a consensus that human activity has changed the climate and we are currently heading into a climate crisis. While public discussion and research efforts on climate change mitigation have increased, potential solutions need to not only be discussed but also effectively deployed. For preventing mismanagement and holding policy makers accountable, transparency and degree of information about government processes have been shown to be crucial. However, currently the quantity of information about climate change discussions and the range of sources make it increasingly difficult for the public and civil society to maintain an overview to hold politicians accountable. In response, we propose a multi-source topic aggregation system (MuSTAS) which processes policy makers speech and rhetoric from several publicly available sources into an easily digestible topic summary. MuSTAS uses novel multi-source hybrid latent Dirichlet allocation to model topics from a variety of documents. This topic digest will serve the general public and civil society in assessing where, how, and when politicians talk about climate and climate policies, enabling them to hold politicians accountable for their actions to mitigate climate change and lack thereof.

Authors: Vili Hätönen (Emblica); Fiona Melzer (University of Edinburgh)

Natural language processing Behavioral and social science Policy Unsupervised and semi-supervised learning
ICML 2021 NeuralNERE: Neural Named Entity Relationship Extraction for End-to-End Climate Change Knowledge Graph Construction (Proposals Track)
Abstract and authors: (click to expand)

Abstract: This paper proposes an end-to-end Neural Named Entity Relationship Extraction model (called NeuralNERE) for climate change knowledge graph (KG) construction, directly from the raw text of relevant news articles. The proposed model will not only remove the need for any kind of human supervision for building knowledge bases for climate change KG construction (used in the case of supervised or dictionary-based KG construction methods), but will also prove to be highly valuable for analyzing climate change by summarising relationships between different factors responsible for climate change, extracting useful insights & reasoning on pivotal events, and helping industry leaders in making more informed future decisions. Additionally, we also introduce the Science Daily Climate Change dataset (called SciDCC) that contains over 11k climate change news articles scraped from the Science Daily website, which could be used for extracting prior knowledge for constructing climate change KGs.

Authors: Prakamya Mishra (Independent Researcher); Rohan Mittal (Independent Researcher)

Natural language processing Behavioral and social science Policy Unsupervised and semi-supervised learning
ICML 2021 A multi-task learning approach to enhance sustainable biomolecule production in engineered microorganisms (Proposals Track)
Abstract and authors: (click to expand)

Abstract: A sustainable alternative to sourcing many materials humans need is metabolic engineering: a field that aims to engineer microorganisms into biological factories that convert renewable feedstocks into valuable biomolecules (i.e., jet fuel, medicine). Microorganism factories must be genetically optimized using predictable DNA sequence tools, however, for many organisms, the exact DNA sequence signals defining their genetic control systems are poorly understood. To better decipher these DNA signals, we propose a multi-task learning approach that uses deep learning and feature attribution methods to identify DNA sequence signals that control gene expression in the methanotroph M. buryatense. This bacterium consumes methane, a potent greenhouse gas. If successful, this work would enhance our ability to build gene expression tools to more effectively engineer M. buryatense into an efficient biomolecule factory that can divert methane pollution into valuable, everyday materials.

Authors: Erin Wilson (University of Washington); Mary Lidstrom (University of Washington); David Beck (University of Washington)

Other Sustainable molecule production
ICML 2021 MethaNet - an AI-driven approach to quantifying methane point-source emission from high-resolution 2-D plume imagery (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Methane (CH4) is one of the most powerful anthropogenic greenhouse gases with a significant impact on global warming trajectory and tropospheric air quality. Quantifying an emission rate of observed CH4 plumes from aerial or satellite images is a critical step for understanding the local distributions and subsequently prioritizing mitigation target sites. However, there exists no method that can reliably predict emission rates from detected plumes in real-time without ancillary data. Here, we trained a convolutional neural network model, called MethaNet, to predict methane point-source emission directly from high-resolution 2-D plume images without relying on other local measurements such as background wind speeds. Our results support the basis for the applicability of using deep learning techniques to quantify CH4 point sources in an automated manner over large geographical areas. MethaNet opens the way for real-time monitoring systems, not only for present and future airborne field campaigns but also for upcoming space-based observations in this decade.

Authors: Siraput Jongaramrungruang (Caltech)

Computer vision and remote sensing Carbon capture and sequestration Climate and Earth science Classification, regression, and supervised learning
ICML 2021 Tackling the Overestimation of Forest Carbon with Deep Learning and Aerial Imagery (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Forest carbon offsets are increasingly popular and can play a significant role in financing climate mitigation, forest conservation, and reforestation. Measuring how much carbon is stored in forests is, however, still largely done via expensive, time-consuming, and sometimes unaccountable field measurements. To overcome these limitations, many verification bodies are leveraging machine learning (ML) algorithms to estimate forest carbon from satellite or aerial imagery. Aerial imagery allows for tree species or family classification, which improves on the satellite imagery-based forest type classification. However, aerial imagery is significantly more expensive to collect and it is unclear by how much the higher resolution improves the forest carbon estimation. This proposal paper describes the first systematic comparison of forest carbon estimation from aerial imagery, satellite imagery, and “ground-truth“ field measurements via deep learning-based algorithms for a tropical reforestation project. Our initial results show that forest carbon estimates from satellite imagery can overestimate above-ground biomass by more than 10-times for tropical reforestation projects. The significant difference between aerial and satellite-derived forest carbon measurements shows the potential for aerial imagery-based ML algorithms and raises the importance to extend this study to a global benchmark between options for carbon measurements.

Authors: Gyri Reiersen (TUM); David Dao (ETH Zurich); Björn Lütjens (MIT); Konstantin Klemmer (University of Warwick); Xiaoxiang Zhu (Technical University of Munich,Germany); Ce Zhang (ETH)

Carbon capture and sequestration Computer vision and remote sensing
ICML 2021 Learning Why: Data-Driven Causal Evaluations of Climate Models (Proposals Track)
Abstract and authors: (click to expand)

Abstract: We plan to use nascent data-driven causal discovery methods to find and compare causal relationships in observed data and climate model output. We will look at ten different features in the Arctic climate collected from public databases and from the Energy Exascale Earth System Model (E3SM). In identifying and comparing the resulting causal networks, we hope to find important differences between observed causal relationships and those in climate models. With these, climate modeling experts will be able to improve the coupling and parameterization of E3SM and other climate models.

Authors: Jeffrey J Nichol (University of New Mexico); Matthew Peterson (Sandia National Laboratories); George M Fricke (UNM); Kara Peterson (Sandia National Laboratories)

Climate and Earth science Causal and Bayesian methods
ICML 2021 Enhancing Laboratory-scale Flow Imaging of Fractured Geological Media with Deep Learning Super Resolution (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Injection into deep geological formations is a promising approach for the utilization, sequestration, and removal from the atmosphere of CO2 emissions. Laboratory experiments are essential to characterize how CO2 flows and reacts in various types of geological media. We reproduce such dynamic injection processes while imaging using Computed Tomography (CT) at sufficient temporal resolution to visualize changes in the flow field. The resolution of CT, however, is on the order of 100's of micrometers and insufficient to characterize fine-scale reaction-induced alterations to micro-fractures. Super resolution deep learning is, therefore, an essential tool to improve spatial resolution of dynamic CT images. We acquired and processed pairs of multi-scale low- and high-resolution CT rock images. We also show the performance of our baseline model on fractured rock images using peak signal to noise ratio and structural similarity index. Coupling dynamic CT imaging with deep learning results in visualization with enhanced spatial resolution of about a factor of 4 thereby enabling improved interpretation.

Authors: Manju Pharkavi Murugesu (Stanford University); Timothy Anderson (Stanford University); Niccolo Dal Santo (MathWorks, Inc.); Vignesh Krishnan (The MathWorks Ltd); Anthony Kovscek (Stanford University)

Carbon capture and sequestration Climate and Earth science Computer vision and remote sensing Generative modeling Unsupervised and semi-supervised learning
ICML 2021 Forecasting emissions through Kaya identity using Neural ODEs (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Starting from Kaya identity, we used a Neural ODE model to predict the evolution of several indicators related to carbon emissions, on a country-level : population, GDP per capita, energy intensity of GDP, carbon intensity of energy. We compared the model with a baseline statistical model - VAR - and obtained good performances. We conclude that this machine-learning approach can be used to produce a wide range of results and give relevant insight to policymakers.

Authors: Pierre Browne (Imperial College London)

Time-series analysis Policy Power and energy
ICML 2021 On the Role of Spatial Clustering Algorithms in Building Species Distribution Models from Community Science Data (Proposals Track) Best Paper: Proposals
Abstract and authors: (click to expand)

Abstract: This paper discusses opportunities for developments in spatial clustering methods to help leverage broad scale community science data for building species distribution models (SDMs). SDMs are tools that inform the science and policy needed to mitigate the impacts of climate change on biodiversity. Community science data span spatial and temporal scales unachievable by expert surveys alone, but they lack the structure imposed in smaller scale studies to allow adjustments for observational biases. Spatial clustering approaches can construct the necessary structure after surveys have occurred, but more work is needed to ensure that they are effective for this purpose. In this proposal, we describe the role of spatial clustering for realizing the potential of large biodiversity datasets, how existing methods approach this problem, and ideas for future work.

Authors: Mark Roth (Oregon State University); Tyler Hallman (Swiss Ornithological Institute); W. Douglas Robinson (Oregon State University); Rebecca Hutchinson (Oregon State University)

Ecosystems and natural resources Unsupervised and semi-supervised learning
ICML 2021 Machine Learning for Climate Change: Guiding Discovery of Sorbent Materials for Direct Air Capture of CO2 (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The global climate crisis requires interdisciplinary collaboration. The same is true for making significant strides in materials discovery for direct air capture (DAC) of carbon dioxide (CO2). DAC is an emerging technology that captures CO2 directly from the atmosphere and it is part of the solution to achieving carbon neutrality by 2050. The proposed project is a collaborative effort that tackles climate change by using machine learning to guide scientists to novel, optimized, advanced sorbent materials for direct air capture of CO2. Immediate impacts will include high throughput machine learning tools for developing new, cost-effective CO2 sorption materials, and continued, expanded collaborations with potential domestic and international stakeholders.

Authors: Diana L Ortiz-Montalvo (NIST); Aaron Gilad Kusne (NIST); Austin McDannald (NIST); Daniel Siderius (NIST); Kamal Choudhary (NIST); Taner Yildirim (NIST)

Carbon capture and sequestration Active learning
ICML 2021 Reducing greenhouse gas emissions by optimizing room temperature set-points (Proposals Track)
Abstract and authors: (click to expand)

Abstract: We design a learning and optimization framework to mitigate greenhouse gas emissions associated with heating and cooling buildings. The framework optimizes room temperature set-points based on forecasts of weather, occupancy, and the greenhouse gas intensity of electricity. We compare two approaches: the first one combines a linear load forecasting model with convex optimization that offers a globally optimal solution, whereas the second one combines a nonlinear load forecasting model with nonconvex optimization that offers a locally optimal solution. The project explores the two approaches with a simulation testbed in EnergyPlus and experiments in university-campus buildings.

Authors: Yuan Cai (MIT); Subhro Das (MIT-IBM Watson AI Lab, IBM Research); Leslie Norford (Massachusetts Institute of Technology); Jeremy Gregory (Massachusetts Institute of Technology); Julia Wang (Massachusetts Institute of Technology); Kevin J Kircher (MIT); Jasmina Burek (Massachusetts Institute of Technology)

Buildings and cities Power and energy Classification, regression, and supervised learning Time-series analysis
ICML 2021 Deep learning network to project future Arctic ocean waves (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The Arctic Ocean is warming at an alarming rate and will likely become ice-free in summer by mid-century. This will be accompanied by higher ocean surface waves, which pose a risk to coastal communities and marine operations. In order to develop climate change adaptation strategies, it is imperative to robustly assess the future changes in the Arctic ocean wave climate. This requires a large ensemble of regional ocean wave projections to properly capture the range of climate modeling uncertainty in the Arctic region. This has been proven challenging, as ocean wave information is typically not provided by climate models, ocean wave numerical modeling is computationally expensive, and most global wave climate ensembles exclude the Arctic region. Here we present a framework to develop a deep learning network based on CNN and LSTM which could be potentially used to obtain such a large ensemble of Arctic wave projections with an affordable cost.

Authors: Merce Casas Prat (Environment and Climate Change Canada); Lluis Castrejon (Mila, Université de Montréal, Facebook AI Research); Shady Moahmmed (University of Ottawa)

Climate and Earth science Computer vision and remote sensing
ICML 2021 Deep Learning for Spatiotemporal Anomaly Forecasting: A Case Study of Marine Heatwaves (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Spatiotemporal data have unique properties and require specific considerations. Forecasting spatiotemporal processes is a difficult task because the data are high-dimensional, often are limited in extent, and temporally correlated. Hence, we propose to evaluate several deep learning-based approaches that are relevant to spatiotemporal anomaly forecasting. We will use marine heatwaves as a case study. Those are observed around the world and have strong impacts on marine ecosystems. The evaluated deep learning methods will be integrated for the task of marine heatwave prediction in order to overcome the limitations of spatiotemporal data and improve data-driven seasonal marine heatwave forecasts.

Authors: Ding Ning (University of Canterbury); Varvara Vetrova (University of Canterbury); Karin Bryan (University of Waikato); Sébastien Delaux (Meteorological Service of New Zealand)

Classification, regression, and supervised learning Climate and Earth science
ICML 2021 Leveraging Domain Adaptation for Low-Resource Geospatial Machine Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Machine learning in remote sensing has matured alongside a proliferation in availability and resolution of geospatial imagery, but its utility is bottlenecked by the need for labeled data. What's more, many labeled geospatial datasets are specific to certain regions, instruments, or extreme weather events. We investigate the application of modern domain-adaptation to multiple proposed geospatial benchmarks, uncovering unique challenges and proposing solutions to them.

Authors: John M Lynch (NC State University); Sam Wookey (Masterful AI)

Unsupervised and semi-supervised learning Ecosystems and natural resources Computer vision and remote sensing
ICML 2021 APPLYING TRANSFORMER TO IMPUTATION OF MULTI-VARIATE ENERGY TIME SERIES DATA (Proposals Track)
Abstract and authors: (click to expand)

Abstract: To reduce the greenhouse gas emissions from electricity production, it is necessaryto switch to an energy system based on renewable energy sources (RES). However,intermittent electricity generation from RES poses challenges for energy systems.The primary input for data-driven solutions is data on electricity generation fromRES, which usually contain many missing values. This proposal studies the useof attention-based algorithms to impute missing values of electricity production,electricity demand and electricity prices. Since attention mechanisms allow us totake into account dependencies between time series across multiple dimensionsefficiently, our approach goes beyond classic statistical methods and incorporatesmany related variables, such as electricity price, demand and production by othersources. Our preliminary results show that while transformers can come at highercomputational costs, they are more precise than classical imputation methods.

Authors: Hasan Ümitcan Yilmaz (Karlsruhe Institute of Technology); Max Kleinebrahm (Karlsruhe Institut für Technologie); Christopher Bülte (Karlsruhe Institute of Technology); Juan Gómez-Romero (Universidad de Granada)

Power and energy Time-series analysis Unsupervised and semi-supervised learning
NeurIPS 2020 Electric Vehicle Range Improvement by Utilizing Deep Learning to Optimize Occupant Thermal Comfort (Papers Track)
Abstract and authors: (click to expand)

Abstract: Heating, ventilation and air-conditioning (HVAC) systems can have a significant impact on the driving range of battery electric vehicles (EV’s). Predicting thermal comfort in an automotive vehicle cabin’s highly asymmetric and dynamic thermal environment is critical for developing energy-efficient HVAC systems. In this study we have coupled high-fidelity Computational Fluid Dynamics (CFD) simulations and Artificial Neural Networks (ANN) to predict vehicle occupant thermal comfort for any combination of steady-state boundary conditions. A vehicle cabin CFD model, validated against climatic wind tunnel measurements, was used to systematically generate training and test data that spanned the entire range of boundary conditions which impact occupant thermal comfort in an electric vehicle. Artificial neural networks (ANN) were applied to the simulation data to predict the overall Equivalent Homogeneous Temperature (EHT) comfort index for each occupant. An ensemble of five neural network models was able to achieve a mean absolute error of 2 ºC or less in predicting the overall EHT for all occupants in the vehicle on unseen or test data, which is acceptable for rapid evaluation and optimization of thermal comfort energy demand. The deep learning model developed in this work enables predictions of thermal comfort for any combination of steady-state boundary conditions in real-time without being limited by time-consuming and expensive CFD simulations or climatic wind tunnel tests. This model has been deployed as an easy-to-use web application within the organization for HVAC engineers to optimize thermal comfort energy demand and, thereby, driving range of electric vehicle programs.

Authors: Alok Warey (General Motors Global Research and Development); Shailendra Kaushik (General Motors Global Research and Development); Bahram Khalighi (General Motors Global Research and Development); Michael Cruse (Siemens Digital Industries Software); Ganesh Venkatesan (Siemens Digital Industries Software)

Transportation Classification, regression, and supervised learning
NeurIPS 2020 Is Africa leapfrogging to renewables or heading for carbon lock-in? A machine-learning-based approach to predicting success of power-generation projects (Papers Track)
Abstract and authors: (click to expand)

Abstract: Several extant energy-planning studies, comprising wide-ranging assumptions about the future, feature projections of Africa’s rapid transition in the next decade towards renewables-based power generation. Here, we develop a novel empirical approach to predicting medium-term generation mix that can complement traditional energy planning. Relying on the largest dataset on historic and planned power plants available for Africa, combined with country-level characteristics, we build a machine-learning-based model, using gradient boosted trees, that demonstrates high predictive performance. Training our model on past successful and failed projects, we find that the most relevant factors for commissioning are plant-level: capacity, fuel, ownership and grid connection type. We then apply the trained model to predict the realisation of the current project pipeline. Contrary to the rapid transition scenarios, our results show that the share of non-hydro renewables in generation is likely to remain below 10% in 2030, despite total generation more than doubling. These findings point to high carbon lock-in risks in Africa, highlighting the urgency to shift its pipeline of projects towards low-carbon energy and improve the realisation chances of renewable energy plants.

Authors: Galina Alova (University of Oxford); Philipp Trotter (University of Oxford); Alex Money (University of Oxford)

Power and energy Climate finance Classification, regression, and supervised learning Interpretable ML
NeurIPS 2020 pymgrid: An Open-Source Python Microgrid Simulator for Applied Artificial Intelligence Research (Papers Track)
Abstract and authors: (click to expand)

Abstract: Microgrids – self-contained electrical grids that are capable of disconnecting from the main grid – hold potential in both tackling climate change mitigation via reducing CO$_2$ emissions and adaptation by increasing infrastructure resiliency. Due to their distributed nature, microgrids are often idiosyncratic; as a result, control of these systems is nontrivial. While microgrid simulators exist, many are limited in scope and in the variety of microgrids they can simulate. We propose \HL{pymgrid}, an open-source Python package to generate and simulate a large number of microgrids, and the first open-source tool that can generate more than 600 different microgrids. \HL{pymgrid} abstracts most of the domain expertise, allowing users to focus on control algorithms. In particular, \HL{pymgrid} is built to be a reinforcement learning (RL) platform, and includes the ability to model microgrids as Markov decision processes. \HL{pymgrid} also introduces two pre-computed list of microgrids, intended to allow for research reproducibility in the microgrid setting.

Authors: Gonzague Henri (Total); Tanguy Levent (Ecole Polytechnique); Avishai Halev (Total, UC Davis); Reda ALAMI (Total R&D); Philippe Cordier (Total S.A.)

Power and energy Reinforcement learning and control
NeurIPS 2020 Towards Optimal District Heating Temperature Control in China with Deep Reinforcement Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Achieving efficiency gains in Chinese district heating networks, thereby reducing their carbon footprint, requires new optimal control methods going beyond current industry tools. Focusing on the secondary network, we propose a data-driven deep reinforcement learning (DRL) approach to address this task. We build a recurrent neural network, trained on simulated data, to predict the indoor temperatures. This model is then used to train two DRL agents, with or without expert guidance, for the optimal control of the supply water temperature. Our tests in a multi-apartment setting show that both agents can ensure a higher thermal comfort and at the same time a smaller energy cost, compared to an optimized baseline strategy.

Authors: Adrien Le Coz (EDF); Tahar Nabil (EDF); Francois Courtot (EDF)

Buildings and cities Reinforcement learning and control
NeurIPS 2020 Deep Reinforcement Learning in Electricity Generation Investment for the Minimization of Long-Term Carbon Emissions and Electricity Costs (Papers Track)
Abstract and authors: (click to expand)

Abstract: A change from a high-carbon emitting electricity power system to one based on renewables would aid in the mitigation of climate change. Decarbonization of the electricity grid would allow for low-carbon heating, cooling and transport. Investments in renewable energy must be made over a long time horizon to maximise return of investment of these long life power generators. Over these long time horizons, there exist multiple uncertainties, for example in future electricity demand and costs to consumers and investors. To mitigate for imperfect information of the future, we use the deep deterministic policy gradient (DDPG) deep reinforcement learning approach to optimize for a low-cost, low-carbon electricity supply using a modified version of the FTT:Power model. In this work, we model the UK and Ireland electricity markets. The DDPG algorithm is able to learn the optimum electricity mix through experience and achieves this between the years of 2017 and 2050. We find that a change from fossil fuels and nuclear power to renewables, based upon wind, solar and wave would provide a cheap and low-carbon alternative to fossil fuels.

Authors: Alexander J. M. Kell (Newcastle University); Pablo Salas (University of Cambridge); Jean-Francois Mercure (University of Exeter); Matthew Forshaw (Newcastle University); A. Stephen McGough (Newcastle University)

Power and energy Reinforcement learning and control
NeurIPS 2020 Short-Term Solar Irradiance Forecasting Using Calibrated Probabilistic Models (Papers Track)
Abstract and authors: (click to expand)

Abstract: Advancing probabilistic solar forecasting methods is essential to supporting the integration of solar energy into the electricity grid. In this work, we develop a variety of state-of-the-art probabilistic models for forecasting solar irradiance. We investigate the use of post-hoc calibration techniques for ensuring well-calibrated probabilistic predictions. We train and evaluate the models using public data from seven stations in the SURFRAD network, and demonstrate that the best model, NGBoost, achieves higher performance at an intra-hourly resolution than the best benchmark solar irradiance forecasting model across all stations. Further, we show that NGBoost with CRUDE post-hoc calibration achieves comparable performance to a numerical weather prediction model on hourly-resolution forecasting.

Authors: Eric Zelikman (Stanford University); Sharon Zhou (Stanford University); Jeremy A Irvin (Stanford); Cooper Raterink (Stanford University); Hao Sheng (Stanford University); Avati Anand (Stanford University); Jack Kelly (Open Climate Fix); Ram Rajagopal (Stanford University); Andrew Ng (Stanford University); David J Gagne (National Center for Atmospheric Research)

Power and energy Climate and Earth science Causal and Bayesian methods Uncertainty quantification and robustness
NeurIPS 2020 Deep Learning for Climate Model Output Statistics (Papers Track) Best ML Innovation
Abstract and authors: (click to expand)

Abstract: Climate models are an important tool for the assessment of prospective climate change effects but they suffer from systematic and representation errors, especially for precipitation. Model output statistics (MOS) reduce these errors by fitting the model output to observational data with machine learning. In this work, we explore the feasibility and potential of deep learning with convolutional neural networks (CNNs) for MOS. We propose the CNN architecture ConvMOS specifically designed for reducing errors in climate model outputs and apply it to the climate model REMO. Our results show a considerable reduction of errors and mostly improved performance compared to three commonly used MOS approaches.

Authors: Michael Steininger (University of Würzburg); Daniel Abel (University of Würzburg); Katrin Ziegler (University of Würzburg); Anna Krause (Universität Würzburg, Department of Computer Science, CHair X Data Science); Heiko Paeth (University of Würzburg); Andreas Hotho (Universitat Wurzburg)

Climate and Earth science Classification, regression, and supervised learning
NeurIPS 2020 A Temporally Consistent Image-based Sun Tracking Algorithm for Solar Energy Forecasting Applications (Papers Track)
Abstract and authors: (click to expand)

Abstract: Improving irradiance forecasting is critical to further increase the share of solar in the energy mix. On a short time scale, fish-eye cameras on the ground are used to capture cloud displacements causing the local variability of the electricity production. As most of the solar radiation comes directly from the Sun, current forecasting approaches use its position in the image as a reference to interpret the cloud cover dynamics. However, existing Sun tracking methods rely on external data and a calibration of the camera, which requires access to the device. To address these limitations, this study introduces an image-based Sun tracking algorithm to localise the Sun in the image when it is visible and interpolate its daily trajectory from past observations. We validate the method on a set of sky images collected over a year at SIRTA's lab. Experimental results show that the proposed method provides robust smooth Sun trajectories with a mean absolute error below 1% of the image size.

Authors: Quentin Paletta (University of Cambridge); Joan Lasenby (University of Cambridge)

Power and energy Classification, regression, and supervised learning Computer vision and remote sensing Time-series analysis
NeurIPS 2020 Characterization of Industrial Smoke Plumes from Remote Sensing Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: The major driver of global warming has been identified as the anthropogenic release of greenhouse gas (GHG) emissions from industrial activities. The quantitative monitoring of these emissions is mandatory to fully understand their effect on the Earth’s climate and to enforce emission regulations on a large scale. In this work, we investigate the possibility to detect and quantify industrial smoke plumes from globally and freely available multi-band image data from ESA’s Sentinel-2 satellites. Using a modified ResNet-50, we can detect smoke plumes of different sizes with an accuracy of 94.3%. The model correctly ignores natural clouds and focuses on those imaging channels that are related to the spectral absorption from aerosols and water vapor, enabling the localization of smoke. We exploit this localization ability and train a U-Net segmentation model on a labeled sub-sample of our data, resulting in an Intersection-over-Union (IoU) metric of 0.608 and an overall accuracy for the detection of any smoke plume of 94.0%; on average, our model can reproduce the area covered by smoke in an image to within 5.6%. The performance of our model is mostly limited by occasional confusion with surface objects, the inability to identify semi-transparent smoke, and human limitations to properly identify smoke based on RGB-only images. Nevertheless, our results enable us to reliably detect and qualitatively estimate the level of smoke activity in order to monitor activity in industrial plants across the globe. Our data set and code base are publicly available.

Authors: Michael Mommert (University of St. Gallen); Mario Sigel (Sociovestix Labs Ltd.); Marcel Neuhausler (ISS Technology Innovation Lab); Linus M. Scheibenreif (University of St. Gallen); Damian Borth (University of St. Gallen)

Computer vision and remote sensing Industry
NeurIPS 2020 Learning the distribution of extreme precipitation from atmospheric general circulation model variables (Papers Track)
Abstract and authors: (click to expand)

Abstract: Precipitation extremes are projected to become more frequent and severe in a warming atmosphere over the coming decades. However, the accurate prediction of precipitation, in particular of extremes, remains a challenge for numerical weather prediction models. A large source of error are subgrid-scale parameterizations of processes that play a crucial role in the complex, multi-scale dynamics of precipitation, but are not explicitly resolved in the model formulation. Here we follow a hybrid, data-driven approach, in which atmospheric variables such as wind fields are forecast in time by a general circulation model (GCM) ensemble and then mapped to precipitation using a deep convolutional autoencoder. A frequency-based weighting of the loss function is introduced to improve the learning with regard to extreme values. Our results show an improved representation of extreme precipitation frequencies, as well as better error and correlation statistics compared to a state-of-the-art GCM ensemble.

Authors: Philipp Hess (Free University Berlin); Niklas Boers (Free University Berlin)

Climate and Earth science Hybrid physical models
NeurIPS 2020 Towards Tracking the Emissions of Every Power Plant on the Planet (Papers Track) Best Pathway to Impact
Abstract and authors: (click to expand)

Abstract: Greenhouse gases emitted from fossil-fuel-burning power plants are a major contributor to climate change. Current methods to track emissions from individual sources are expensive and only used in a few countries. While carbon dioxide concentrations can be measured globally using remote sensing, background fluctuations and low spatial resolution make it difficult to attribute emissions to individual sources. We use machine learning to infer power generation and emissions from visible and thermal power plant signatures in satellite images. By training on a data set of power plants for which we know the generation or emissions, we are able to apply our models globally. This paper demonstrates initial progress on this project by predicting whether a power plant is on or off from a single satellite image.

Authors: Heather D Couture (Pixel Scientia Labs); Joseph O'Connor (Carbon Tracker); Grace Mitchell (WattTime); Isabella Söldner-Rembold (Carbon Tracker); Durand D'souza (Carbon Tracker); Krishna Karra (WattTime); Keto Zhang (WattTime); Ali Rouzbeh Kargar (WattTime); Thomas Kassel (WattTime); Brian Goldman (Google); Daniel Tyrrell (Google); Wanda Czerwinski (Google); Alok Talekar (Google); Colin McCormick (Georgetown University)

Power and energy Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2020 Spatio-Temporal Learning for Feature Extraction inTime-Series Images (Papers Track)
Abstract and authors: (click to expand)

Abstract: Earth observation programs have provided highly useful information in global climate change research over the past few decades and greatly promoted its development, especially through providing biological, physical, and chemical parameters on a global scale. Programs such as Landsat, Sentinel, SPOT, and Pleiades can be used to acquire huge volume of medium to high resolution images every day. In this work, we organize these data in time series and we exploit both temporal and spatial information they provide to generate accurate and up-to-date land cover maps that can be used to monitor vulnerable areas threatened by the ongoing climatic and anthropogenic global changes. For this purpose, we combine a fully convolutional neural network with a convolutional long short-term memory. Implementation details of the proposed spatio-temporal neural network architecture are described. Examples are provided for the monitoring of roads and mangrove forests on the West African coast.

Authors: Gael Kamdem De Teyou (Huawei)

Agriculture, forestry and other land use Ecosystems and natural resources
NeurIPS 2020 Meta-modeling strategy for data-driven forecasting (Papers Track)
Abstract and authors: (click to expand)

Abstract: Accurately forecasting the weather is a key requirement for climate change mitigation. Data-driven methods offer the ability to make more accurate forecasts, but lack interpretability and can be expensive to train and deploy if models are not carefully developed. Here, we make use of two historical climate data sets and tools from machine learning, to accurately predict temperature fields. Furthermore, we are able to use low fidelity models that are cheap to train and evaluate, to selectively avoid expensive high fidelity function evaluations, as well as uncover seasonal variations in predictive power. This allows for an adaptive training strategy for computationally efficient geophysical emulation.

Authors: Dominic J Skinner (MIT); Romit Maulik (Argonne National Laboratory)

Climate and Earth science Interpretable ML Time-series analysis
NeurIPS 2020 Short-term prediction of photovoltaic power generation using Gaussian process regression (Papers Track)
Abstract and authors: (click to expand)

Abstract: Photovoltaic (PV) power is affected by weather conditions, making the power generated from the PV systems uncertain. Solving this problem would help improve the reliability and cost effectiveness of the grid, and could help reduce reliance on fossil fuel plants. The present paper focuses on evaluating predictions of the energy generated by PV systems in the United Kingdom using Gaussian process regression (GPR). Gaussian process regression is a Bayesian non-parametric model that can provide predictions along with the uncertainty in the predicted value, which can be very useful in applications with a high degree of uncertainty. The model is evaluated for short-term forecasts of 48 hours against three main factors – training period, sky area coverage and kernel model selection – and for very short-term forecasts of four hours against sky area. We also compare very short-term forecasts in terms of cloud coverage within the prediction period and only initial cloud coverage as a predictor.

Authors: Yahya Hasan Al Lawati (Queen Mary University of London); Jack Kelly (Open Climate Fix); Dan Stowell (Queen Mary University of London)

Classification, regression, and supervised learning Causal and Bayesian methods
NeurIPS 2020 Formatting the Landscape: Spatial conditional GAN for varying population in satellite imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change is expected to reshuffle the settlement landscape: forcing people in affected areas to migrate, to change their lifeways, and continuing to affect demographic change throughout the world. Changes to the geographic distribution of population will have dramatic impacts on land use and land cover and thus constitute one of the major challenges of planning for climate change scenarios. In this paper, we explore a generative model framework for generating satellite imagery conditional on gridded population distributions. We make additions to the existing ALAE [30] architecture, creating a spatially conditional version: SCALAE. This method allows us to explicitly disentangle population from the model’s latent space and thus input custom population forecasts into the generated imagery. We postulate that such imagery could then be directly used for land cover and land use change estimation using existing frameworks, as well as for realistic visualisation of expected local change. We evaluate the model by comparing pixel and semantic reconstructions, as well as calculate the standard FID metric. The results suggest the model captures population distributions accurately and delivers a controllable method to generate realistic satellite imagery.

Authors: Tomas Langer (Intuition Machines); Natalia Fedorova (Max Planck Institute for Evolutionary Anthropology); Ron Hagensieker (Osir.io)

Generative modeling Behavioral and social science Buildings and cities Societal adaptation Computer vision and remote sensing
NeurIPS 2020 Storing Energy with Organic Molecules: Towards a Metric for Improving Molecular Performance for Redox Flow Batteries (Papers Track)
Abstract and authors: (click to expand)

Abstract: Energy storage is an important tool in the decarbonization of energy systems, particularly when coupled with intermittent forms of energy. However, storage technologies are still not commercially competitive to garner mainstream adoption. This work focuses on the cost reduction of organic redox flow batteries (ORFBs) via materials discovery. We identify macroscopic metrics of interest to optimize for lowering their cost and relate them to the molecular properties of the materials involved. Furthermore, we consolidate a benchmark set of experimental data for building predictive models for these materials properties. Building more accurate models will aid practitioners in the rational design of new ORFB.

Authors: Luis M Mejia Mendoza (University of Toronto); Alan Aspuru-Guzik (Harvard University); Martha Flores Leonar (University of Toronto)

Classification, regression, and supervised learning Other Meta- and transfer learning
NeurIPS 2020 Predicting Landsat Reflectance with Deep Generative Fusion (Papers Track)
Abstract and authors: (click to expand)

Abstract: Public satellite missions are commonly bound to a trade-off between spatial and temporal resolution as no single sensor provides fine-grained acquisitions with frequent coverage. This hinders their potential to assist vegetation monitoring or humanitarian actions, which require detecting rapid and detailed terrestrial surface changes. In this work, we probe the potential of deep generative models to produce high-resolution optical imagery by fusing products with different spatial and temporal characteristics. We introduce a dataset of co-registered Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat surface reflectance time series and demonstrate the ability of our generative model to blend coarse daily reflectance information into low-paced finer acquisitions. We benchmark our proposed model against state-of-the-art reflectance fusion algorithms.

Authors: Shahine Bouabid (University of Oxford); Jevgenij Gamper (Cervest Ltd.)

Generative modeling Agriculture, forestry and other land use Computer vision and remote sensing
NeurIPS 2020 Quantitative Assessment of Drought Impacts Using XGBoost based on the Drought Impact Reporter (Papers Track)
Abstract and authors: (click to expand)

Abstract: Under climate change, the increasing frequency, intensity, and spatial extent of drought events lead to higher socio-economic costs. However, the relationships between the hydro-meteorological indicators and drought impacts are not identified well yet because of the complexity and data scarcity. In this paper, we proposed a framework based on the extreme gradient model (XGBoost) for Texas to predict multi-category drought impacts and connected a typical drought indicator, Standardized Precipitation Index (SPI), to the text-based impacts from the Drought Impact Reporter (DIR). The preliminary results of this study showed an outstanding performance of the well-trained models to assess drought impacts on agriculture, fire, society & public health, plants & wildlife, as well as relief, response & restrictions in Texas. It also provided a possibility to appraise drought impacts using hydro-meteorological indicators with the proposed framework in the United States, which could help drought risk management by giving additional information and improving the updating frequency of drought impacts. Our interpretation results using the Shapley additive explanation (SHAP) interpretability technique revealed that the rules guiding the predictions of XGBoost comply with domain expertise knowledge around the role that SPI indicators play around drought impacts.

Authors: Beichen Zhang (University of Nebraska-Lincoln); Fatima K Abu Salem (American University of Beirut); Michael Hayes (University of Nebraska-Lincoln); Tsegaye Tadesse (University of Nebraska-Lincoln)

Disaster prediction, management, and relief Interpretable ML
NeurIPS 2020 Estimating Forest Ground Vegetation Cover From Nadir Photographs Using Deep Convolutional Neural Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: Forest fires, such as those on the US west coast in September 2020, are an important factor in climate change. Wildfire modeling and mitigation require mapping vegetation ground cover over large plots of land. The current forestry practice is to send out human ground crews to collect photos of the forest floor at precisely determined locations, then manually calculate the percent cover of ground fuel types. In this work, we propose automating this process using a supervised learning-based deep convolutional neural network to perform image segmentation. Experimental results on a real dataset show this approach delivers very promising performance.

Authors: Pranoy Panda (Indian Institute of Technology, Hyderabad); Martin Barczyk (University of Alberta); Jen Beverly (University of Alberta)

Agriculture, forestry and other land use Classification, regression, and supervised learning
NeurIPS 2020 A Machine Learning Approach to Methane Emissions Mitigation in the Oil and Gas Industry (Papers Track) Overall Best Paper
Abstract and authors: (click to expand)

Abstract: Reducing methane emissions from the oil and gas sector is a key component of climate policy in the United States. Methane leaks across the supply chain are stochastic and intermittent, with a small number of sites (‘super-emitters’) responsible for a majority of emissions. Thus, cost-effective emissions reduction critically relies on effectively identifying the super-emitters from thousands of well-sites and millions of miles of pipelines. Conventional approaches such as walking surveys using optical gas imaging technology are slow and time-consuming. In addition, several variables contribute to the formation of leaks such as infrastructure age, production, weather conditions, and maintenance practices. Here, we develop a machine learning algorithm to predict high-emitting sites that can be prioritized for follow-up repair. Such prioritization can significantly reduce the cost of surveys and increase emissions reductions compared to conventional approaches. Our results show that the algorithm using logistic regression performs the best out of several algorithms. The model achieved a 70% accuracy rate with a 57% recall and a 66% balanced accuracy rate. Compared to the conventional approach, the machine learning model reduced the time to achieve a 50% emissions mitigation target by 42%. Correspondingly, the mitigation cost reduced from $85/t CO2e to $49/t CO2e.

Authors: Jiayang Wang (Harrisburg University); Selvaprabu Nadarajah (University of Illinois at Chicago); Jingfan Wang (Stanford University); Arvind Ravikumar (Harrisburg University)

Power and energy Classification, regression, and supervised learning
NeurIPS 2020 Monitoring the Impact of Wildfires on Tree Species with Deep Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: One of the impacts of climate change is the difficulty of tree regrowth after wildfires over areas that traditionally were covered by certain tree species. Here a deep learning model is customized to classify land covers from four-band aerial imagery before and after wildfires to study the prolonged consequences of wildfires on tree species. The tree species labels are generated from manually delineated maps for five land cover classes: Conifer, Hardwood, Shrub, ReforestedTree, and Barren land. With an accuracy of 92% on the test split, the model is applied to three wildfires on data from 2009 to 2018. The model accurately delineates areas damaged by wildfires, changes in tree species, and regrowth in burned areas. The result shows clear evidence of wildfires impacting the local ecosystem and the outlined approach can help monitor reforested areas, observe changes in forest composition, and track wildfire impact on tree species.

Authors: Wang Zhou (IBM Research); Levente Klein (IBM Research)

Agriculture, forestry and other land use Disaster prediction, management, and relief Computer vision and remote sensing
NeurIPS 2020 ForestNet: Classifying Drivers of Deforestation in Indonesia using Deep Learning on Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Characterizing the processes leading to deforestation is critical to the development and implementation of targeted forest conservation and management policies. In this work, we develop a deep learning model called ForestNet to classify the drivers of primary forest loss in Indonesia, a country with one of the highest deforestation rates in the world. Using satellite imagery, ForestNet identifies the direct drivers of deforestation in forest loss patches of any size. We curate a dataset of Landsat 8 satellite images of known forest loss events paired with driver annotations from expert interpreters. We use the dataset to train and validate the models and demonstrate that ForestNet substantially outperforms other standard driver classification approaches. In order to support future research on automated approaches to deforestation driver classification, the dataset curated in this study is publicly available at https://stanfordmlgroup.github.io/projects/forestnet .

Authors: Jeremy A Irvin (Stanford); Hao Sheng (Stanford University); Neel Ramachandran (Stanford University); Sonja Johnson-Yu (Stanford University); Sharon Zhou (Stanford University); Kyle Story (Descartes Labs); Rose Rustowicz (Descartes Labs); Cooper Elsworth (Descartes Labs); Kemen Austin (RTI International); Andrew Ng (Stanford University)

Agriculture, forestry and other land use Computer vision and remote sensing
NeurIPS 2020 Mangrove Ecosystem Detection using Mixed-Resolution Imagery with a Hybrid-Convolutional Neural Network (Papers Track)
Abstract and authors: (click to expand)

Abstract: Mangrove forests are rich in biodiversity and are a large contributor to carbon sequestration critical in the fight against climate change. However, they are currently under threat from anthropogenic activities, so monitoring their health, extent, and productivity is vital to our ability to protect these important ecosystems. Traditionally, lower resolution satellite imagery or high resolution unmanned air vehicle (UAV) imagery has been used independently to monitor mangrove extent, both offering helpful features to predict mangrove extent. To take advantage of both of these data sources, we propose the use of a hybrid neural network, which combines a Convolutional Neural Network (CNN) feature extractor with a Multilayer-Perceptron (MLP), to accurately detect mangrove areas using both medium resolution satellite and high resolution drone imagery. We present a comparison of our novel Hybrid CNN with algorithms previously applied to mangrove image classification on a data set we collected of dwarf mangroves from consumer UAVs in Baja California Sur, Mexico, and show a 95\% intersection over union (IOU) score for mangrove image classification, outperforming all our baselines.

Authors: Dillon Hicks (Engineers for Exploration); Ryan Kastner (University of California San Diego); Curt Schurgers (University of California San Diego); Astrid Hsu (University of California San Diego); Octavio Aburto (University of California San Diego)

Computer vision and remote sensing Carbon capture and sequestration Ecosystems and natural resources Agriculture, forestry and other land use Classification, regression, and supervised learning
NeurIPS 2020 Context-Aware Urban Energy Efficiency Optimization Using Hybrid Physical Models (Papers Track)
Abstract and authors: (click to expand)

Abstract: Buildings produce more U.S. greenhouse gas emissions through electricity generation than any other economic sector. To improve the energy efficiency of buildings, engineers often rely on physics-based building simulations to predict the impacts of retrofits in individual buildings. In dense urban areas, these models suffer from inaccuracy due to imprecise parameterization or external, unmodeled urban context factors such as inter-building effects and urban microclimates. In a case study of approximately 30 buildings in Sacramento, California, we demonstrate how our hybrid physics-driven deep learning framework can use these external factors advantageously to identify a more optimal energy efficiency retrofit installation strategy and achieve significant savings in both energy and cost.

Authors: Benjamin Choi (Stanford University); Alex Nutkiewicz (Stanford University); Rishee Jain (Stanford University)

Hybrid physical models Buildings and cities
NeurIPS 2020 Deep learning architectures for inference of AC-OPF solutions (Papers Track)
Abstract and authors: (click to expand)

Abstract: We present a systematic comparison between neural network (NN) architectures for inference of AC-OPF solutions. Using fully connected NNs as a baseline we demonstrate the efficacy of leveraging network topology in the models by constructing abstract representations of electrical grids in the graph domain, for both convolutional and graph NNs. The performance of the NN architectures is compared for regression (predicting optimal generator set-points) and classification (predicting the active set of constraints) settings. Computational gains for obtaining optimal solutions are also presented.

Authors: Thomas Falconer (University College London); Letif Mones (Invenia Labs)

Classification, regression, and supervised learning Power and energy
NeurIPS 2020 Predicting the Solar Potential of Rooftops using Image Segmentation and Structured Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Estimating the amount of electricity that can be produced by rooftop photovoltaic systems is a time-consuming process that requires on-site measurements, a difficult task to achieve on a large scale. In this paper, we present an approach to estimate the solar potential of rooftops based on their location and architectural characteristics, as well as the amount of solar radiation they receive annually. Our technique uses computer vision to achieve semantic segmentation of roof sections and roof objects on the one hand, and a machine learning model based on structured building features to predict roof pitch on the other hand. We then compute the azimuth and maximum number of solar panels that can be installed on a rooftop with geometric approaches. Finally, we compute precise shading masks and combine them with solar irradiation data that enables us to estimate the yearly solar potential of a rooftop.

Authors: Daniel de Barros Soares (nam.R); François ANDRIEUX (nam.R); Bastien HELL (nam.R); Julien LENHARDT (nam.R; ENSTA); JORDI BADOSA (Ecole Polytechnique); Sylvain GAVOILLE (nam.R); Stéphane GAIFFAS (nam.R; LPSM (Université de Paris)); Emmanuel BACRY (nam.R; CEREMADE (Université Paris Dauphine, PSL))

Buildings and cities Power and energy Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2020 Revealing the Oil Majors' Adaptive Capacity to the Energy Transition with Deep Multi-Agent Reinforcement Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: A low-carbon energy transition is transpiring to combat climate change, posing an existential threat to oil and gas companies, particularly the Majors. Though Majors yield the resources and expertise to adapt to low-carbon business models, meaningful climate-aligned strategies have yet to be enacted. A 2-degrees pathways (2DP) wargame was developed to assess climate-compatible pathways for the oil Majors. Recent advances in deep multi-agent reinforcement learning (MARL) have achieved superhuman-level performance in solving high-dimensional continuous control problems. Modeling within a Markovian framework, we present the novel 2DP-MARL model which applies deep MARL methods to solve the 2DP wargame across a multitude of transition scenarios. Designed to best mimic Majors in real- life competition, the model reveals all Majors quickly adapt to low-carbon business models to remain robust amidst energy transition uncertainty. The purpose of this work is provide tangible metrics to support the call for oil Majors to diversify into low-carbon business models and, thus, accelerate the energy transition.

Authors: Dylan Radovic (Imperial College London); Lucas Kruitwagen (University of Oxford); Christian Schroeder de Witt (University of Oxford)

Industry Climate finance Reinforcement learning and control Uncertainty quantification and robustness
NeurIPS 2020 Quantifying the presence of air pollutants over a road network in high spatio-temporal resolution (Papers Track)
Abstract and authors: (click to expand)

Abstract: Monitoring air pollution plays a key role when trying to reduce its impact on the environment and on human health. Traditionally, two main sources of information about the quantity of pollutants over a city are used: monitoring stations at ground-level (when available), and satellites' remote sensing. In addition to these two, other methods have been developed in the last years that aim at understanding how traffic emissions behave in space and time at a finer scale, taking into account the human mobility patterns. We present a simple and versatile framework for estimating the quantity of four air pollutants (CO2, NOx, PM, VOC) emitted by private vehicles moving on a road network, starting from raw GPS traces and information about vehicles' fuel type, and use this framework for analyses on how such pollutants distribute over the road networks of different cities.

Authors: Matteo Bohm (Sapienza University of Rome); Mirco Nanni (ISTI-CNR Pisa, Italy); Luca Pappalardo (ISTI)

Transportation Data mining
NeurIPS 2020 Annual and in-season mapping of cropland at field scale with sparse labels (Papers Track)
Abstract and authors: (click to expand)

Abstract: Spatial information about where crops are being grown, known as cropland maps, are critical inputs for analyses and decision-making related to food security and climate change. Despite a widespread need for readily-updated annual and in-season cropland maps at the management (field) scale, these maps are unavailable for most regions at risk of food insecurity. This is largely due to lack of in-situ labels for training and validating machine learning classifiers. Previously, we developed a method for binary classification of cropland that learns from sparse local labels and abundant global labels using a multi-headed LSTM and time-series multispectral satellite inputs over one year. In this work, we present a new method that uses an autoregressive LSTM to classify cropland during the growing season (i.e., partially-observed time series). We used these methods to produce publicly-available 10m-resolution cropland maps in Kenya for the 2019-2020 and 2020-2021 growing seasons. These are the highest-resolution and most recent cropland maps publicly available for Kenya. These methods and associated maps are critical for scientific studies and decision-making at the intersection of food security and climate change.

Authors: Gabriel Tseng (NASA Harvest); Hannah R Kerner (University of Maryland); Catherine L Nakalembe (University of Maryland); Inbal Becker-Reshef (University of Maryland)

Agriculture, forestry and other land use Computer vision and remote sensing
NeurIPS 2020 NightVision: Generating Nighttime Satellite Imagery from Infra-Red Observations (Papers Track)
Abstract and authors: (click to expand)

Abstract: The recent explosion in applications of machine learning to satellite imagery often rely on visible images and therefore suffer from a lack of data during the night. The gap can be filled by employing available infra-red observations to generate visible images. This work presents how Deep Learning can be applied successfully to create those images by using U-Net based architectures. The proposed methods show promising results, achieving a structural similarity index (SSIM) up to 86\% on an independent test set and providing visually convincing output images, generated from infra-red observations.

Authors: Paula Harder (Fraunhofer ITWM); William Jones (University of Oxford); Redouane Lguensat (LSCE-IPSL); Shahine Bouabid (University of Oxford); James Fulton (University of Edinburgh); Dánnell Quesada-Chacón (Technische Universität Dresden); Aris Marcolongo (University of Bern); Sofija Stefanovic (University of Oxford); Yuhan Rao (North Carolina Institute for Climate Studies); Peter Manshausen (University of Oxford); Duncan Watson-Parris (University of Oxford)

Computer vision and remote sensing Climate and Earth science Generative modeling
NeurIPS 2020 Analyzing Sustainability Reports Using Natural Language Processing (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change is a far-reaching, global phenomenon that will impact many aspects of our society, including the global stock market. In recent years, companies have increasingly been aiming to both mitigate their environmental impact and adapt their practices the changing climate context. This is reported via increasingly exhaustive reports, which cover many types of sustainability measures, often under the umbrella of Environmental, Social, and Governance (ESG) disclosures. However, given this abundance of data, sustainability analysts are obliged to comb through hundreds of pages of reports in order to find relevant information. We have leveraged recent progress in Natural Language Processing (NLP) to create a custom model, ClimateQA, which allows the analysis of financial reports in order to identify climate-relevant sections using a question answering approach. We present this tool and the methodology that we used to develop it in the present article.

Authors: Sasha Luccioni (Mila); Emi Baylor (McGill); Nicolas Duchene (Universite de Montreal)

Climate finance Natural language processing
NeurIPS 2020 Automated Identification of Oil Field Features using CNNs (Papers Track)
Abstract and authors: (click to expand)

Abstract: Oil and gas production sites have been identified as a major source of anthropogenic methane emissions. Emissions studies utilize counts of equipment to estimate emissions from production facilities. However these counts are poorly documented, including both information about well pad locations and major equipment on each well pad. While these data can be found by manually reviewing satellite imagery, it is prohibitively difficult and time consuming. This work, part of a larger study of methane emission studies in Colorado, US, adapted a machine learning (ML) algorithm to detect well pads and associated equipment. Our initial model showed an average well pad detection accuracy of 95% on the Denver-Julesburg (DJ) basin in northeastern Colorado. Our example demonstrates the potential for this type of automated detection from satellite imagery, leading to more accurate and complete models of production emissions.

Authors: SONU DILEEP (Colorado State University); Daniel Zimmerle (Colorado State University); Ross Beveridge (CSU); Timothy Vaughn (Colorado State University)

Climate and Earth science Computer vision and remote sensing
NeurIPS 2020 Using attention to model long-term dependencies in occupancy behavior (Papers Track)
Abstract and authors: (click to expand)

Abstract: Over the past years, more and more models have been published that aim to capture relationships in human residential behavior. Most of these models are different Markov variants or regression models that have a strong assumption bias and are therefore unable to capture complex long-term dependencies and the diversity in occupant behavior. This work shows that attention based models are able to capture complex long-term dependencies in occupancy behavior and at the same time adequately depict the diversity in behavior across the entire population and different socio-demographic groups. By combining an autoregressive generative model with an imputation model, the advantages of two data sets are combined and new data are generated which are beneficial for multiple use cases (e.g. generation of consistent household energy demand profiles). The two step approach generates synthetic activity schedules that have similar statistical properties as the empirical collected schedules and do not contain direct information about single individuals. Therefore, the presented approach forms the basis to make data on occupant behavior freely available, so that further investigations based on the synthetic data can be carried out without a large data application effort. In future work it is planned to take interpersonal dependencies into account in order to be able to generate entire household behavior profiles.

Authors: Max Kleinebrahm (Karlsruhe Institut für Technologie); Jacopo Torriti (University Reading); Russell McKenna (University of Aberdeen); Armin Ardone (Karlsruhe Institut für Technologie); Wolf Fichtner (Karlsruhe Institute of Technology)

Behavioral and social science Buildings and cities Power and energy Transportation Natural language processing Time-series analysis
NeurIPS 2020 Street to Cloud: Improving Flood Maps With Crowdsourcing and Semantic Segmentation (Papers Track)
Abstract and authors: (click to expand)

Abstract: To address the mounting destruction caused by floods in climate-vulnerable regions, we propose Street to Cloud, a machine learning pipeline for incorporating crowdsourced ground truth data into the segmentation of satellite imagery of floods. We propose this approach as a solution to the labor-intensive task of generating high-quality, hand-labeled training data, and demonstrate successes and failures of different plausible crowdsourcing approaches in our model. Street to Cloud leverages community reporting and machine learning to generate novel, near-real time insights into the extent of floods to be used for emergency response.

Authors: Veda Sunkara (Cloud to Street); Matthew Purri (Rutgers University); Bertrand Le Saux (European Space Agency (ESA)); Jennifer Adams (European Space Agency (ESA))

Disaster prediction, management, and relief Computer vision and remote sensing
NeurIPS 2020 Accurate river level predictions using a Wavenet-like model (Papers Track)
Abstract and authors: (click to expand)

Abstract: The effects of climate change on river levels are noticeable through a higher occurrence of floods with disastrous social and economic impacts. As such, river level forecasting is essential in flood mitigation, infrastructure management and secure shipping. Historical records of river levels and influencing factors such as rainfall or soil conditions are used for predicting future river levels. The current state-of-the-art time-series prediction model is the LSTM network, a recurrent neural network. In this work we study the efficiency of convolutional models, and specifically the WaveNet model in forecasting one-day ahead river levels. We show that the additional benefit of the WaveNet model is the computational ease with which other input features can be included in the predictions of river stage and river flow. The conditional WaveNet models outperformed conditional LSTM models for river level prediction by capturing short-term, non-linear dependencies between input data. Furthermore, the Wavenet model offers a faster computation time, stable results and more possibilities for fine-tuning.

Authors: Shannon Doyle (UvA); Anastasia Borovykh (Imperial College London)

Disaster prediction, management, and relief Other Classification, regression, and supervised learning
NeurIPS 2020 Movement Tracks for the Automatic Detection of Fish Behavior in Videos (Papers Track)
Abstract and authors: (click to expand)

Abstract: Global warming is predicted to profoundly impact ocean ecosystems. Fish behavior is an important indicator of changes in such marine environments. Thus, the automatic identification of key fish behavior in videos represents a much needed tool for marine researchers, enabling them to study climate change-related phenomena. We offer a dataset of sablefish (Anoplopoma fimbria) startle behaviors in underwater videos, and investigate the use of deep learning (DL) methods for behavior detection on it. Our proposed detection system identifies fish instances using DL-based frameworks, determines trajectory tracks, derives novel behavior-specific features, and employs Long Short-Term Memory (LSTM) networks to identify startle behavior in sablefish. Its performance is studied by comparing it with a state-of-the-art DL-based video event detector.

Authors: Declan GD McIntosh (University Of Victoria); Tunai Porto Marques (University of Victoria); Alexandra Branzan Albu (University of Victoria); Rodney Rountree (University of Victoria); Fabio De Leo Cabrera (Ocean Networks Canada)

Computer vision and remote sensing Ecosystems and natural resources Other Classification, regression, and supervised learning Time-series analysis
NeurIPS 2020 Counting Cows: Tracking Illegal Cattle Ranching From High-Resolution Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Cattle farming is responsible for 8.8\% of greenhouse gas emissions worldwide. In addition to the methane emitted due to their digestive process, the growing need for grazing areas is an important driver of deforestation. While some regulations are in place for preserving the Amazon against deforestation, these are being flouted in various ways. Hence the need to scale and automate the monitoring of cattle ranching activities. Through a partnership with \textit{Anonymous under review}, we explore the feasibility of tracking and counting cattle at the continental scale from satellite imagery. With a license from Maxar Technologies, we obtained satellite imagery of the Amazon at 40cm resolution, and compiled a dataset of 903 images containing a total of 28498 cattle. Our experiments show promising results and highlight important directions for the next steps on both counting algorithms and the data collection processes for solving such challenges.

Authors: Issam Hadj Laradji (Element AI); Pau Rodriguez (Element AI); Alfredo Kalaitzis (University of Oxford); David Vazquez (Element AI); Ross Young (Element AI); Ed Davey (Global Witness); Alexandre Lacoste (Element AI)

Computer vision and remote sensing Agriculture, forestry and other land use Climate and Earth science Ecosystems and natural resources
NeurIPS 2020 RainBench: Enabling Data-Driven Precipitation Forecasting on a Global Scale (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change is expected to aggravate extreme precipitation events, directly impacting the livelihood of millions. Without a global precipitation forecasting system in place, many regions -- especially those constrained in resources to collect expensive groundstation data -- are left behind. To mitigate such unequal reach of climate change, a solution is to alleviate the reliance on numerical models (and by extension groundstation data) by enabling machine-learning-based global forecasts from satellite imagery. Though prior works exist in regional precipitation nowcasting, there lacks work in global, medium-term precipitation forecasting. Importantly, a common, accessible baseline for meaningful comparison is absent. In this work, we present RainBench, a multi-modal benchmark dataset dedicated to advancing global precipitation forecasting. We establish baseline tasks and release PyRain, a data-handling pipeline to enable efficient processing of decades-worth of data by any modeling framework. Whilst our work serves as a basis for a new chapter on global precipitation forecast from satellite imagery, the greater promise lies in the community joining forces to use our released datasets and tools in developing machine learning approaches to tackle this important challenge.

Authors: Catherine Tong (University of Oxford); Christian A Schroeder de Witt (University of Oxford); Valentina Zantedeschi (GE Global Research); Daniele De Martini (University of Oxford); Alfredo Kalaitzis (University of Oxford); Matthew Chantry (University of Oxford); Duncan Watson-Parris (University of Oxford); Piotr Bilinski (University of Warsaw / University of Oxford)

Climate and Earth science Classification, regression, and supervised learning
NeurIPS 2020 Machine learning for advanced solar cell production: adversarial denoising, sub-pixel alignment and the digital twin (Papers Track)
Abstract and authors: (click to expand)

Abstract: Photovoltaic is a main pillar to achieve the transition towards a renewable energy supply. In order to continue the tremendous cost decrease of the last decades, novel cell techologies and production processes are implemented into mass production to improve cell efficiency. Raising their full potential requires novel techniques of quality assurance and data analysis. We present three use-cases along the value chain where machine learning techniques are investigated for quality inspection and process optimization: Adversarial learning to denoise wafer images, alignment of surface structuring processes via sub-pixel coordinate regression, and the development of a digital twin for wafers and solar cells for material and process analysis.

Authors: Matthias Demant (Fraunhofer ISE); Leslie Kurumundayil (Fraunhofer ISE); Philipp Kunze (Fraunhofer ISE); Aditya Kovvali (Fraunhofer ISE); Alexandra Woernhoer (Fraunhofer ISE); Stefan Rein (Fraunhofer ISE)

Power and energy Industry Classification, regression, and supervised learning Computer vision and remote sensing Unsupervised and semi-supervised learning
NeurIPS 2020 Climate Change Driven Crop Yield Failures (Papers Track)
Abstract and authors: (click to expand)

Abstract: The effect of extreme temperatures, precipitation and variations in other meteorological factors affect crop yields, and hence climate change jeopardizes the entire food supply chain and dependent economic activities. We utilize Deep Neural Networks and Gaussian Processes for understanding crop yields as functions of climatological variables, and use change detection techniques to identify climatological thresholds where yield drops significantly.

Authors: Somya Sharma (U. Minnesota); Deepak Ray (University of Minnesota); Snigdhansu Chatterjee (University of Minnesota)

Agriculture, forestry and other land use Spatial deep learning
NeurIPS 2020 Physics-constrained Deep Recurrent Neural Models of Building Thermal Dynamics (Papers Track)
Abstract and authors: (click to expand)

Abstract: We develop physics-constrained and control-oriented predictive deep learning models for the thermal dynamics of a real-world commercial office building. The proposed method is based on the systematic encoding of physics-based prior knowledge into a structured recurrent neural architecture. Specifically, our model mimics the structure of the building thermal dynamics model and leverages penalty methods to model inequality constraints. Additionally, we use constrained matrix parameterization based on the Perron-Frobenius theorem to bound the eigenvalues of the learned network weights. We interpret the stable eigenvalues as dissipativeness of the learned building thermal model. We demonstrate the effectiveness of the proposed approach on a dataset obtained from an office building with 20 thermal zones.

Authors: Jan Drgona (Pacific Northwest National Laboratory); Aaron R Tuor (Pacific Northwest National Laboratory); Vikas Chandan (PNNL); Draguna Vrabie (PNNL)

Hybrid physical models Buildings and cities
NeurIPS 2020 Narratives and Needs: Analyzing Experiences of Cyclone Amphan Using Twitter Discourse (Papers Track)
Abstract and authors: (click to expand)

Abstract: People often turn to social media to comment upon and share information about major global events. Accordingly, social media is receiving increasing attention as a rich data source for understanding people's social, political and economic experiences of extreme weather events. In this paper, we contribute two novel methodologies that leverage Twitter discourse to characterize narratives and identify unmet needs in response to Cyclone Amphan, which affected 18 million people in May 2020.

Authors: Ancil S Crayton (Booz Allen Hamilton); Joao Fonseca (NOVA Information Management School); Kanav Mehra (Independent Researcher); Jared Ross (Booz Allen Hamilton); Marcelo Sandoval-Castañeda (New York University Abu Dhabi); Michelle Ng (International Water Management Institute); Rachel von Gnechten (International Water Management Institute)

Disaster prediction, management, and relief Natural language processing Other Unsupervised and semi-supervised learning
NeurIPS 2020 FlowDB: A new large scale river flow, flash flood, and precipitation dataset (Papers Track)
Abstract and authors: (click to expand)

Abstract: Flooding results in 8 billion dollars of damage annually in the US and causes the most deaths of any weather related event. Due to climate change scientists expect more heavy precipitation events in the future. However, no current datasets exist that contain both hourly precipitation and river flow data. We introduce a novel hourly river flow and precipitation dataset and a second subset of flash flood events with damage estimates and injury counts. Using these datasets we create two challenges (1) general stream flow forecasting and (2) flash flood damage estimation. We also create a public benchmark and an Python package to enable easy adding of new models . Additionally, in the future we aim to augment our dataset with snow pack data and soil index moisture data to improve predictions

Authors: Isaac Godfried (CoronaWhy)

Time-series analysis Climate and Earth science Data mining
NeurIPS 2020 Can Federated Learning Save The Planet ? (Papers Track)
Abstract and authors: (click to expand)

Abstract: Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers. In response, alternatives to centralized training such as Federated Learning (FL) have emerged. Perhaps unexpectedly, FL in particular is starting to be deployed at a global scale by companies that must adhere to new legal demands and policies originating from governments and the civil society for privacy protection. \textit{However, the potential environmental impact related to FL remains unclear and unexplored. This paper offers the first-ever systematic study of the carbon footprint of FL.} First, we propose a rigorous model to quantify the carbon footprint, hence facilitating the investigation of the relationship between FL design and carbon emissions. Then, we compare the carbon footprint of FL to traditional centralized learning. Our findings show FL, despite being slower to converge, can be a greener technology than data center GPUs. Finally, we highlight and connect the reported results to the future challenges and trends in FL to reduce its environmental impact, including algorithms efficiency, hardware capabilities, and stronger industry transparency.

Authors: Xinchi Qiu (University of Cambridge); Titouan Parcollet (University of Oxford); Daniel J Beutel (Adap GmbH / University of Cambridge); Taner Topal (Adap GmbH); Akhil Mathur (Nokia Bell Labs); Nicholas Lane (University of Cambridge and Samsung AI)

Power and energy Federated Learning
NeurIPS 2020 FireSRnet: Geoscience-driven super-resolution of future fire risk from climate change (Papers Track)
Abstract and authors: (click to expand)

Abstract: With fires becoming increasingly frequent and severe across the globe in recent years, understanding climate change’s role in fire behavior is critical for quantifying current and future fire risk. However, global climate models typically simulate fire behavior at spatial scales too coarse for local risk assessments. Therefore, we propose a novel approach towards super-resolution (SR) enhancement of fire risk exposure maps that incorporates not only 2000 to 2020 monthly satellite observations of active fires but also local information on land cover and temperature. Inspired by SR architectures, we propose an efficient deep learning model trained for SR on fire risk exposure maps. We evaluate this model on resolution enhancement and find it outperforms standard image interpolation techniques at both 4x and 8x enhancement while having comparable performance at 2x enhancement. We then demonstrate the generalizability of this SR model over northern California and New South Wales, Australia. We conclude with a discussion and application of our proposed model to climate model simulations of fire risk in 2040 and 2100, illustrating the potential for SR enhancement of fire risk maps from the latest state-of-the-art climate models.

Authors: Tristan C Ballard (Sust Global, Stanford University); Gopal Erinjippurath (Sust Global)

Computer vision and remote sensing Climate and Earth science Societal adaptation
NeurIPS 2020 An Enriched Automated PV Registry: Combining Image Recognition and 3D Building Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: While photovoltaic (PV) systems are installed at an unprecedented rate, reliable information on an installation level remains scarce. As a result, automatically created PV registries are a timely contribution to optimize grid planning and operations. This paper demonstrates how aerial imagery and three-dimensional building data can be combined to create an address-level PV registry, specifying area, tilt, and orientation angles. We demonstrate the benefits of this approach for PV capacity estimation. In addition, this work presents, for the first time, a comparison between automated and officially-created PV registries. Our results indicate that our enriched automated registry proves to be useful to validate, update, and complement official registries.

Authors: Benjamin Rausch (Stanford); Kevin Mayer (Stanford); Marie-Louise Arlt (Stanford); Gunther Gust (University of Freiburg); Philipp Staudt (KIT); Christof Weinhardt (Karlsruhe Institute of Technology); Dirk Neumann (Universität Freiburg); Ram Rajagopal (Stanford University)

Power and energy Buildings and cities Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2020 Satellite imagery analysis for Land Use, Land Use Change and Forestry: A pilot study in Kigali, Rwanda (Papers Track)
Abstract and authors: (click to expand)

Abstract: Estimating greenhouse gases from the Agriculture, Forestry and Other land Use (AFOLU) sector is very challenging partly due to the unavailability of data (particularly for land use and land use change sectors) and inadequate experts to analyze this data in case it is available. We used Collect Earth together with Machine Learning techniques to be able to predict and classify all the land use types based on some few points collected using Collect Earth. We investigated the adoption of this tool and technology in Rwanda to help its national and sub-national inventories. The use of Collect Earth and the Machine Learning (ML) implementation will help Rwanda monitor and predict its Land Use, Land Use Change, and Forestry in a cost-effective manner whiles enhancing the quality of reports submitted to national and international bodies whiles introducing a new approach. Among the classification algorithms we tested, we had an overall classification accuracy of 97% using the Classification and Regression Trees (CART) algorithm to to predict the six land Use classes across the country.

Authors: Bright Aboh (African Institute for Mathematical Sciences); Alphonse Mutabazi (UN Environment Program)

Agriculture, forestry and other land use Classification, regression, and supervised learning
NeurIPS 2020 EarthNet2021: A novel large-scale dataset and challenge for forecasting localized climate impacts (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change is global, yet its concrete impacts can strongly vary between different locations in the same region. Seasonal weather forecasts currently operate at the mesoscale (> 1 km). For more targeted mitigation and adaptation, modelling impacts to < 100 m is needed. Yet, the relationship between driving variables and Earth’s surface at such local scales remains unresolved by current physical models. Large Earth observation datasets now enable us to create machine learning models capable of translating coarse weather information into high-resolution Earth surface forecasts encompassing localized climate impacts. Here, we define high-resolution Earth surface forecasting as video prediction of satellite imagery conditional on mesoscale weather forecasts. Video prediction has been tackled with deep learning models. Developing such models requires analysis-ready datasets. We introduce EarthNet2021, a new, curated dataset containing target spatio-temporal Sentinel 2 satellite imagery at 20 m resolution, matched with high-resolution topography and mesoscale (1.28 km) weather variables. With over 32000 samples it is suitable for training deep neural networks. Comparing multiple Earth surface forecasts is not trivial. Hence, we define the EarthNetScore, a novel ranking criterion for models forecasting Earth surface reflectance. For model intercomparison we frame EarthNet2021 as a challenge with four tracks based on different test sets. These allow evaluation of model validity and robustness as well as model applicability to extreme events and the complete annual vegetation cycle. In addition to forecasting directly observable weather impacts through satellite-derived vegetation indices, capable Earth surface models will enable downstream applications such as crop yield prediction, forest health assessments, coastline management, or biodiversity monitoring. Find data, code, and how to participate at www.earthnet.tech .

Authors: Christian Requena-Mesa (Computer Vision Group, Friedrich Schiller University Jena; DLR Institute of Data Science, Jena; Max Planck Institute for Biogeochemistry, Jena); Vitus Benson (Max-Planck-Institute for Biogeochemistry); Jakob Runge (Institute of Data Science, German Aerospace Center (DLR)); Joachim Denzler (Computer Vision Group, Friedrich Schiller University Jena, Germany); Markus Reichstein (Max Planck Institute for Biogeochemistry, Jena; Michael Stifel Center Jena for Data-Driven and Simulation Science, Jena)

Climate and Earth science Agriculture, forestry and other land use Disaster prediction, management, and relief Ecosystems and natural resources Computer vision and remote sensing Data mining Generative modeling Hybrid physical models
NeurIPS 2020 DeepWaste: Applying Deep Learning to Waste Classification for a Sustainable Planet (Papers Track)
Abstract and authors: (click to expand)

Abstract: Accurate waste disposal, at the point of disposal, is crucial to fighting climate change. When materials that could be recycled or composted get diverted into landfills, they cause the emission of potent greenhouse gases such as methane. Current attempts to reduce erroneous waste disposal are expensive, inaccurate, and confusing. In this work, we propose DeepWaste, an easy-to-use mobile app, that utilizes highly optimized deep learning techniques to provide users instantaneous waste classification into trash, recycling, and compost. We experiment with several convolution neural network architectures to detect and classify waste items. Our best model, a deep learning residual neural network with 50 layers, achieves an average precision of 0.881 on the test set. We demonstrate the performance and efficiency of our app on a set of real-world images.

Authors: Yash Narayan (The Nueva School)

Other Classification, regression, and supervised learning
NeurIPS 2020 Machine Learning Climate Model Dynamics: Offline versus Online Performance (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate models are complicated software systems that approximate atmospheric and oceanic fluid mechanics at a coarse spatial resolution. Typical climate forecasts only explicitly resolve processes larger than 100 km and approximate any process occurring below this scale (e.g. thunderstorms) using so-called parametrizations. Machine learning could improve upon the accuracy of some traditional physical parametrizations by learning from so-called global cloud-resolving models. We compare the performance of two machine learning models, random forests (RF) and neural networks (NNs), at parametrizing the aggregate effect of moist physics in a 3 km resolution global simulation with an atmospheric model. The NN outperforms the RF when evaluated offline on a testing dataset. However, when the ML models are coupled to an atmospheric model run at 200 km resolution, the NN-assisted simulation crashes with 7 days, while the RF-assisted simulations remain stable. Both runs produce more accurate weather forecasts than a baseline configuration, but globally averaged climate variables drift over longer timescales.

Authors: Noah D Brenowitz (Vulcan Inc.); Brian Henn (Vulcan, Inc.); Spencer Clark (Vulcan, Inc.); Anna Kwa (Vulcan, Inc.); Jeremy McGibbon (Vulcan, Inc.); W. Andre Perkins (Vulcan, Inc.); Oliver Watt-Meyer (Vulcan, Inc.); Christopher S. Bretherton (Vulcan, Inc.)

Climate and Earth science Hybrid physical models
NeurIPS 2020 OGNet: Towards a Global Oil and Gas Infrastructure Database using Deep Learning on Remotely Sensed Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: At least a quarter of the warming that the Earth is experiencing today is due to anthropogenic methane emissions. There are multiple satellites in orbit and planned for launch in the next few years which can detect and quantify these emissions; however, to attribute methane emissions to their sources on the ground, a comprehensive database of the locations and characteristics of emission sources worldwide is essential. In this work, we develop deep learning algorithms that leverage freely available high-resolution aerial imagery to automatically detect oil and gas infrastructure, one of the largest contributors to global methane emissions. We use the best algorithm, which we call OGNet, together with expert review to identify the locations of oil refineries and petroleum terminals in the U.S. We show that OGNet detects many facilities which are not present in four standard public datasets of oil and gas infrastructure. All detected facilities are associated with characteristics critical to quantifying and attributing methane emissions, including the types of infrastructure and number of storage tanks. The data curated and produced in this study is freely available at https://link/provided/in/camera/ready/version.

Authors: Hao Sheng (Stanford University); Jeremy A Irvin (Stanford); Sasankh Munukutla (Stanford University); Shawn Zhang (Stanford University); Christopher Cross (Stanford University); Zutao Yang (Stanford University); Kyle Story (Descartes Labs); Rose Rustowicz (Descartes Labs); Cooper Elsworth (Descartes Labs); Mark Omara (Environmental Defense Fund); Ritesh Gautam (Environmental Defense Fund); Rob Jackson (Stanford University); Andrew Ng (Stanford University)

Power and energy Computer vision and remote sensing
NeurIPS 2020 VConstruct: Filling Gaps in Chl-a Data Using a Variational Autoencoder (Papers Track)
Abstract and authors: (click to expand)

Abstract: Remote sensing of Chlorophyll-a is vital in monitoring climate change. Chlorphylla measurements give us an idea of the algae concentrations in the ocean, which lets us monitor ocean health. However, a common problem is that the satellites used to gather the data are commonly obstructed by clouds and other artifacts. This means that time series data from satellites can suffer from spatial data loss. There are a number of algorithms that are able to reconstruct the missing parts of these images to varying degrees of accuracy, with Data INterpolating Empirical Orthogonal Functions (DINEOF) being the current standard. However, DINEOF is slow, suffers from accuracy loss in temporally homogenous waters, reliant on temporal data, and only able to generate a single potential reconstruction. We propose a machine learning approach to reconstruction of Chlorophyll-a data using a Variational Autoencoder (VAE). Our accuracy results to date are competitive with but slightly less accurate than DINEOF. We show the benefits of our method including vastly decreased computation time and ability to generate multiple potential reconstructions. Lastly, we outline our planned improvements and future work.

Authors: Matthew Ehrler (University of Victoria); Neil Ernst (University of Victoria)

Computer vision and remote sensing Climate and Earth science Ecosystems and natural resources Generative modeling
NeurIPS 2020 A Comparison of Data-Driven Models for Predicting Stream Water Temperature (Papers Track)
Abstract and authors: (click to expand)

Abstract: Changes to the Earth's climate are expected to negatively impact water resources in the future. It is important to have accurate modelling of river flow and water quality to make optimal decisions for water management. Machine learning and deep learning models have become promising methods for making such hydrological predictions. Using these models, however, requires careful consideration both of data constraints and of model complexity for a given problem. Here, we use machine learning (ML) models to predict monthly stream water temperature records at three monitoring locations in the Northwestern United States with long-term datasets, using meteorological data as predictors. We fit three ML models: a Multiple Linear Regression, a Random Forest Regression, and a Support Vector Regression, and compare them against two baseline models: a persistence model and historical model. We show that all three ML models are reasonably able to predict mean monthly stream temperatures with root mean-squared errors (RMSE) ranging from 0.63-0.91 degrees Celsius. Of the three ML models, Support Vector Regression performs the best with an error of 0.63-0.75 degrees Celsius. However, all models perform poorly on extreme values of water temperature. We identify the need for machine learning approaches for predicting extreme values for variables such as water temperature, since it has significant implications for stream ecosystems and biota.

Authors: Helen Weierbach (Lawrence Berkeley); Aranildo Lima (Aquatic Informatics); Danielle Christianson (Lawrence Berkeley National Lab); Boris Faybishenko (Lawrence Berkeley National Lab); Val Hendrix (Lawrence Berkeley National Lab); Charuleka Varadharajan (Lawrence Berkeley National Lab)

Ecosystems and natural resources Climate and Earth science Classification, regression, and supervised learning Time-series analysis
NeurIPS 2020 Automated Salmonid Counting in Sonar Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: The prosperity of salmonids is crucial for several ecological and economic functions. Accurately counting spawning salmonids during their seasonal migration is essential in monitoring threatened populations, assessing the efficacy of recovery strategies, guiding fishing season regulations, and supporting the management of commercial and recreational fisheries. While several different methods exist for counting river fish, they all rely heavily on human involvement, introducing a hefty financial and time burden. In this paper we present an automated fish counting method that utilizes data captured from ARIS sonar cameras to detect and track salmonids migrating in rivers. Our results show that our fully automated system has a 19.3% per-clip error when compared to human counting performance. There is room to improve, but our system can already decrease the amount of time field biologists and fishery managers need to spend manually watching ARIS clips.

Authors: Peter Kulits (Caltech); Angelina Pan (Caltech); Sara M Beery (Caltech); Erik Young (Trout Unlimited); Pietro Perona (California Institute of Technology); Grant Van Horn (Cornell University)

Ecosystems and natural resources Agriculture, forestry and other land use Climate and Earth science Industry Computer vision and remote sensing Time-series analysis
NeurIPS 2020 Short-term PV output prediction using convolutional neural network: learning from an imbalanced sky images dataset via sampling and data augmentation (Papers Track)
Abstract and authors: (click to expand)

Abstract: Integrating photovoltaics (PV) into electricity grids is one of the major pathways towards a low-carbon energy system. However, the biggest challenge is the strong fluctuation in PV power generation. In recent years, sky-image-based PV output prediction using deep neural networks has emerged as a promising approach to alleviate the uncertainty. Despite the research surge in exploring different model architectures, there is currently no study addressing the issue of learning from an imbalanced sky images dataset, the outcome of which would be highly beneficial for improving the reliability of existing and new solar forecasting models. In this study, we train convolutional neural network (CNN) models from an imbalanced sky images dataset for two disparate PV output prediction tasks, i.e., nowcast and forecast. We empirically examine the efficacy of using different sampling and data augmentation approaches to create synthesized dataset for model development. We further apply a three-stage selection approach to determine the optimal sampling approach, data augmentation technique and oversampling rate.

Authors: Yuhao Nie (Stanford University); Ahmed S Zamzam (The National Renewable Energy Laboratory); Adam Brandt (Stanford University)

Computer vision and remote sensing Climate and Earth science Classification, regression, and supervised learning
NeurIPS 2020 OfficeLearn: An OpenAI Gym Environment for Building Level Energy Demand Response (Papers Track)
Abstract and authors: (click to expand)

Abstract: Energy Demand Response (DR) will play a crucial role in balancing renewable energy generation with demand as grids decarbonize. There is growing interest in developing Reinforcement Learning (RL) techniques to optimize DR pricing, as pricing set by electric utilities often cannot take behavioral irrationality into account. However, so far, attempts to standardize RL efforts in this area do not exist. In this paper, we present a first of the kind OpenAI gym environment for testing DR with occupant level building dynamics. We demonstrate the variety of parameters built into our office environment allowing the researcher to customize a building to meet their specifications of interest. We hope that this work enables future work in DR in buildings.

Authors: Lucas Spangher (U.C. Berkeley); Akash Gokul (University of California at Berkeley); Utkarsha Agwan (U.C. Berkeley); Joseph Palakapilly (UC Berkeley); Manan Khattar (University of California at Berkeley); Akaash Tawade (University of California at Berkeley); Costas J. Spanos (University of California at Berkeley)

Buildings and cities Power and energy Reinforcement learning and control Time-series analysis
NeurIPS 2020 Machine Learning for Glacier Monitoring in the Hindu Kush Himalaya (Papers Track)
Abstract and authors: (click to expand)

Abstract: Glacier mapping is key to ecological monitoring in the Hindu Kush Himalaya region. Climate change poses a risk to individuals whose livelihoods depend on the health of glacier ecosystems. In this work, we present a machine learning based approach to support ecological monitoring, with a focus on glaciers. Our approach is based on semi-automated mapping from satellite images. We utilize readily available remote sensing data to create a model to identify and outline both clean ice and debris-covered glaciers from satellite imagery. We also release data and develop a web tool that allows experts to visualize and correct model predictions, with the ultimate aim of accelerating the glacier mapping process.

Authors: Shimaa Baraka (Mila); Benjamin Akera (Makerere University); Bibek Aryal (The University of Texas at El Paso); Tenzing Sherpa (International Centre for Integrated Mountain Development); Finu Shrestha (International Centre for Integrated Mountain Development); Anthony Ortiz (Microsoft); Kris Sankaran (University of Wisconsin-Madison); Juan M Lavista Ferres (Microsoft); Mir A Matin (International Center for Integrated Mountain Development); Yoshua Bengio (Mila)

Ecosystems and natural resources Computer vision and remote sensing
NeurIPS 2020 Data-driven modeling of cooling demand in a commercial building (Papers Track)
Abstract and authors: (click to expand)

Abstract: Heating, ventilation, and air conditioning (HVAC) systems account for 30% of the total energy consumption in buildings. Design and implementation of energy-efficient schemes can play a pivotal role in minimizing energy usage. As an important first step towards improved HVAC system controls, this study proposes a new framework for modeling the thermal response of buildings by leveraging data measurements and formulating a data-driven system identification model. The proposed method combines principal component analysis (PCA) to identify the most significant predictors that influence the cooling demand of a building with an auto-regressive integrated moving average with exogenous variables (ARIMAX) model. The performance of the developed model was evaluated both analytically and visually. It was found that our PCA-based ARIMAX (2-0-5) model was able to accurately forecast the cooling demand for the prediction horizon of 7 days. In this work, the actual measurements from a university campus building are used for model development and validation.

Authors: Aqsa Naeem (Stanford University); Sally Benson (Stanford University); Jacques de Chalendar (Stanford University)

Buildings and cities Power and energy Hybrid physical models
NeurIPS 2020 Investigating two super-resolution methods for downscaling precipitation: ESRGAN and CAR (Papers Track)
Abstract and authors: (click to expand)

Abstract: In an effort to provide optimal inputs to downstream modeling systems (e.g., a hydrodynamics model that simulates the water circulation of a lake), we hereby strive to enhance resolution of precipitation fields from a weather model by up to 9x. We test two super-resolution models: the enhanced super-resolution generative adversarial networks (ESRGAN) proposed in 2017, and the content adaptive resampler (CAR) proposed in 2020. Both models outperform simple bicubic interpolation, with the ESRGAN exceeding expectations for accuracy. We make several proposals for extending the work to ensure it can be useful tool for quantifying the impact of climate change on local ecosystems while removing reliance on energy-intensive, high-resolution weather model simulations.

Authors: Campbell Watson (IBM); Chulin Wang (Northwestern University); Tim Lynar (University of New South Wales); Komminist Weldemariam (IBM Research)

Classification, regression, and supervised learning Ecosystems and natural resources
NeurIPS 2020 Emerging Trends of Sustainability Reporting in the ICT Industry: Insights from Discriminative Topic Mining (Papers Track)
Abstract and authors: (click to expand)

Abstract: The Information and Communication Technologies (ICT) industry has a considerable climate change impact and accounts for approximately 3 percent of global carbon emissions. Despite the increasing availability of sustainability reports provided by ICT companies, we still lack a systematic understanding of what has been disclosed at an industry level. In this paper, we make the first major effort to use modern unsupervised learning methods to investigate the sustainability reporting themes and trends of the ICT industry over the past two decades. We build a cross-sector dataset containing 22,534 environmental reports from 1999 to 2019, of which 2,187 are ICT specific. We then apply CatE, a text embedding based topic modeling method, to mine specific keywords that ICT companies use to report on climate change and energy. As a result, we identify (1) important shifts in ICT companies' climate change narratives from physical metrics towards climate-related disasters, (2) key organizations with large influence on ICT companies, and (3) ICT companies' increasing focus on data center and server energy efficiency.

Authors: Lin Shi (Stanford University); Nhi Truong Vu (Stanford University)

Industry Policy Data mining Natural language processing Unsupervised and semi-supervised learning
NeurIPS 2020 Loosely Conditioned Emulation of Global Climate Models With Generative Adversarial Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate models encapsulate our best understanding of the Earth system, allowing research to be conducted on its future under alternative assumptions of how human-driven climate forces are going to evolve. An important application of climate models is to provide metrics of mean and extreme climate changes, particularly under these alternative future scenarios, as these quantities drive the impacts of climate on society and natural systems. Because of the need to explore a wide range of alternative scenarios and other sources of uncertainties in a computationally efficient manner, climate models can only take us so far, as they require significant computational resources, especially when attempting to characterize extreme events, which are rare and thus demand long and numerous simulations in order to accurately represent their changing statistics. Here we use deep learning in a proof of concept that lays the foundation for emulating global climate model output for different scenarios. We train two "loosely conditioned" Generative Adversarial Networks (GANs) that emulate daily precipitation output from a fully coupled Earth system model: one GAN modeling Fall-Winter behavior and the other Spring-Summer. Our GANs are trained to produce spatiotemporal samples: 32 days of precipitation over a 64x128 regular grid discretizing the globe. We evaluate the generator with a set of related performance metrics based upon KL divergence, and find the generated samples to be nearly as well matched to the test data as the validation data is to test. We also find the generated samples to accurately estimate the mean number of dry days and mean longest dry spell in the 32 day samples. Our trained GANs can rapidly generate numerous realizations at a vastly reduced computational expense, compared to large ensembles of climate models, which greatly aids in estimating the statistics of extreme events.

Authors: Alex Ayala (Western Washington University); Chris Drazic (Western Washington University); Brian Hutchinson (Western Washington University); Ben Kravitz (Indiana University); Claudia Tebaldi (Joint Global Change Research Institute)

Generative modeling Climate and Earth science
NeurIPS 2020 The Peruvian Amazon Forestry Dataset: A Leaf Image Classification Corpus (Papers Track)
Abstract and authors: (click to expand)

Abstract: This paper introduces the Peruvian Amazon Forestry Dataset, which includes 59,441 leaves samples from ten of the most profitable and endangered Amazon timber-tree species. Besides, the proposal includes a background removal algorithm to feed a fine-tuned CNN. We evaluate the quantitative (accuracy metric) and qualitative (visual interpretation) impacts of each stage by ablation experiments. The results show a 96.64 % training accuracy and 96.52 % testing accuracy on the VGG-19 model. Furthermore, the visual interpretation of the model evidences that leaf venations have the highest correlation in the plant recognition task.

Authors: Gerson Waldyr Vizcarra Aguilar (San Pablo Catholic University); Danitza Bermejo (Universidad Nacional del Altiplano); Manasses A. Mauricio (Universidad Católica San Pablo); Ricardo Zarate (Instituto de Investigaciones de la Amazonía Peruana); Erwin Dianderas (Instituto de Investigaciones de la Amazonía Peruana)

Agriculture, forestry and other land use Meta- and transfer learning
NeurIPS 2020 Spatiotemporal Features Improve Fine-Grained Butterfly Image Classification (Papers Track)
Abstract and authors: (click to expand)

Abstract: Understanding the changing distributions of butterflies gives insight into the impacts of climate change across ecosystems and is a prerequisite for conservation efforts. eButterfly is a citizen science website created to allow people to track the butterfly species around them and use these observations to contribute to research. However, correctly identifying butterfly species is a challenging task for non-specialists and currently requires the involvement of entomologists to verify the labels of novice users on the website. We have developed a computer vision model to label butterfly images from eButterfly automatically, decreasing the need for human experts. We employ a model that incorporates geographic and temporal information of where and when the image was taken, in addition to the image itself. We show that we can successfully apply this spatiotemporal model for fine-grained image recognition, significantly improving the accuracy of our classification model compared to a baseline image recognition system trained on the same dataset.

Authors: Marta Skreta (University of Toronto); Sasha Luccioni (Mila); David Rolnick (McGill University, Mila)

Ecosystems and natural resources Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2020 High-resolution global irrigation prediction with Sentinel-2 30m data (Papers Track)
Abstract and authors: (click to expand)

Abstract: An accurate and precise understanding of global irrigation usage is crucial for a variety of climate science efforts. Irrigation is highly energy-intensive, and as population growth continues at its current pace, increases in crop need and water usage will have an impact on climate change. Precise irrigation data can help with monitoring water usage and optimizing agricultural yield, particularly in developing countries. Irrigation data, in tandem with precipitation data, can be used to predict water budgets as well as climate and weather modeling. With our research, we produce an irrigation prediction model that combines unsupervised clustering of Normalized Difference Vegetation Index (NDVI) temporal signatures with a precipitation heuristic to label the months that irrigation peaks for each cropland cluster in a given year. We have developed a novel irrigation model and Python package ("Irrigation30") to generate 30m resolution irrigation predictions of cropland worldwide. With a small crowdsourced test set of cropland coordinates and irrigation labels, using a fraction of the resources used by the state-of-the-art NASA-funded GFSAD30 project with irrigation data limited to India and Australia, our model was able to achieve consistency scores in excess of 97% and an accuracy of 92% in a small geo-diverse randomly sampled test set.

Authors: Will Hawkins (UC Berkeley); Weixin Wu (UC Berkeley); Sonal Thakkar (UC Berkeley); Puya Vahabi (UC Berkeley); Alberto Todeschini (UC Berkeley)

Agriculture, forestry and other land use Unsupervised and semi-supervised learning
NeurIPS 2020 Do Occupants in a Building exhibit patterns in Energy Consumption? Analyzing Clusters in Energy Social Games (Papers Track)
Abstract and authors: (click to expand)

Abstract: Energy use in buildings account for approximately half of global electricity consumption and a significant amount of CO2 emissions. To encourage energy efficient behavior among occupants in a building, energy social games have emerged to be a successful strategy leveraging human-in-the-loop strategy and engaging users in a competitive game with incentives for energy efficient behavior. Prior works involve an incentive design mechanism which is dependent on knowledge of utility functions (energy use behavior) for the users, which is hard to compute when the number of users is high, common in buildings. We propose that the utilities can be grouped to a relatively small number of clusters, which can then be targeted with tailored incentives. Proposed work performs the above segmentation by learning the features leading to human decision making towards energy usage in competitive environment. We propose a graphical lasso based approach with explainable nature for such segmentation, by studying the feature correlations in a real-world energy social game dataset.

Authors: Hari Prasanna Das (UC Berkeley); Ioannis C. Konstantakopoulos (UC Berkeley); Aummul Baneen Manasawala (UC Berkeley); Tanya Veeravalli (UC Berkeley); Huihan Liu (UC Berkeley); Costas J. Spanos (University of California at Berkeley)

Buildings and cities Other
NeurIPS 2020 In-N-Out: Pre-Training and Self-Training using Auxiliary Information for Out-of-Distribution Robustness (Papers Track)
Abstract and authors: (click to expand)

Abstract: Many machine learning applications used to tackle climate change involve lots of unlabeled data (such as satellite imagery) along with auxiliary information such as climate data. In this work, we show how to use auxiliary information in a semi-supervised setting to improve both in-distribution and out-of-distribution (OOD) accuracies (e.g. for countries in Africa where we have very little labeled data). We show that 1) on real-world datasets, the common practice of using auxiliary information as additional input features improves in-distribution error but can hurt OOD. Oppositely, we find that 2) using auxiliary information as outputs of auxiliary tasks to pre-train a model improves OOD error. 3) To get the best of both worlds, we introduce In-N-Out, which first trains a model with auxiliary inputs and uses it to pseudolabel all the in-distribution inputs, then pre-trains a model on OOD auxiliary outputs and fine-tunes this model with the pseudolabels (self-training). We show both theoretically and empirically on remote sensing datasets for land cover prediction and cropland prediction that In-N-Out outperforms auxiliary inputs or outputs alone on both in-distribution and OOD error.

Authors: Robbie M Jones (Stanford University); Sang Michael Xie (Stanford University); Ananya Kumar (Stanford University); Fereshte Khani (Stanford); Tengyu Ma (Stanford University); Percy Liang (Stanford University)

Meta- and transfer learning Agriculture, forestry and other land use Computer vision and remote sensing Unsupervised and semi-supervised learning
NeurIPS 2020 Climate-FEVER: A Dataset for Verification of Real-World Climate Claims (Papers Track)
Abstract and authors: (click to expand)

Abstract: Our goal is to introduce \textsc{climate-fever}, a new publicly available dataset for verification of climate change-related claims. By providing a dataset for the research community, we aim to help and encourage work on improving algorithms for retrieving climate-specific information and detecting fake news in social and mass media to reduce the impact of misinformation on the formation of public opinion on climate change. We adapt the methodology of \textsc{fever} \cite{thorne2018fever}, the largest dataset of artificially designed claims, to real-life claims collected from the Internet. Although during this process, we could count on the support of renowned climate scientists, it turned out to be no easy task. We discuss the surprising, subtle complexity of modeling real-world climate-related claims within the \textsc{fever} framework, which provides a valuable challenge for general natural language understanding. We hope that our work will mark the beginning of an exciting long-term joint effort by the climate science and \textsc{ai} community to develop robust algorithms to verify the facts for climate-related claims.

Authors: Markus Leippold (University of Zurich); Thomas Diggelmann (ETH Zurich)

Natural language processing Behavioral and social science Climate finance Other
NeurIPS 2020 Understanding global fire regimes using Artificial Intelligence (Papers Track)
Abstract and authors: (click to expand)

Abstract: Improved understanding of fire activity and its influencing factors will impact the way we interact and coexist with not only the fire itself but also with the ecosystem as a whole. We consolidate more than 20 million wildfire records between 2000 and 2018 across the six continents. This data is processed with artificial intelligence methods to discover global fire regimes, areas with characteristic fire behavior over long periods. We discover 15 groups with clear differences in fire-related historical behavior. Despite sharing historical fire behavior, regions belonging to the same group present significant differences in location and influencing factors. Groups are further divided into 62 regimes based on spatial aggregation patterns, providing a comprehensive characterization. This allows an interpretation of how a combination of vegetation, climate, and demographic features results in a specific fire regime. The current work expands on existing classification efforts and is a step forward in addressing the complex challenge of characterizing global fire regimes.

Authors: Cristobal Pais (University of California Berkeley); Jose-Ramon Gonzalez (CTFC); Pelagy Moudio (University of California Berkeley); Jordi Garcia-Gonzalo (CTFC); Marta C. González (Berkeley); Zuo-Jun Shen (University of California, Berkeley)

Climate and Earth science Disaster prediction, management, and relief
NeurIPS 2020 ClimaText: A Dataset for Climate Change Topic Detection (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change communication in the mass media and other textual sources may affect and shape public perception. Extracting climate change information from these sources is an important task, e.g., for filtering content and e-discovery, sentiment analysis, automatic summarization, question-answering, and fact-checking. However, automating this process is a challenge, as climate change is a complex, fast-moving, and often ambiguous topic with scarce resources for popular text-based AI tasks. In this paper, we introduce \textsc{ClimaText}, a dataset for sentence-based climate change topic detection, which we make publicly available. We explore different approaches to identify the climate change topic in various text sources. We find that popular keyword-based models are not adequate for such a complex and evolving task. Context-based algorithms like BERT~\cite{devlin2018bert} can detect, in addition to many trivial cases, a variety of complex and implicit topic patterns. Nevertheless, our analysis reveals a great potential for improvement in several directions, such as, e.g., capturing the discussion on indirect effects of climate change. Hence, we hope this work can serve as a good starting point for further research on this topic.

Authors: Markus Leippold (University of Zurich); Francesco Saverio Varini (ETH)

Natural language processing Behavioral and social science Other
NeurIPS 2020 Towards Data-Driven Physics-Informed Global Precipitation Forecasting from Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Under the effects of global warming, extreme events such as floods and droughts are increasing in frequency and intensity. This trend directly affects communities and make all the more urgent widening the access to accurate precipitation forecasting systems for disaster preparedness. Nowadays, weather forecasting relies on numerical models necessitating massive computing resources that most developing countries cannot afford. Machine learning approaches are still in their infancy but already show the promise for democratizing weather predictions, by leveraging any data source and requiring less compute. In this work, we propose a methodology for data-driven and physics-aware global precipitation forecasting from satellite imagery. To fully take advantage of the available data, we design the system as three elements: 1. The atmospheric state is estimated from recent satellite data. 2. The atmospheric state is propagated forward in time. 3. The atmospheric state is used to derive the precipitation intensity within a nearby time interval. In particular, our use of stochastic methods for forecasting the atmospheric state represents a novel application in this domain.

Authors: Valentina Zantedeschi (GE Global Research); Daniele De Martini (University of Oxford); Catherine Tong (University of Oxford); Christian A Schroeder de Witt (University of Oxford); Piotr Bilinski (University of Warsaw / University of Oxford); Alfredo Kalaitzis (University of Oxford); Matthew Chantry (University of Oxford); Duncan Watson-Parris (University of Oxford)

Climate and Earth science Agriculture, forestry and other land use Disaster prediction, management, and relief Ecosystems and natural resources Classification, regression, and supervised learning Computer vision and remote sensing
NeurIPS 2020 A Generative Adversarial Gated Recurrent Network for Power Disaggregation & Consumption Awareness (Papers Track)
Abstract and authors: (click to expand)

Abstract: Separating the household aggregated power signal into its additive sub-components is called energy (power) disaggregation or Non-Intrusive Load Monitoring. NILM can play an instrumental role as a driver towards consumer energy consumption awareness and behavioral change. In this paper, we propose EnerGAN++, a model based on GANs for robust energy disaggregation. We propose a unified autoencoder (AE) and GAN architecture, in which the AE achieves a non-linear power signal source separation. The discriminator performs sequence classification, using a recurrent CNN to handle the temporal dynamics of an appliance energy consumption time series. Experimental results indicate the proposed method’s superiority compared to the current state of the art.

Authors: Maria Kaselimi (National Technical University of Athens); Athanasios Voulodimos (University of West Attica); Nikolaos Doulamis (National Technical University of Athens); Anastasios Doulamis (Technical University of Crete); Eftychios Protopapadakis (National Technical University of Athens)

Power and energy Generative modeling
NeurIPS 2020 Deep Fire Topology: Understanding the role of landscape spatial patterns in wildfire susceptibility (Papers Track)
Abstract and authors: (click to expand)

Abstract: Increasing wildfire activity across the globe has become an urgent issue with enormous ecological and social impacts. While there is evidence that landscape topology affects fire growth, no study has yet reported its potential influence on fire ignition. This study proposes a deep learning framework focused on understanding the impact of different landscape topologies on the ignition of a wildfire and the rationale behind these results. Our model achieves an accuracy of above 90\% in fire occurrence prediction, detection, and classification of risky areas by only exploiting topological pattern information from 17,579 landscapes. This study reveals the strong potential of landscape topology in wildfire occurrence prediction and its implications for similar research. The proposed methodology can be applied to multiple fields/studies to understand and capture the role and impact of different topological features and their interactions.

Authors: Cristobal Pais (University of California Berkeley); Alejandro Miranda (University of Chile); Jaime Carrasco (University of Chile); Zuo-Jun Shen (University of California, Berkeley)

Computer vision and remote sensing Disaster prediction, management, and relief Agriculture, forestry and other land use
NeurIPS 2020 Interpretability in Convolutional Neural Networks for Building Damage Classification in Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Natural disasters ravage the world's cities, valleys, and shores on a monthly basis. Having precise and efficient mechanisms for assessing infrastructure damage is essential to channel resources and minimize the loss of life. Using a dataset that includes labeled pre- and post- disaster satellite imagery, we train multiple convolutional neural networks to assess building damage on a per-building basis. In order to investigate how to best classify building damage, we present a highly interpretable deep-learning methodology that seeks to explicitly convey the most useful information required to train an accurate classification model. We also delve into which loss functions best optimize these models. Our findings include that ordinal-cross entropy loss is the most optimal loss function to use and that including the type of disaster that caused the damage in combination with a pre- and post-disaster image best predicts the level of damage caused. Our research seeks to computationally contribute to aiding in this ongoing and growing humanitarian crisis, heightened by climate change.

Authors: Thomas Y Chen (The Academy for Mathematics, Science, and Engineering)

Computer vision and remote sensing Buildings and cities Interpretable ML
NeurIPS 2020 Long-Range Seasonal Forecasting of 2m-Temperature with Machine Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: A significant challenge in seasonal climate prediction is whether a prediction can beat climatology. We hereby present results from two data-driven models - a convolutional (CNN) and a recurrent (RNN) neural network - that predict 2m temperature out to 52 weeks for six geographically-diverse locations. The motivation for testing the two classes of ML models is to allow the CNN to leverage information related to teleconnections and the RNN to leverage long-term historical temporal signals. The ML models boast improved accuracy of long-range temperature forecasts up to a lead time of 30 weeks for PCC and up 52 weeks for RMSESS, however only for select locations. Further iteration is required to ensure the ML models have value beyond regions where the climatology has a noticeably reduced correlation skill, namely the tropics.

Authors: Etienne E Vos (IBM); Ashley Gritzman (IBM); Sibusisiwe Makhanya (IBM Research); Thabang Mashinini (IBM); Campbell Watson (IBM)

Classification, regression, and supervised learning Climate and Earth science
NeurIPS 2020 Explaining Complex Energy Systems: A Challenge (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Designing future low-carbon, sector-coupled energy systems is a complex task. The work is therefore often supported by software tools that model and optimize possible energy systems. These tools typically have high dimensional inputs and outputs and are tailored towards domain experts. The final investment decisions to implement a certain system, however, are mostly made by people with little time and prior knowledge, thus unable to understand models and their input data used in these tools. Since such decisions are often connected to significant personal consequences for the decision makers, it is not enough for them to rely on experts only. They need an own, at least rough understanding. Explaining the key rationales behind complex energy system designs to non-expert decision makers in a short amount of time is thus a critical task for realizing projects of the energy transition in practice. It is also an interesting, novel challenge for the explainable AI community.

Authors: Jonas Hülsmann (TU Darmstadt); Florian Steinke (TU Darmstadt)

Interpretable ML Climate finance Power and energy
NeurIPS 2020 The Human Effect Requires Affect: Addressing Social-Psychological Factors of Climate Change with Machine Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Machine learning has the potential to aid in mitigating the human effects of climate change. Previous applications of machine learning to tackle the human effects in climate change include approaches like informing individuals of their carbon footprint and strategies to reduce it. For these methods to be the most effective they must consider relevant social-psychological factors for each individual. Of social-psychological factors at play in climate change, affect has been previously identified as a key element in perceptions and willingness to engage in mitigative behaviours. In this work, we propose an investigation into how affect could be incorporated to enhance machine learning based interventions for climate change. We propose using affective agent-based modelling for climate change as well as the use of a simulated climate change social dilemma to explore the potential benefits of affective machine learning interventions. Behavioural and informational interventions can be a powerful tool in helping humans adopt mitigative behaviours. We expect that utilizing affective ML can make interventions an even more powerful tool and help mitigative behaviours become widely adopted.

Authors: Kyle Tilbury (University of Waterloo); Jesse Hoey (University of Waterloo)

Behavioral and social science Societal adaptation Causal and Bayesian methods
NeurIPS 2020 A Way Toward Low-Carbon Shipping: Improving Port Operations Planning using Machine Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Despite being the most carbon-efficient way of transportation, shipping is an important contributor to air pollution especially in coastal areas. The sector’s impact on the environment still need mitigation, through different measures undertaken so far. Operational optimization of ports and ships is a step in shipping progress towards reducing the pollution. The main purpose of this research is to reduce the degree of error and uncertainty of some operational parameters using Machine Learning models, and provide port managers with accurate information to assist them in their decision-making process. Therefore, they will be able to manage ships speed and port times for a better monitoring of ships emissions during sea voyage and port stay.

Authors: Sara El Mekkaoui (EMI Engineering School); Loubna Benabou (UQAR); Abdelaziz Berrado (EMI Engineering School)

Transportation
NeurIPS 2020 Privacy Preserving Demand Forecasting to Encourage Consumer Acceptance of Smart Energy Meters (Proposals Track)
Abstract and authors: (click to expand)

Abstract: In this proposal paper we highlight the need for privacy preserving energy demand forecasting to allay a major concern consumers have about smart meter installations. High resolution smart meter data can expose many private aspects of a consumer’s household such as occupancy, habits and individual appliance usage. Yet smart metering infrastructure has the potential to vastly reduce carbon emissions from the energy sector through improved operating efficiencies. We propose the application of a distributed machine learning setting known as federated learning for energy demand forecasting at various scales to make load prediction possible whilst retaining the privacy of consumers’ raw energy consumption data.

Authors: Christopher Briggs (Keele University); Zhong Fan (Keele University); Peter Andras (Keele University, School of Computing and Mathematics, Newcastle-under-Lyme, UK)

Power and energy Buildings and cities Societal adaptation Classification, regression, and supervised learning Time-series analysis
NeurIPS 2020 Leveraging Machine learning for Sustainable and Self-sufficient Energy Communities (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Community Energies (CEs) are the next-generation energy management techniques that empowers citizens to interact with the energy market as self-consumers or prosumers actively. Successful implementation of CEs will promote sustainable energy production and consumption practices; thus, contributing to affordable and clean energy (SDG7) and climate action (SDG 13). Despite the potential of CEs, managing the overall power production and demand is challenging. This is because power is generated, distributed and controlled by several producers, each of which with different, and potentially conflicting, objectives. Thus, this project will investigate the role of machine learning approaches in smartening CEs, increasing energy awareness and enabling distributed energy resources planning and management. The project implementation will be centered around proof of concept development and capacity development in Africa.

Authors: Anthony Faustine (University College Dublin); Lucas Pereira (ITI, LARSyS, Técnico Lisboa); Loubna Benabou (UQAR); Daniel Ngondya (The University of Dodoma)

Power and energy
NeurIPS 2020 Structural Forecasting for Tropical Cyclone Intensity Prediction: Providing Insight with Deep Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Tropical cyclone (TC) intensity forecasts are ultimately issued by human forecasters. The human in-the-loop pipeline requires that any forecasting guidance must be easily digestible by TC experts if it is to be adopted at operational centers like the National Hurricane Center. Our proposed framework leverages deep learning to provide forecasters with something neither end-to-end prediction models nor traditional intensity guidance does: a powerful tool for monitoring high-dimensional time series of key physically relevant predictors and the means to understand how the predictors relate to one another and to short-term intensity changes.

Authors: Irwin H McNeely (Carnegie Mellon University); Kimberly Wood (Mississippi State University); Niccolo Dalmasso (Carnegie Mellon University); Ann Lee (Carnegie Mellon University)

Disaster prediction, management, and relief Interpretable ML
NeurIPS 2020 Hyperspectral Remote Sensing of Aquatic Microbes to Support Water Resource Management (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Harmful algal blooms in drinking water supply and at recreational sites endanger human health. Excessive algal growth can result in low oxygen environments, making them uninhabitable for fish and other aquatic life. Harmful algae and algal blooms are predicted to increase in frequency and extent due to the warming climate, but microbial dynamics remain difficult to predict. Existing satellite remote sensing monitoring technologies are ill-equipped to discriminate harmful algae, while models do not adequately capture the complex controls on algal populations. This proposal explores the potential for Bayesian neural networks to detect phytoplankton pigments from hyperspectral remote sensing reflectance retrievals. Once developed, such a model could enable hyperspectral remote sensing retrievals to support decision making in water resource management as more advanced ocean color satellites are launched in the coming decade. While uncertainty quantification motivates the proposed use of Bayesian models, the interpretation of these uncertainties in an operational context must be carefully considered.

Authors: Grace E Kim (Booz Allen Hamilton); Evan Poworoznek (NASA GSFC); Susanne Craig (NASA GSFC)

Ecosystems and natural resources Climate and Earth science
NeurIPS 2020 Wildfire Smoke and Air Quality: How Machine Learning Can Guide Forest Management (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Prescribed burns are currently the most effective method of reducing the risk of widespread wildfires, but a largely missing component in forest management is knowing which fuels one can safely burn to minimize exposure to toxic smoke. Here we show how machine learning, such as spectral clustering and manifold learning, can provide interpretable representations and powerful tools for differentiating between smoke types, hence providing forest managers with vital information on effective strategies to reduce climate-induced wildfires while minimizing production of harmful smoke.

Authors: Lorenzo Tomaselli (Carnegie Mellon University); Coty Jen (Carnegie Mellon University); Ann Lee (Carnegie Mellon University)

Disaster prediction, management, and relief Agriculture, forestry and other land use Interpretable ML Unsupervised and semi-supervised learning
NeurIPS 2020 HECT: High-Dimensional Ensemble Consistency Testing for Climate Models (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Climate models play a crucial role in understanding the effect of environmental and man-made changes on climate to help mitigate climate risks and inform governmental decisions. Large global climate models such as the Community Earth System Model (CESM), developed by the National Center for Atmospheric Research, are very complex with millions of lines of code describing interactions of the atmosphere, land, oceans, and ice, among other components. As development of the CESM is constantly ongoing, simulation outputs need to be continuously controlled for quality. To be able to distinguish a ``climate-changing'' modification of the code base from a true climate-changing physical process or intervention, there needs to be a principled way of assessing statistical reproducibility that can handle both spatial and temporal high-dimensional simulation outputs. Our proposed work uses probabilistic classifiers like tree-based algorithms and deep neural networks to perform a statistically rigorous goodness-of-fit test of high-dimensional spatio-temporal data.

Authors: Niccolo Dalmasso (Carnegie Mellon University); Galen Vincent (Carnegie Mellon University); Dorit Hammerling (Colorado School of Mines); Ann Lee (Carnegie Mellon University)

Climate and Earth science Classification, regression, and supervised learning Uncertainty quantification and robustness
NeurIPS 2020 Towards DeepSentinel: An extensible corpus of labelled Sentinel-1 and -2 imagery and a proposed general purpose sensor-fusion semantic embedding model (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Earth observation offers new insight into anthropogenic changes to nature, and how these changes are effecting (and are effected by) the built environment and the real economy. With the global availability of medium-resolution (10-30m) synthetic aperature radar (SAR) Sentinel-1 and multispectral Sentinel-2 imagery, machine learning can be employed to offer these insights at scale, unbiased to company- and country-level reporting. In this proposal, we document the development of an extensible corpus of labelled and unlabelled Sentinel-1 and Sentinel-2 imagery for the purposes of sensor fusion research. We make a large corpus and supporting code publicly available. We propose our own experiment design for the development of \emph{DeepSentinel}, a general-purpose semantic embedding model. Our aspiration is to provide pretrained models for transfer learning applications, significantly accelerating the impact of machine learning-enhanced earth observation on climate change mitigation.

Authors: Lucas Kruitwagen (University of Oxford)

Computer vision and remote sensing Agriculture, forestry and other land use
NeurIPS 2020 Monitoring Shorelines via High-Resolution Satellite Imagery and Deep Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Twentieth-century has seen an overall sea-level rise of 0.5m [7, 11] and the studies for the twenty-first-century project the overall increment within a range of 0.5m to 2m, considering high emission scenarios and rapid melting of major Antarctic glaciers. Naturally, this has a severe impact on a major percentage of the population inhabiting coastal land zones], with a recent study placing 110million people living below the local high tide line. Of all the different coastline types, sandy shores, forming 31% of the world’s beaches, undergo major erosion and accretion changes and hence are of special focus in this paper. Because of these reasons, it is paramount to regularly monitor the coastline changes across the world for better understanding and to create necessary preparation and mitigation strategies.

Authors: Venkatesh Ramesh (HyperVerge); Digvijay Singh (HyperVerge)

Computer vision and remote sensing
NeurIPS 2020 Graph Neural Networks for Improved El Niño Forecasting (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicting El Ni\~no-Southern Oscillation (ENSO). However, current deep learning models are based on convolutional neural networks which are difficult to interpret and can fail to model large-scale atmospheric patterns called teleconnections. Hence, we propose the application of spatiotemporal Graph Neural Networks (GNN) to forecast ENSO at long lead times, finer granularity and improved predictive skill than current state-of-the-art methods. The explicit modeling of information flow via edges may also allow for more interpretable forecasts. Preliminary results are promising and outperform state-of-the art systems for projections 1 and 3 months ahead.

Authors: Salva Rühling Cachay (Technical University of Darmstadt); Emma Erickson (University of Illinois at Urbana-Champaign); Arthur F C Bucker (University of São Paulo); Ernest J Pokropek (Warsaw University of Techology); Willa Potosnak (Duquesne University); Salomey Osei (African Master's of Machine Intelligence(AMMI-GH)); Björn Lütjens (MIT)

Climate and Earth science Agriculture, forestry and other land use Disaster prediction, management, and relief Classification, regression, and supervised learning Interpretable ML Time-series analysis
NeurIPS 2020 Residue Density Segmentation for Monitoring and Optimizing Tillage Practices (Proposals Track)
Abstract and authors: (click to expand)

Abstract: "No-till" and cover cropping are often identified as the leading simple, best management practices for carbon sequestration in agriculture. However, the root of the problem is more complex, with the potential benefits of these approaches depending on numerous factors including a field's soil type(s), topography, and management history. Instead of using computer vision approaches to simply classify a field as till vs. no-till, we instead seek to identify the degree of residue coverage across a field through a probabilistic deep learning segmentation approach to enable more accurate analysis of carbon holding potential and realization. This approach will not only provide more precise insights into currently implemented practices, but also enable a more accurate identification process of fields with the greatest potential for adopting new practices to significantly impact carbon sequestration in agriculture.

Authors: Jennifer Hobbs (IntelinAir); Ivan A Dozier (IntelinAir); Naira Hovakimyan (UIUC)

Agriculture, forestry and other land use Carbon capture and sequestration Computer vision and remote sensing
NeurIPS 2020 Machine Learning Informed Policy for Environmental Justice in Atlanta with Climate Justice Implications (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Environmental hazards are not evenly distributed between the privileged and the protected classes in the U.S. Neighborhood zoning and planning of hazardous treatment, storage, and disposal facilities (TSDs) play a significant role in this sanctioned environmental racism. TSDs and toxic chemical releases into the air are accounted for by the U.S. Environmental Protection Agency’s (EPA) Toxic Release Inventories (TRIs) [2,4,7, 14]. TSDs and toxic chemical releases not only emit carbon dioxide and methane, which are the top two drivers of climate change, but also emit contaminants, such as arsenic, lead, and mercury into the water, air, and crops [12]. Studies on spatial disparities in TRIs and TSDs based on race/ethnicity and socioeconomic status (SES) in U.S. cities, such as Charleston, SC, San Joaquin Valley, CA, and West Oakland, CA showed that there are more TRIs and TSDs in non-white and low SES areas in those cities [2,4,7]. Environmental justice recognizes that the impacts of environmental burdens, such as socioeconomic and public health outcomes, are not equitably distributed, and in fact bear the heaviest burden on marginalized people, including communities of color and low-income communities [12]. In our case, environmental justice has a strong tie to climate justice since the TRIs release carbon dioxide and methane into the atmosphere.

Authors: Lelia Hampton (Massachusetts Institute of Technology)

Policy Behavioral and social science Climate justice Classification, regression, and supervised learning Unsupervised and semi-supervised learning
NeurIPS 2020 A Multi-source, End-to-End Solution for Tracking Climate Change Adaptation in Agriculture (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The impact of climate change on tropical agri-food systems will depend on both the direction and magnitude of climate change, and the agricultural sector’s adaptive capacity, the latter being affected by the chosen adaptation strategies. By extending SEIRS, a Satellite Remote Sensing (SRS) based system originally developed by the International Center for Tropical Agriculture - CIAT for monitoring U.S. Government-funded development programs across cropping areas in Africa, this research proposes the development and deployment of a scalable AI-based platform exploiting free-of-charge SRS data that will enable the agri-food sector to monitor a wide range of climate change adaptation (CCA) interventions in a timely, evidence-driven and comparable manner. The main contributions of the platform are i) ingesting and processing variety sources of SRS data with a considerable record (> 5 years) of vegetation greenness and precipitation (input data); ii) operating an end-to-end system by exploiting AI-based models suited to time series analysis such as Seq2Seq and Transformers; iii) providing customised proxies informing the success or failure of a given local CCA intervention(s).

Authors: Alejandro Coca-Castro (Kings College London); Aaron Golden (NUI Galway); Louis Reymondin (The Alliance of Bioversity International and the International Center for Tropical Agriculture)

Computer vision and remote sensing Agriculture, forestry and other land use Climate finance Policy Classification, regression, and supervised learning Time-series analysis
NeurIPS 2020 Expert-in-the-loop Systems Towards Safety-critical Machine Learning Technology in Wildfire Intelligence (Proposals Track)
Abstract and authors: (click to expand)

Abstract: With the advent of climate change, wildfires are becoming more frequent and severe across several regions worldwide. To prevent and mitigate its effects, wildfire intelligence plays a pivotal role, e.g. to monitor the evolution of wildfires and for early detection in high-risk areas such as wildland-urban-interface regions. Recent works have proposed deep learning solutions for fire detection tasks, however the current limited databases prevent reliable real-world deployments. We propose the development of expert-in-the-loop systems that combine the benefits of semi-automated data annotation with relevant domain knowledge expertise. Through this approach we aim to improve the data curation process and contribute to the generation of large-scale image databases for relevant wildfire tasks and empower the application of machine learning techniques in wildfire intelligence in real scenarios.

Authors: Maria João Sousa (IDMEC, Instituto Superior Técnico, Universidade de Lisboa); Alexandra Moutinho (IDMEC, Instituto Superior Técnico, Universidade de Lisboa); Miguel Almeida (ADAI, University of Coimbra)

Computer vision and remote sensing Carbon capture and sequestration Disaster prediction, management, and relief Agriculture, forestry and other land use Classification, regression, and supervised learning Interpretable ML Meta- and transfer learning Natural language processing Uncertainty quantification and robustness Unsupervised and semi-supervised learning
NeurIPS 2020 ACED: Accelerated Computational Electrochemical systems Discovery (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Large-scale electrification is vital to addressing the climate crisis, but many engineering challenges remain to fully electrifying both the chemical industry and transportation. In both of these areas, new electrochemical materials and systems will be critical, but developing these systems currently relies heavily on computationally expensive first-principles simulations as well as human-time-intensive experimental trial and error. We propose to develop an automated workflow that accelerates these computational steps by introducing both automated error handling in generating the first-principles training data as well as physics-informed machine learning surrogates to further reduce computational cost. It will also have the capacity to include automated experiments ``in the loop'' in order to dramatically accelerate the overall materials discovery pipeline.

Authors: Rachel C Kurchin (CMU); Eric Muckley (Citrine Informatics); Lance Kavalsky (CMU); Vinay Hegde (Citrine Informatics); Dhairya Gandhi (Julia Computing); Xiaoyu Sun (CMU); Matthew Johnson (MIT); Alan Edelman (MIT); James Saal (Citrine Informatics); Christopher V Rackauckas (Massachusetts Institute of Technology); Bryce Meredig (Citrine Informatics); Viral Shah (Julia Computing); Venkat Viswanathan (Carnegie Mellon University)

Power and energy Agriculture, forestry and other land use Transportation Active learning Classification, regression, and supervised learning Hybrid physical models Interpretable ML Uncertainty quantification and robustness
NeurIPS 2020 Forecasting Marginal Emissions Factors in PJM (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Many climate change applications rely on accurate forecasts of power grid emissions, but many forecasting methods can be expensive, sensitive to input errors, or lacking in domain knowledge. Motivated by initial experiments using deep learning and power system modeling techniques, we propose a method that combines the strengths of both of these approaches to forecast hourly day-ahead MEFs for the PJM region of the United States.

Authors: Amy H Wang (Western University); Priya L Donti (Carnegie Mellon University)

Power and energy Hybrid physical models Time-series analysis
NeurIPS 2020 Artificial Intelligence, Machine Learning and Modeling for Understanding the Oceans and Climate Change (Proposals Track)
Abstract and authors: (click to expand)

Abstract: These changes will have a drastic impact on almost all forms of life in the ocean with further consequences on food security, ecosystem services in coastal and inland communities. Despite these impacts, scientific data and infrastructures are still lacking to understand and quantify the consequences of these perturbations on the marine ecosystem. Understanding this phenomenon is not only an urgent but also a scientifically demanding task. Consequently, it is a problem that must be addressed with a scientific cohort approach, where multi-disciplinary teams collaborate to bring the best of different scientific areas. In this proposal paper, we describe our newly launched four-years project focused on developing new artificial intelligence, machine learning, and mathematical modeling tools to contribute to the understanding of the structure, functioning, and underlying mechanisms and dynamics of the global ocean symbiome and its relation with climate change. These actions should enable the understanding of our oceans and predict and mitigate the consequences of climate change.

Authors: Nayat Sánchez Pi (Inria); Luis Martí (Inria); André Abreu (Fountation Tara Océans); Olivier Bernard (Inria); Colomban de Vargas (CNRS); Damien Eveillard (Univ. Nantes); Alejandro Maass (CMM, U. Chile); Pablo Marquet (PUC); Jacques Sainte-Marie (Inria); Julien Salomin (Inria); Marc Schoenauer (INRIA); Michele Sebag (LRI, CNRS, France)

Interpretable ML Carbon capture and sequestration Ecosystems and natural resources Active learning Causal and Bayesian methods Computer vision and remote sensing Hybrid physical models Meta- and transfer learning Time-series analysis
NeurIPS 2020 Machine Learning towards a Global Parameterisation of Atmospheric New Particle Formation and Growth (Proposals Track)
Abstract and authors: (click to expand)

Abstract: New particle formation (NPF) and growth in the atmosphere affects climate, weather, air quality, and human health. It is the first step of the complex process leading to cloud condensation nuclei (CCN) formation. Even though there is a wealth of observations from field measurements (in forests, high-altitude, polar regions, coastal and urban sites, aircraft campaigns), as well as laboratory studies of multi-component nucleation (including the CLOUD chamber at CERN), and improved nucleation theories, the NPF parameterisations in regional and global models are lacking. These deficiencies make the impacts of aerosols one of the highest sources of uncertainty in global climate change modelling, and associated impacts on weather and human health. We propose to use Machine Learning methods to overcome the challenges in modelling aerosol nucleation and growth, by ingesting the data from the multitude of available sources to create a single parameterisation applicable throughout the modelled atmosphere (troposphere and stratosphere at all latitudes) that efficiently encompasses all input ambient conditions and concentrations of relevant species.

Authors: Theodoros Christoudias (Cyprus Institute); Mihalis A Nicolaou (Cyprus Institute)

Climate and Earth science Classification, regression, and supervised learning
ICLR 2020 BISCUIT: Building Intelligent System Customer Investment Tools (Papers Track)
Abstract and authors: (click to expand)

Abstract: Energy use in buildings account for approximately half of global electricity consumption and a significant amount of CO2 emissions. Often, the higher energy usage in buildings are accounted to old and poorly maintained infrastructure and equipments. On the other hand, Smart buildings are capable of achieving energy efficiency by using intelligent services such as indoor positioning, personalized lighting, demand-based heating ventilation and air-conditioning, automatic fault detection and recovery etc. However, most buildings nowadays lack the basic components and infrastructure to support such services. The investment decision of intelligent system design and retrofit can be a daunting task, because it involves both hardware (sensors, actuators, servers) and software (operating systems, service algorithms), which have issues of compatibility, functionality constraints, and opportunities of co-design of synergy. Our work proposes a user-oriented investment decision toolset using optimization and machine learning techniques aimed at handling the complexity of exploration in the large design space and to enhance cost-effectiveness, energy efficiency, and human-centric values. The toolset is demonstrated in a case study to retrofit a medium-sized building, where it is shown to propose a design that significantly lowers the overall investment cost while achieving user specifications.

Authors: Ming Jin (U.C. Berkeley); Ruoxi Jia (UC Berkeley); Hari Prasanna Das (UC Berkeley); Wei Feng (Lawrence Berkeley National Laboratory); Costas J. Spanos (University of California at Berkeley)

Buildings and cities
ICLR 2020 Deep Reinforcement Learning based Renewable Energy Error Compensable Forecasting (Papers Track)
Abstract and authors: (click to expand)

Abstract: Recently, renewable energy is rapidly integrated into the power grid to prevent climate change, and accurate forecasting of renewable generation becomes critical for reliable power system operation. However, existing forecasting algorithms only focused on reducing forecasting errors without considering error compensability by using a large-scale battery. In this paper, we propose a novel strategy called error compensable forecasting. We switch the objective of forecasting from reducing errors to making errors compensable by leveraging a battery. Specifically, we propose a deep reinforcement learning based framework having forecasting in the loop of control. Extensive simulations show that the proposed one-hour ahead forecasting achieves zero error for more than 98% of time while reducing the operational expenditure by up to 44%.

Authors: Jaeik Jeong (Sogang University); Hongseok Kim (Sogang University)

Power and energy Data presentation and management
ICLR 2020 Missing-insensitive Short-term Load Forecasting Leveraging Autoencoder and LSTM (Papers Track)
Abstract and authors: (click to expand)

Abstract: Short-term load forecasting (STLF) is fundamental for power system operation, demand response, and also greenhouse gas emission reduction. So far, most deep learning-based STLF techniques require intact data, but many real-world datasets contain missing values due to various reasons, and thus missing imputation using deep learning is actively studied. However, missing imputation and STLF have been considered independently so far. In this paper, we jointly consider missing imputation and STLF and propose a family of autoencoder/LSTM combined models to realize missing-insensitive STLF. Specifically, autoencoder (AE), denoising autoencoder (DAE), and convolutional autoencoder (CAE) are investigated for extracting features, which is directly fed into the input of LSTM. Our results show that three proposed autoencoder/LSTM combined models significantly improve forecasting accuracy compared to the baseline models of deep neural network and LSTM. Furthermore, the proposed CAE/LSTM combined model outperforms all other models for 5%-25% of random missing data.

Authors: Kyungnam Park (Sogang University); Jaeik Jeong (Sogang University); Hongseok Kim (Sogang University)

Power and energy Data presentation and management
ICLR 2020 A Machine Learning Pipeline to Predict Vegetation Health (Papers Track)
Abstract and authors: (click to expand)

Abstract: Agricultural droughts can exacerbate poverty and lead to famine. Timely distribution of disaster relief funds is essential to help minimise the impact of drought. Indices of vegetation health are indicative of higher risk of agricultural drought, but their prediction remains challenging, particularly in Africa. Here, we present an open-source machine learning pipeline for climate-related data. Specifically, we train and analyse a recurrent model to predict pixel-wise vegetation health in Kenya.

Authors: Thomas Lees (University of Oxford); Gabriel Tseng (Okra Solar); Simon Dadson (University of Oxford); Alex Hernández (University of Osnabrück); Clement G. Atzberger (University of Natural Resources and Life Sciences); Steven Reece (University of Oxford)

Disaster prediction, management, and relief Extreme weather events
ICLR 2020 Understanding the dynamics of climate-crucial food choice behaviours using Distributional Semantics (Papers Track)
Abstract and authors: (click to expand)

Abstract: Developed countries must make swift movements toward plant-based diets in order to mitigate climate change and maintain food security. However, researchers currently lack clear insight into the psychological dimensions that influence food choice, which is necessary to encourage the societal adaptation of new diets. In this project, we use Skip-gram word embeddings trained on the ukWaC corpus as a lens to study the implicit mental representations people have of foods. Our data-driven insights expand on findings from traditional, interview-based studies by uncovering implicit mental representations, allowing a better understanding the complex combination of conscious and sub-conscious processes surrounding food choice. In particular, our findings shed light on the pervasiveness of meat as the ‘centre’ of the meal in the UK.

Authors: Claudia Haworth (University of Sheffield); Gabriella Viglioco (University College London)

Societal adaptation Climate change and diet
ICLR 2020 SolarNet: A Deep Learning Framework to Map Solar Plants In China From Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Renewable energy such as solar power is critical to fight the ever more serious climate, how to effectively detect renewable energy has became an important issue for governments. In this paper, we proposed a deep learning framework named SolarNet which is designed to perform semantic segmentation on large scale satellite imagery data to detect solar farms. SolarNet has successfully mapped 439 solar farms in China, covering near 2000 square kilometers, equivalent to the size of whole Shenzhen city or two and a half of New York city. To the best of our knowledge, it is the first time that we used deep learning to reveal the locations and sizes of solar farms in China, which could provide insights for solar power companies, climate finance and markets.

Authors: Xin Hou (WeBank); Biao Wang (WeBank); Wanqi Hu (WeBank); lei yin (WeBank); Anbu Huang (WeBank); Haishan Wu (WeBank)

Power and energy Ecosystems and natural resources
ICLR 2020 Embedding Hard Physical Constraints in Convolutional Neural Networks for 3D Turbulence (Papers Track)
Abstract and authors: (click to expand)

Abstract: Deep learning approaches have shown much promise for climate sciences, especially in dimensionality reduction and compression of large datasets. A major issue in deep learning of climate phenomena, like geophysical turbulence, is the lack of physical guarantees. In this work, we propose a general framework to directly embed the notion of incompressible fluids into Convolutional Neural Networks, for coarse-graining of turbulence. These \textbf{physics-embedded neural networks} leverage interpretable strategies from numerical methods and computational fluid dynamics to enforce physical laws and boundary conditions by taking advantage the mathematical properties of the underlying equations. We demonstrate results on 3D fully-developed turbulence, showing that the \textit{physics-aware inductive bias} drastically improves local conservation of mass, without sacrificing performance according to several other metrics characterizing the fluid flow.

Authors: Arvind T Mohan (Los Alamos National Laboratory); NIcholas Lubbers (Los Alamos National Laboratory); Daniel Livescu (Los Alamos National Laboratory); Misha Chertkov (University of Arizona)

Climate and Earth science Extreme weather events
ICLR 2020 DETECTION OF HOUSING AND AGRICULTURE AREAS ON DRY-RIVERBEDS FOR THE EVALUATION OF RISK BY LANDSLIDES USING LOW-RESOLUTION SATELLITE IMAGERY BASED ON DEEP LEARNING. STUDY ZONE: LIMA, PERU (Papers Track)
Abstract and authors: (click to expand)

Abstract: The expansion of human settlements in Peru has caused risk exposure to landslides. However, this risk could increase because the intensity of the El niño phenomenon will be greater in the coming years, increasing rainfall on the Peruvian coast. In this paper, we present a novel methodology for detecting housing areas and agricultural lands in low-resolution satellite imagery in order to analyze potential risk in case of unexpected landslides. It was developed by creating two datasets from Lima Metropolitana in Peru, one of which is for detecting dry riverbeds and agriculture lands, and the other for classifying housing areas. We applied data augmentation based on geometrical methods and trained architectures based on U-net methods separately and then, overlap the results for risk assessment. We found that there are areas with significant potential risk that have been classified by the Peruvian government as medium or low risk areas. On this basis, it is recommended obtain a dataset with better resolution that can identify how many housing areas will be affected and take the appropriate prevention measures. Further research in post-processing is needed for suppress noise in our results.

Authors: Brian Cerrón (National University of Engineering); Cristopher Bazan (National University of Engineering); Alberto Coronado (National University of Engineering)

Buildings and cities Agriculture, forestry and other land use Climate and Earth science Industry
ICLR 2020 Non-linear interlinkages and key objectives amongst the Paris Agreement and the Sustainable Development Goals (Papers Track)
Abstract and authors: (click to expand)

Abstract: The United Nations' ambitions to combat climate change and prosper human development are manifested in the Paris Agreement and the Sustainable Development Goals (SDGs), respectively. These are inherently inter-linked as progress towards some of these objectives may accelerate or hinder progress towards others. We investigate how these two agendas influence each other by defining networks of 18 nodes, consisting of the 17 SDGs and climate change, for various groupings of countries. We compute a non-linear measure of conditional dependence, the partial distance correlation, given any subset of the remaining 16 variables. These correlations are treated as weights on edges, and weighted eigenvector centralities are calculated to determine the most important nodes. We find that SDG 6, clean water and sanitation, and SDG 4, quality education, are most central across nearly all groupings of countries. In developing regions, SDG 17, partnerships for the goals, is strongly connected to the progress of other objectives in the two agendas whilst, somewhat surprisingly, SDG 8, decent work and economic growth, is not as important in terms of eigenvector centrality.

Authors: Felix Laumann (Imperial College London); Julius von Kügelgen (MPI for Intelligent Systems, Tübingen & University of Cambridge); Mauricio Barahona (Imperial College London)

Policy Data presentation and management Societal adaptation
ICLR 2020 A CONTINUAL LEARNING APPROACH FOR LOCAL LEVEL ENVIRONMENTAL MONITORING IN LOW-RESOURCE SETTINGS (Papers Track)
Abstract and authors: (click to expand)

Abstract: An increasingly important dimension in the quest for mitigation and monitoring of environmental change is the role of citizens. The crowd-based monitoring of local level anthropogenic alterations is essential towards measurable changes in different contributing factors to climate change. With the proliferation of mobile technologies here in the African continent, it is useful to have machine learning based models that are deployed on mobile devices and that can learn continually from streams of data over extended time, possibly pertaining to different tasks of interest. In this paper, we demonstrate the localisation of deforestation indicators using lightweight models and extend to incorporate data about wildfires and smoke detection. The idea is to show the need and potential of continual learning approaches towards building robust models to track local environmental alterations.

Authors: Arijit Patra (University of Oxford)

Agriculture, forestry and other land use Disaster prediction, management, and relief Ecosystems and natural resources Societal adaptation
ICLR 2020 WeatherBench: A benchmark dataset for data-driven weather forecasting (Papers Track) Best Paper Award
Abstract and authors: (click to expand)

Abstract: Accurate weather forecasts are a crucial prerequisite for climate change adaptation. Can these be provided by deep learning? First studies show promise, but the lack of a common dataset and evaluation metrics make inter-comparison between the proposed models difficult. In fact, despite the recent research surge in data-driven weather forecasting, there is currently no standard approach for evaluating the proposed models. Here we introduce WeatherBench, a benchmark dataset for data-driven medium-range weather forecasting. We provide data derived from an archive of assimilated earth observations for the last 40 years that has been processed to facilitate the use in machine learning models. We propose a simple and clear evaluation metric which will enable a direct comparison between different proposed methods. Further, we provide baseline scores from simple linear regression techniques, purely physical forecasting models as well as existing deep learning weather forecasting models. All data and code are made publicly available along with tutorials for getting started. We believe WeatherBench will provide a useful and reproducible way of evaluating data-driven weather forecasting models and we hope that it will accelerate research in this direction.

Authors: Stephan Rasp (Technical University of Munich); Soukayna Mouatadid (University of Toronto); Peter Dueben (European Centre for Medium-Range Weather Forecasts (ECMWF)); Sebastian Scher (Stockholm University); Jonathan Weyn (University of Washington); Nils Thuerey (nils.thuerey@tum.de)

Climate and Earth science Extreme weather events
ICLR 2020 Modeling Cloud Reflectance Fields using Conditional Generative Adversarial Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: We introduce a conditional Generative Adversarial Network (cGAN) approach to generate cloud reflectance fields (CRFs) conditioned on large scale meteorological variables such as sea surface temperature and relative humidity. We show that our trained model can generate realistic CRFs from the corresponding meteorological observations, which represents a step towards a data-driven framework for stochastic cloud parameterization.

Authors: Victor Schmidt (Mila); Mustafa Alghali Muhammed (University of Khartoum); Kris Sankaran (Montreal Institute for Learning Algorithms); Tianle Yuan (NASA); Yoshua Bengio (Mila)

Climate and Earth science
ICLR 2020 SMArtCast: Predicting soil moisture interpolations into the future using Earth observation data in a deep learning framework (Papers Track)
Abstract and authors: (click to expand)

Abstract: Soil moisture is critical component of crop health and monitoring it can enable further actions for increasing yield or preventing catastrophic die off. As climate change increases the likelihood of extreme weather events and reduces the predictability of weather, and non-optimal soil moistures for crops may become more likely. In this work, we use a series of LSTM architectures to analyze measurements of soil moisture and vegetation indices derived from satellite imagery. The system learns to predict the future values of these measurements. These spatially sparse values and indices are used as input features to an interpolation method that infer spatially dense moisture maps at multiple depths for a future time point. This has the potential to provide advance warning for soil moistures that may be inhospitable to crops across an area with limited monitoring capacity.

Authors: Conrad J Foley (Deep Planet); Sagar Vaze (deepplanet.ai); Mohamed El Amine Seddiq (Deep Planet); Aleksei Unagaev (Deep Planet); Natalia Efremova (University of Oxford)

Agriculture, forestry and other land use Ecosystems and natural resources Extreme weather events
ICLR 2020 Prediction of Bayesian Intervals for Tropical Storms (Papers Track)
Abstract and authors: (click to expand)

Abstract: Building on recent research for prediction of hurricane trajectories using recurrent neural networks (RNNs), we have developed improved methods and generalized the approach to predict a confidence interval region of the trajectory utilizing Bayesian methods. Tropical storms are capable of causing severe damage, so accurately predicting their trajectories can bring significant benefits to cities and lives, especially as they grow more intense due to climate change effects. By implementing the Bayesian confidence interval using dropout in an RNN, we improve the actionability of the predictions, for example by estimating the areas to evacuate in the landfall region. We used an RNN to predict the trajectory of the storms at 6-hour intervals. We used latitude, longitude, windspeed, and pressure features from a Statistical Hurricane Intensity Prediction Scheme (SHIPS) dataset of about 500 tropical storms in the Atlantic Ocean. Our results show how neural network dropout values affect our predictions and Bayesian intervals.

Authors: Max Chiswick (Independent); Sam Ganzfried (Ganzfried Research)

Extreme weather events Climate and Earth science
ICLR 2020 MobilityNet: Towards a Public Dataset for Multi-modal Mobility Research (Papers Track)
Abstract and authors: (click to expand)

Abstract: Influencing transportation demand can significantly reduce CO2 emissions. Individual user mobility models are key to influencing demand at the personal and structural levels. Constructing such models is a challenging task that depends on a number of interdependent steps. Progress on this task is hamstrung by the lack of high quality public datasets. We introduce MobilityNet: the first step towards a common ground for multi-modal mobility research. MobilityNet solves the holistic evaluation, privacy preservation and fine grained ground truth problems through the use of artificial trips, control phones, and repeated travel. It currently includes 1080 hours of data from both Android and iOS, representing 16 different travel contexts and 4 different sensing configurations.

Authors: K. Shankari (UC Berkeley); Jonathan Fürst (NEC Laboratories Europe); Mauricio Fadel Argerich (NEC Laboratories Europe); Eleftherios Avramidis (DFKI GmbH); Jesse Zhang (UC Berkeley)

Transportation Buildings and cities
ICLR 2020 Wavelet-Powered Neural Networks for Turbulence (Papers Track)
Abstract and authors: (click to expand)

Abstract: One of the fundamental driving phenomena for climate effects is fluid turbulence in geophysical flows. Modeling these flows and explaining its associated spatio-temporal phenomena are notoriously difficult tasks. Navier-Stokes (NS) equations describe all the details of the fluid motions, but require accounting for unfeasibly many degrees of freedom in the regime of developed turbulence. Model reduction and surrogate modeling of turbulence is a general methodology aiming to circumvent this curse of dimensionality. Originally driven by phenomenological considerations, multiple attempts to model-reduce NS equations got a new boost recently with Deep Learning (DL), trained on the ground truth data, e.g. extracted from high-fidelity Direct Numerical Simulations (DNS). However, early attempts of building NNs to model turbulence has also revealed its lack of interpretability as the most significant shortcoming. In this paper we address the key challenge of devising reduced but, at least partially, interpretable model. We take advantage of the balance between strong mathematical foundations and the physical interpretability of wavelet theory to build a spatio-temporally reduced dynamical map which fuses wavelet based spatial decomposition with spatio-temporal modeling based on Convolutional Long Short Term Memory (C-LSTM) architecture. It is shown that the wavelet-based NN makes progress in scaling to large flows, by reducing computational costs and GPU memory requirements.

Authors: Arvind T Mohan (Los Alamos National Laboratory); Daniel Livescu (Los Alamos National Laboratory); Misha Chertkov (University of Arizona)

Climate and Earth science Data presentation and management
ICLR 2020 Benchmarks for Grid Flexibility Prediction: Enabling Progress and Machine Learning Applications (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Decarbonizing the grid is recognized worldwide as one of the objectives for the next decades. Its success depends on our ability to massively deploy renewable resources, but to fully benefit from those, grid flexibility is needed. In this paper we put forward the design of a benchmark that will allow for the systematic measurement of demand response programs' effectiveness, information that we do not currently have. Furthermore, we explain how the proposed benchmark will facilitate the use of Machine Learning techniques in grid flexibility applications.

Authors: Diego Kiedansk (Telecom ParisTech); Lauren Kuntz (Gaiascope); Daniel Kofman (Telecom ParisTech)

Power and energy Data presentation and management
ICLR 2020 Machine Learning Approaches to Safeguarding Continuous Water Supply in the Arid and Semi-arid Lands of Northern Kenya (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Arid and semi-arid regions (ASALs) in developing countries are heavily affected by the effects of global warming and climate change, leading to adverse climatic conditions such as drought and flooding. This paper explores the problem of fresh-water access in northern Kenya and measures being taken to safeguard water access despite these harsh climatic changes. We present an integrated water management and decision-support platform, eMaji Manager, that we developed and deployed in five ASAL counties in northern Kenya to manage waterpoint access for people and livestock. We then propose innovative machine learning methods for understanding waterpoint usage and repair patterns for sensor-instrumented waterpoints (e.g., boreholes). We explore sub-sequence discriminatory models and recurrent neural networks to predict water-point failures, improve repair response times and ultimately support continuous access to water.

Authors: Fred Otieno (IBM); Timothy Nyota (IBM); Isaac Waweru (IBM); Celia Cintas (IBM Research); Samuel C Maina (IBM Research); William Ogallo (IBM Research); Aisha Walcott-Bryant (IBM Research - Africa)

Climate and Earth science Data presentation and management Societal adaptation
ICLR 2020 Accelerated Data Discovery for Scalable Climate Action (Proposals Track)
Abstract and authors: (click to expand)

Abstract: According to the Intergovernmental Panel on Climate Change (IPCC), the planet must decarbonize by 50% by 2030 in order to keep global warming below 1.5C. This goal calls for a prompt and massive deployment of solutions in all societal sectors - research, governance, finance, commerce, health care, consumption. One challenge for experts and non-experts is access to the rapidly growing body of relevant information, which is currently scattered across many weakly linked domains of expertise. We propose a large-scale, semi-automatic, AI-based discovery system to collect, tag, and semantically index this information. The ultimate goal is a near real-time, partially curated data catalog of global climate information for rapidly scalable climate action.

Authors: Henning Schwabe (Private); Sumeet Sandhu (Elementary IP LLC); Sergy Grebenschikov (Private)

Data presentation and management Climate and Earth science Climate finance Industry Policy
ICLR 2020 YOU FORGOT IT IN THE GENOTYPE, MODELING TOWARDS ADAPTATION OF FOOD CROPS UNDER CLIMATE CHANGE THREAT (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Agriculture is facing the disastrous effects of frequent drastic climate changes. Efforts have increased towards the implementation of inexpensive solutions for crop-yield prediction using publicly available data to prevent severe long-term problems like food scarcity and security, amongst others. Agricultural productiv- ity is intrinsic to the choice of plant species (i.e. cultivar) and represents oppor- tunity cost for farm managers. The currently used cultivars have been artificially selected for productivity at the expense of not being flexible to survive drastic cli- mate changes. Current state-of-the-art machine learning models have modelled holistically all agricultural counterparts (i.e. soil, management, weather, crop cul- tivars etc), albeit, oversimplifying some of the biological features of their culti- vars without taking advantage of their data properties. Specifically, these models oversimplify some biological features like the genotype making them irrelevant or depicting incomplete conclusions since not all of the information from the cul- tivar is incorporated. With the goal of creating new models that perform well on the yield prediction task in unstable weather conditions (e.g. under the effect of climate change), here the authors argue for the importance of incorporating additional biological features inferred from the genotype, like stability, and hy- pothesise that current state-of-the-art models for grain-yield prediction are blind to such features, and hence not applicable in such scenario.

Authors: Olivia Mendivil Ramos (Cold Spring Harbor Laboratory); Linda Petrini (Mila)

Agriculture, forestry and other land use
ICLR 2020 Hurricane Nowcasting with Irregular Time-step using Neural-ODE and Video Prediction (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Fast and accurate prediction of extreme climate events is critical especially in the recent globally warming environment. Considering recent advancements in deep neural networks, it is worthwhile to tackle this problem as data-driven spatio-temporal prediction using neural networks. However, a nontrivial challenge in practice lies in irregular time gaps between which climate observation data are collected due to sensor errors and other issues. This paper proposes an approach for spatio-temporal hurricane prediction that can address this issue of irregular time gaps in collected data with a simple but robust end-to-end model based on Neural Ordinary Differential Equation and video prediction model based on Retrospective Cycle-GAN.

Authors: Sunghyun Park (KAIST); Kangyeol Kim (KAIST); Sookyung Kim (Lawrence Livermore National Laboratory); Joonseok Lee (Google Research); Junsoo Lee (KAIST); Jiwoo Lee (Lawrence Livermore National Laboratory); Jaegul Choo (KAIST)

Extreme weather events Disaster prediction, management, and relief
ICLR 2020 Indigenous Knowledge Aware Drought Monitoring, Forecasting and Prediction Using Deep Learning Techniques (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The general objective of this proposed research work is to design deep learning based hybrid comprehensive framework for drought monitoring, forecasting and prediction using scientific and indigenous knowledge as an integration of connectionist and symbolic AI. In Ethiopia, among all extreme climate events, drought is considered as the most complex phenomenon affecting the country and its impact is also high due to absence of locally grounded intelligent and explainable technology-oriented drought early warning and monitoring system. Thus, studying Ethiopic perspective of drought monitoring and prediction in line with continental and global climate change is vital for drought impact minimization and sustainable development of the country. Moreover, having technology assisted early protective, preventative action is also many times cheaper than the associated response to humanitarian crisis. Accordingly, this proposed work will have different expected outputs, including: drought risk identification, drought monitoring, drought preparedness, drought forecasting, drought mitigation, and post drought best practice recommendation models with interactive visualizations and explanations.

Authors: Kidane W Degefa (Haramaya University)

Disaster prediction, management, and relief Extreme weather events
ICLR 2020 TrueBranch: Metric Learning-based Verification of Forest Conservation Projects (Proposals Track) Best Proposal Award
Abstract and authors: (click to expand)

Abstract: International stakeholders increasingly invest in offsetting carbon emissions, for example, via issuing Payments for Ecosystem Services (PES) to forest conservation projects. Issuing trusted payments requires a transparent monitoring, reporting, and verification (MRV) process of the ecosystem services (e.g., carbon stored in forests). The current MRV process, however, is either too expensive (on-ground inspection of forest) or inaccurate (satellite). Recent works propose low-cost and accurate MRV via automatically determining forest carbon from drone imagery, collected by the landowners. The automation of MRV, however, opens up the possibility that landowners report untruthful drone imagery. To be robust against untruthful reporting, we propose TrueBranch, a metric learning-based algorithm that verifies the truthfulness of drone imagery from forest conservation projects. TrueBranch aims to detect untruthfully reported drone imagery by matching it with public satellite imagery. Preliminary results suggest that nominal distance metrics are not sufficient to reliably detect untruthfully reported imagery. TrueBranch leverages a method from metric learning to create a feature embedding in which truthfully and untruthfully collected imagery is easily distinguishable by distance thresholding.

Authors: Simona Santamaria (ETH Zurich); David Dao (ETH Zurich); Björn Lütjens (MIT); Ce Zhang (ETH)

Agriculture, forestry and other land use Carbon capture and sequestration Climate finance Ecosystems and natural resources
ICLR 2020 Advancing Renewable Electricity Consumption With Reinforcement Learning (Proposals Track)
Abstract and authors: (click to expand)

Abstract: As the share of renewable energy sources in the present electric energy mix rises, their intermittence proves to be the biggest challenge to carbon free electricity generation. To address this challenge, we propose an electricity pricing agent, which sends price signals to the customers and contributes to shifting the customer demand to periods of high renewable energy generation. We propose an implementation of a pricing agent with a reinforcement learning approach where the environment is represented by the customers, the electricity generation utilities and the weather conditions.

Authors: Filip Tolovski (Fraunhofer Heinrich-Hertz-Institut)

Power and energy Data presentation and management Industry
ICLR 2020 Xingu: Explaining critical geospatial predictions in weak supervision for climate finance (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Monitoring, Reporting, and Verification (MRV) play a crucial key role in the decision-making of climate investors, policymakers and conservationists. Remote sensing is commonly used for MRV but practical solutions are constrained by a lack of labels to train machine learning-based downstream tasks. Recent work leverages weak supervision to alleviate the problem of labelled data scarcity. However, the definition of weak supervision signals is limited by the existence of millions of possible heuristic-based feature generation rules. Furthermore, these rules are often difficult to interpret for climate finance and underperform in critical data subsets. We propose Xingu, an interpretable MRV system to explain weak supervision rules using game-theoretic SHAP values for critical model predictions. Moreover, Xingu enables domain experts to collectively design and share labelling functions, thus curating a reusable knowledge base for weak supervision signals.

Authors: David Dao (ETH Zurich); Johannes Rausch (ETH Zurich); Ce Zhang (ETH); Iveta Rott (ETH Zurich)

Climate finance Data presentation and management
ICLR 2020 Towards a unified standards for smart infrastructure datasets (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Development of smart devices and smart home appliances allowed us to harness more data about energy patterns inside households, overtime this amount will increase. There are contributions published to address building datasets, working for objective of energy consumption optimization. Yet there are still factors if included could help in understanding problem better. This proposal tries to annotate missing features that if applied could help in a better understanding energy consumption in smart buildings impact on environment. Second, to have a unified standards that help different solutions to be compared properly.

Authors: Abdulrahman A Ahmed (Cairo University)

Buildings and cities Power and energy
ICLR 2020 MACHINE LEARNING APPLICATIONS THAT CAN HELP PASTORAL COMMUNITIES IN NORTHERN KENYA AND ELSEWHERE ADAPT TO CLIMATE CHANGE (Proposals Track)
Abstract and authors: (click to expand)

Abstract: I propose the use of Machine Learning techniques such as Active Learning(AL) and Transfer Learning(TL) to translate climate information and adaption technique from major Western and Asian languages to thousands of low resource languages in the developing world. Studies have shown that access to information can help people assess the magnitude of the climate change challenge, possible options and those feasible within the relevant context (Nyahunda & Tiri-vangasi, 2019) I endeavor to demonstrate that if this information was available in a language the locals can understand, it would result in local empowerment and as a result inspire action.

Authors: Jefferson Sankara (Lori Systems)

Societal adaptation
ICLR 2020 Nutrient demand, Risk and Climate change: Evidence from historical rice yield trials in India (Proposals Track)
Abstract and authors: (click to expand)

Abstract: We use data from historical agronomic fertilizer trials to identify the effect of climate change on the average rice yield and the yield variability in India. The contribution of this paper is three folds: firstly, it has a methodological contribution by modelling the input conditional yield densities using a stochastic production structure for a developing country like India. In doing so, it predicts and measure the effects of climate change on rice grown in tropical regions; secondly,it estimates the nutrient demand and its link with the climate change; thirdly, by modelling the yield uncertainty, it characterizes the risk and role for insurance as a tool for tackling climate change in the developing countries.

Authors: Sandip K Agarwal (IISER Bhopal)

Agriculture, forestry and other land use Policy
ICLR 2020 USING MACHINE LEARNING TO ANALYZE CLIMATE CHANGE TECHNOLOGY TRANSFER (CCTT) (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The objective of the present paper is to review the climate change technology transfer. This research proposes a method for analysing CCTT using patent analysis and topic modelling. A collection of climate change mitigation related technology (CCMT) patents from patent databases would be used as input to group patents in several relevant topics for climate change mitigation using the topic exploration model in this research. The research questions we want to address are: how have the patenting activities changed over time in CCMT patents? And who are the technological leaders? The investigation of these questions can offer the technological landscape in climate change-related technologies at the international level. We propose a hybrid Latent Dirichlet Allocation (LDA) approach for topic modelling and identification of relationships between terms and topics related to CCMT, enabling better visualizations of underlying intellectual property dynamics. Further, we propose predictive modelling for CCTT and competitor analysis to identify and rank countries with a similar patent landscape. The projected results are expected to facilitate the transfer process associated with existing and emerging climate change technologies and improve technology cooperation between governments.

Authors: Shruti Kulkarni (Indian Institute of Science (IISc))

Climate finance Data presentation and management Societal adaptation
ICLR 2020 Using ML to close the vocabulary gap in the context of environment and climate change in Chichewa (Proposals Track)
Abstract and authors: (click to expand)

Abstract: In the west, alienation from nature and deteriorating opportunities to experience it, have led educators to incorporate educational programs in schools, to bring pupils in contact with nature and to enhance their understanding of issues related to the environment and its protection. In Africa, and in Malawi, where most people engage in agriculture, and spend most of their time in the 'outdoors', alienation from nature is happening too, although in different ways. Large portion of the indigenous vocabulary and knowledge remains unknown or is slowly disappearing, and there is a need to build a glossary of terms regarding environment and climate change in the vernacular to improve the dialog regarding climate change and environmental protection.. We believe that ML has a role to play in closing the ‘vocabulary gap’ of terms and concepts regarding the environment and climate change that exists in Chichewa and other Malawian languages by helping to creating a visual dictionary of key terms used to describe the environment and explain the issues involved in climate change and their meaning. Chichewa is a descriptive language, one English term may be translated using several words. Thus, the task is not to detect just literal translations, but also translations by means of ‘descriptions’ and illustrations and thus extract correspondence between terms and definitions and to measure how appropriate a term is to convey the meaning intended. As part of this project, ML can be used to identify ‘loanword patterns’, which may be useful in understanding the transmission of cultural items.

Authors: Amelia Taylor (University of Malawi, The Polytechnic)

Ecosystems and natural resources Agriculture, forestry and other land use Climate and Earth science
NeurIPS 2019 Warm-Starting AC Optimal Power Flow with Graph Neural Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: Efficient control of power grids is important both for efficiently managing genera- tors and to prolong longevity of components. However, that problem is NP-hard and linear approximations are necessary. The deployment of machine learning methods is hampered by the need to guarantee solutions. We propose to use Graph Neural Networks (GNNs) to model a power grid and produce an initial solution used to warm-start the optimization. This allows us to achieve the best of both worlds: Fast convergence and guaranteed solutions. On a synthetic power grid modelling Texas, we achieve a mean speedup by a factor of 2.8. This allows us to dispense with linear approximation, leads to more efficient generator dispatch, and can potentially save hundreds of megatons of CO2 -equivalent.

Authors: Frederik Diehl (fortiss)

Power and energy
NeurIPS 2019 Quantifying Urban Canopy Cover with Deep Convolutional Neural Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: Urban canopy cover is important to mitigate the impact of climate change. Yet, existing quantification of urban greenery is either manual and not scalable, or use traditional computer vision methods that are inaccurate. We train deep convolutional neural networks (DCNNs) on datasets used for self-driving cars to estimate urban greenery instead, and find that our semantic segmentation and direct end-to-end estimation method are more accurate and scalable, reducing mean absolute error of estimating the Green View Index (GVI) metric from 10.1% to 4.67%. With the revised DCNN methods, the Treepedia project was able to scale and analyze canopy cover in 22 cities internationally, sparking interest and action in public policy and research fields.

Authors: Bill Cai (Massachusetts Institute of Technology); Xiaojiang Li (Temple University); Carlo Ratti (Massachusetts Institute of Technology )

Buildings and cities Agriculture, forestry and other land use
NeurIPS 2019 Using LSTMs for climate change assessment studies on droughts and floods (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change affects occurrences of floods and droughts worldwide. However, predicting climate impacts over individual watersheds is difficult, primarily because accurate hydrological forecasts require models that are calibrated to past data. In this work we present a large-scale LSTM-based modeling approach that - by training on large data sets - learns a diversity of hydrological behaviors. Previous work shows that this model is more accurate than current state-of-the-art models, even when the LSTM-based approach operates out-of-sample and the latter in-sample. In this work, we show how this model can assess the sensitivity of the underlying systems with regard to extreme (high and low) flows in individual watersheds over the continental US.

Authors: Frederik Kratzert (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Daniel Klotz (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Johannes Brandstetter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria); Pieter-Jan Hoedt (Johannes Kepler University Linz); Grey Nearing (Department of Geological Sciences, University of Alabama, Tuscaloosa, AL United States); Sepp Hochreiter (LIT AI Lab, Institute for Machine Learning, Johannes Kepler University Linz, Austria)

Climate and Earth science
NeurIPS 2019 Learning to Focus and Track Hurricanes (Papers Track)
Abstract and authors: (click to expand)

Abstract: This paper tackles the task of extreme climate event tracking. We propose a simple but robust end-to-end model based on multi-layered ConvLSTMs, suitable for climate event tracking. It first learns to imprint the location and the appearance of the target at the first frame in an auto-encoding fashion. Next, the learned feature is fed to the tracking module to track the target in subsequent time frames. To tackle the data shortage problem, we propose data augmentation based on conditional generative adversarial networks. Extensive experiments show that the proposed framework significantly improves tracking performance of a hurricane tracking task over several state-of-the-art methods.

Authors: Sookyung Kim (Lawrence Livermore National Laboratory); Sunghyun Park (Korea University); Sunghyo Chung (Kakao Corp.); Joonseok Lee (Google Research); Jaegul Choo (Korea University); Mr Prabhat (Lawrence Berkeley National Laboratory); Yunsung Lee (Korea University)

Extreme weather events Climate and Earth science
NeurIPS 2019 DeepWind: Weakly Supervised Localization of Wind Turbines in Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wind energy is being adopted at an unprecedented rate. The locations of wind energy sources, however, are largely undocumented and expensive to curate manually, which significantly impedes their integration into power systems. Towards the goal of mapping global wind energy infrastructure, we develop deep learning models to automatically localize wind turbines in satellite imagery. Using only image-level supervision, we experiment with several different weakly supervised convolutional neural networks to detect the presence and locations of wind turbines. Our best model, which we call DeepWind, achieves an average precision of 0.866 on the test set. DeepWind demonstrates the potential of automated approaches for identifying wind turbine locations using satellite imagery, ultimately assisting with the management and adoption of wind energy worldwide.

Authors: Sharon Zhou (Stanford University); Jeremy Irvin (Stanford); Zhecheng Wang (Stanford University); Ram Rajagopal (Stanford University); Andrew Ng (Stanford U.); Eva Zhang (Stanford University); Will Deaderick (Stanford University); Jabs Aljubran (Stanford University)

Power and energy
NeurIPS 2019 Streamflow Prediction with Limited Spatially-Distributed Input Data (Papers Track)
Abstract and authors: (click to expand)

Abstract: Climate change causes more frequent and extreme weather phenomena across the globe. Accurate streamflow prediction allows for proactive and mitigative action in some of these events. As a first step towards models that predict streamflow in watersheds for which we lack ground truth measurements, we explore models that work on spatially-distributed input data. In such a scenario, input variables are more difficult to acquire, and thus models have access to limited training data. We present a case study focusing on Lake Erie, where we find that tree-based models can yield more accurate predictions than both neural and physically-based models.

Authors: Martin Gauch (University of Waterloo); Juliane Mai (University of Waterloo); Shervan Gharari (University of Saskatchewan); Jimmy Lin (University of Waterloo)

Climate and Earth science Disaster prediction, management, and relief Extreme weather events
NeurIPS 2019 Establishing an Evaluation Metric to Quantify Climate Change Image Realism (Papers Track)
Abstract and authors: (click to expand)

Abstract: With success on controlled tasks, generative models are being increasingly applied to humanitarian applications. In this paper, we focus on the evaluation of a conditional generative model that illustrates the consequences of climate change-induced flooding to encourage public interest and awareness on the issue. Because metrics for comparing the realism of different modes in a conditional generative model do not exist, we propose several automated and human-based methods for evaluation. To do this, we adapt several existing metrics, and assess the automated metrics against gold standard human evaluation. We find that using Frechet Inception Distance (FID) with embeddings from an intermediary Inception-V3 layer that precedes the auxiliary classifier produces results most correlated with human realism. While insufficient alone to establish a human-correlated automatic evaluation metric, we believe this work begins to bridge the gap between human and automated generative evaluation procedures.

Authors: Sharon Zhou (Stanford University); Sasha Luccioni (Mila); Gautier Cosne (Mila); Michael Bernstein (Stanford University); Yoshua Bengio (Mila)

Data presentation and management Societal adaptation
NeurIPS 2019 Energy Usage Reports: Environmental awareness as part of algorithmic accountability (Papers Track)
Abstract and authors: (click to expand)

Abstract: The carbon footprint of algorithms must be measured and transparently reported so computer scientists can take an honest and active role in environmental sustainability. In this paper, we take analyses usually applied at the industrial level and make them accessible for individual computer science researchers with an easy-to-use Python package. Localizing to the energy mixture of the electrical power grid, we make the conversion from energy usage to CO2 emissions, in addition to contextualizing these results with more human-understandable benchmarks such as automobile miles driven. We also include comparisons with energy mixtures employed in electrical grids around the world. We propose including these automatically-generated Energy Usage Reports as part of standard algorithmic accountability practices, and demonstrate the use of these reports as part of model-choice in a machine learning context.

Authors: Kadan Lottick (Haverford College); Silvia Susai (Haverford College); Sorelle Friedler (Haverford College); Jonathan Wilson (Haverford College)

Energy usage and CO2 emissions measurement and reporting Environmental impacts of computing
NeurIPS 2019 Natural Language Generation for Operations and Maintenance in Wind Turbines (Papers Track)
Abstract and authors: (click to expand)

Abstract: Wind energy is one of the fastest-growing sustainable energy sources in the world but relies crucially on efficient and effective operations and maintenance to generate sufficient amounts of energy and reduce downtime of wind turbines and associated costs. Machine learning has been applied to predict faults in wind turbines, but these predictions have not been supported by suggestions on how to avert and fix occurring errors. In this paper, we present a data-to-text generation system utilising transformers to produce event descriptions of turbine faults from SCADA data capturing the operational status of turbines, and proposing maintenance strategies. Experiments show that our model learns reasonable feature representations that correspond to expert judgements. We anticipate that in making a contribution to the reliability of wind energy, we can encourage more organisations to switch to sustainable energy sources and help combat climate change.

Authors: Joyjit Chatterjee (University of Hull); Nina Dethlefs (University of Hull)

Power and energy Ecosystems and natural resources
NeurIPS 2019 Make Thunderbolts Less Frightening — Predicting Extreme Weather Using Deep Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Forecasting severe weather conditions is still a very challenging and computationally expensive task due to the enormous amount of data and the complexity of the underlying physics. Machine learning approaches and especially deep learning have however shown huge improvements in many research areas dealing with large datasets in recent years. In this work, we tackle one specific sub-problem of weather forecasting, namely the prediction of thunderstorms and lightning. We propose the use of a convolutional neural network architecture inspired by UNet++ and ResNet to predict thunderstorms as a binary classification problem based on satellite images and lightnings recorded in the past. We achieve a probability of detection of more than 94% for lightnings within the next 15 minutes while at the same time minimizing the false alarm ratio compared to previous approaches.

Authors: Christian Schön (Saarland Informatics Campus); Jens Dittrich (Saarland University)

Extreme weather events Climate and Earth science
NeurIPS 2019 Cumulo: A Dataset for Learning Cloud Classes (Papers Track) Best Paper Award
Abstract and authors: (click to expand)

Abstract: One of the greatest sources of uncertainty in future climate projections comes from limitations in modelling clouds and in understanding how different cloud types interact with the climate system. A key first step in reducing this uncertainty is to accurately classify cloud types at high spatial and temporal resolution. In this paper, we introduce Cumulo, a benchmark dataset for training and evaluating global cloud classification models. It consists of one year of 1km resolution MODIS hyperspectral imagery merged with pixel-width `tracks' of CloudSat cloud labels. Bringing these complementary datasets together is a crucial first step, enabling the Machine-Learning community to develop innovative new techniques which could greatly benefit the climate community. To showcase Cumulo, we provide baseline performance analysis using an invertible flow generative model (IResNet), which further allows us to discover new sub-classes for a given cloud class by exploring the latent space.

Authors: Valentina Zantedeschi (Jean Monnet University); Fabrizio Falasca (Georgia Institute of Technology); Alyson Douglas (University of Wisconsin Madison); Richard Strange (University of Oxford); Matt Kusner (University College London); Duncan Watson-Parris (University of Oxford)

Climate and Earth science Data presentation and management
NeurIPS 2019 Targeting Buildings for Energy Retrofit Using Recurrent Neural Networks with Multivariate Time Series (Papers Track)
Abstract and authors: (click to expand)

Abstract: The existing building stock accounts for over 30% of global carbon emissions and energy demand. Effective building retrofits are therefore vital in reducing global emissions. Current methods for building energy assessment typically rely on walk-throughs, surveys or the collection of in-situ measurements, none of which are scalable or cost effective. Supervised machine learning methods have the potential to overcome these issues, but their application to retrofit analysis has been limited. This paper serves as a novel showcase for how multivariate time series analysis with Gated Recurrent Units can be applied to targeted retrofit analysis via two case studies: (1) classification of building heating system type and (2) prediction of building envelope thermal properties.

Authors: Gaby Baasch (University of Victoria)

Buildings and cities
NeurIPS 2019 Coupling Oceanic Observation Systems to Study Mesoscale Ocean Dynamics (Papers Track)
Abstract and authors: (click to expand)

Abstract: Understanding local currents in the North Atlantic region of the ocean is a key part of modelling heat transfer and global climate patterns. Satellites provide a surface signature of the temperature of the ocean with a high horizontal resolution while in situ autonomous probes supply high vertical resolution, but horizontally sparse, knowledge of the ocean interior thermal structure. The objective of this paper is to develop a methodology to combine these complementary ocean observing systems measurements to obtain a three-dimensional time series of ocean temperatures with high horizontal and vertical resolution. Within an observation-driven framework, we investigate the extent to which mesoscale ocean dynamics in the North Atlantic region may be decomposed into a mixture of dynamical modes, characterized by different local regressions between Sea Surface Temperature (SST), Sea Level Anomalies (SLA) and Vertical Temperature fields. Ultimately we propose a Latent-class regression method to improve prediction of vertical ocean temperature.

Authors: Gautier Cosne (Mila); Pierre Tandeo (IMT-Atlantique); Guillaume Maze (Ifremer)

Climate and Earth science Data presentation and management
NeurIPS 2019 Background noise trends and the detection of calving events in a glacial fjord (Papers Track)
Abstract and authors: (click to expand)

Abstract: Predicting future sea levels depends on accurately estimating the rate at which ice sheets deliver fresh water and ice to the oceans, and projecting rates of iceberg calving will be improved with more observations of calving events. The background noise environment in a glacial fjord was measured and the data were analyzed. This paper includes an analysis of methods useful for evaluating background noise. It explores the utility of spectral probability density in evaluating background noise characteristics in the frequency domain, models probability density functions of spectral levels and introduces a parameter \(\sigma_T\) that quantifies the character of noise in frequency bands of interest. It also explores the utility of k-medoids clustering as a pre-sorting method to inform the selection of features on which to base the training of more complex algorithms.

Authors: Dara Farrell (Graduate of University of Washington)

Climate and Earth science
NeurIPS 2019 Reducing Inefficiency in Carbon Auctions with Imperfect Competition (Papers Track)
Abstract and authors: (click to expand)

Abstract: We study auctions for carbon licenses, a policy tool used to control the social cost of pollution. Each identical license grants the right to produce a unit of pollution. Each buyer (i.e., firm that pollutes during the manufacturing process) enjoys a decreasing marginal value for licenses, but society suffers an increasing marginal cost for each license distributed. The seller (i.e., the government) can choose a number of licenses to auction, and wishes to maximize societal welfare: the total economic value of the buyers minus the social cost. Motivated by emission license markets deployed in practice, we focus on uniform price auctions with a price floor and/or price ceiling. The seller has distributional information about the market, and their goal is to tune the auction parameters to maximize expected welfare. The target benchmark is the maximum expected welfare achievable by any such auction under truth-telling behavior. Unfortunately, the uniform price auction is not truthful, and strategic behavior can significantly reduce (even below zero) the welfare of a given auction configuration. We use tools from theoretical computer science and algorithmic game theory to address the strategic vulnerabilities of these auctions. We describe a subclass of "safe-price" auctions for which the welfare at any Bayes-Nash equilibrium will approximate the welfare under truth-telling behavior. We then show that the better of a safe-price auction, or a truthful auction that allocates licenses to only a single buyer, will approximate the target benchmark. In particular, we show how to choose a number of licenses and a price floor so that the worst-case welfare, at any equilibrium, is a constant approximation to the best achievable welfare under truth-telling after excluding the welfare contribution of a single buyer. This provides a concrete recommendation for how to set the auction parameters in practice in order to achieve guarantees, even in the face of strategic participants.

Authors: Kira Goldner (Columbia University); Nicole Immorlica (Microsoft Research); Brendan Lucier (Microsoft Research New England)

Carbon capture and sequestration
NeurIPS 2019 Reduction of the Optimal Power Flow Problem through Meta-Optimization (Papers Track)
Abstract and authors: (click to expand)

Abstract: We introduce a method for solving Optimal Power Flow (OPF) using meta-optimization, which can substantially reduce solution times. A pre-trained classifier that predicts the binding constraints of the system is used to generate an initial reduced OPF problem, defined by removing the predicted non-binding constraints. Through an iterative procedure, this initial set of constraints is then ex- tended by those constraints that are violated but not represented in the reduced OPF, guaranteeing an optimal solution of the original OPF problem with the full set of constraints. The classifier is trained using a meta-loss objective, defined by the computational cost of the series of reduced OPF problems.

Authors: Letif Mones (Invenia Labs); Alex Robson (Invenia Labs); Mahdi Jamei (Invenia Labs); Cozmin Ududec (Invenia Labs)

Power and energy Optimization
NeurIPS 2019 Human-Machine Collaboration for Fast Land Cover Mapping (Papers Track)
Abstract and authors: (click to expand)

Abstract: We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predictions on unlabeled data, choose which data to label, and see the resulting effect on the model's predictions. This bi-directional feedback loop allows humans to learn how the model responds to new data. Our hypothesis is that this rich feedback allows human labelers to create mental models that enable them to better choose which biases to introduce to the model. We implement this framework for fine-tuning high-resolution land cover segmentation models and evaluate it against traditional active learning based approaches. More specifically, we fine-tune a deep neural network -- trained to segment high-resolution aerial imagery into different land cover classes in Maryland, USA -- to a new spatial area in New York, USA. We find that the tight loop turns the algorithm and the human operator into a hybrid system that can produce land cover maps of large areas more efficiently than the traditional workflows.

Authors: Caleb Robinson (Georgia Institute of Technology); Anthony Ortiz (University of Texas at El Paso); Nikolay Malkin (Yale University); Blake Elias (Microsoft); Andi Peng (Microsoft); Dan Morris (Microsoft); Bistra Dilkina (University of Southern California); Nebojsa Jojic (Microsoft Research)

Agriculture, forestry and other land use Ecosystems and natural resources
NeurIPS 2019 A User Study of Perceived Carbon Footprint (Papers Track)
Abstract and authors: (click to expand)

Abstract: We propose a statistical model to understand people’s perception of their carbon footprint. Driven by the observation that few people think of CO2 impact in absolute terms, we design a system to probe people’s perception from simple pairwise comparisons of the relative carbon footprint of their actions. The formulation of the model enables us to take an active-learning approach to selecting the pairs of actions that are maximally informative about the model parameters. We define a set of 18 actions and collect a dataset of 2183 comparisons from 176 users on a university campus. The early results reveal promising directions to improve climate communication and enhance climate mitigation.

Authors: Victor Kristof (EPFL); Valentin Quelquejay-Leclere (EPFL); Robin Zbinden (EPFL); Lucas Maystre (Spotify); Matthias Grossglauser (École Polytechnique Fédérale de Lausanne (EPFL)); Patrick Thiran (EPFL)

Societal adaptation
NeurIPS 2019 Design, Benchmarking and Graphical Lasso based Explainability Analysis of an Energy Game-Theoretic Framework (Papers Track)
Abstract and authors: (click to expand)

Abstract: Energy use in buildings account for approximately half of global electricity consumption and a significant amount of CO2 emissions. The occupants of a building typically lack the independent motivation necessary to optimize their energy usage. In this paper, we propose a novel energy game-theoretic framework for smart building which incorporates human-in-the-loop modeling by creating an interface to allow interaction with occupants and potentially incentivize energy efficient behavior. We present open-sourced dataset and benchmarked results for forecasting of energy resource usage patterns by leveraging classical machine learning and deep learning methods including deep bi-directional recurrent neural networks. Finally, we use graphical lasso to demonstrate the explainable nature on human decision making towards energy usage inherent in the dataset.

Authors: Hari Prasanna Das (UC Berkeley ); Ioannis C. Konstantakopoulos (UC Berkeley); Aummul Baneen Manasawala (UC Berkeley); Tanya Veeravalli (UC Berkeley); Huihan Liu (UC Berkeley ); Costas J. Spanos (University of California at Berkeley)

Buildings and cities Power and energy
NeurIPS 2019 Predicting ice flow using machine learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Though machine learning has achieved notable success in modeling sequential and spatial data for speech recognition and in computer vision, applications to remote sensing and climate science problems are seldom considered. In this paper, we demonstrate techniques from unsupervised learning of future video frame prediction, to increase the accuracy of ice flow tracking in multi-spectral satellite images. As the volume of cryosphere data increases in coming years, this is an interesting and important opportunity for machine learning to address a global challenge for climate change, risk management from floods, and conserving freshwater resources. Future frame prediction of ice melt and tracking the optical flow of ice dynamics presents modeling difficulties, due to uncertainties in global temperature increase, changing precipitation patterns, occlusion from cloud cover, rapid melting and glacier retreat due to black carbon aerosol deposition, from wildfires or human fossil emissions. We show the adversarial learning method helps improve the accuracy of tracking the optical flow of ice dynamics compared to existing methods in climate science. We present a dataset, IceNet, to encourage machine learning research and to help facilitate further applications in the areas of cryospheric science and climate change.

Authors: Yimeng Min (Mila); Surya Karthik Mukkavilli (Mila); Yoshua Bengio (Mila)

Climate and Earth science
NeurIPS 2019 DeepClimGAN: A High-Resolution Climate Data Generator (Papers Track)
Abstract and authors: (click to expand)

Abstract: Earth system models (ESMs), which simulate the physics and chemistry of the global atmosphere, land, and ocean, are often used to generate future projections of climate change scenarios. These models are far too computationally intensive to run repeatedly, but limited sets of runs are insufficient for some important applications, like adequately sampling distribution tails to characterize extreme events. As a compromise, emulators are substantially less expensive but may not have all of the complexity of an ESM. Here we demonstrate the use of a conditional generative adversarial network (GAN) to act as an ESM emulator. In doing so, we gain the ability to produce daily weather data that is consistent with what ESM might output over any chosen scenario. In particular, the GAN is aimed at representing a joint probability distribution over space, time, and climate variables, enabling the study of correlated extreme events, such as floods, droughts, or heatwaves.

Authors: Alexandra Puchko (Western Washington University); Brian Hutchinson (Western Washington University); Robert Link (Joint Global Change Research Institute)

Climate and Earth science Extreme weather events
NeurIPS 2019 Quantifying the Carbon Emissions of Machine Learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: From an environmental standpoint, there are a few crucial aspects of training a neural network that have a major impact on the quantity of carbon that it emits. These factors include: the location of the server used for training and the energy grid that it uses, the length of the training procedure, and even the make and model of hardware on which the training takes place. In order to approximate these emissions, we present our Machine Learning Emissions Calculator, a tool for our community to better understand the environmental impact of training ML models. We accompany this tool with an explanation of the factors cited above, as well as concrete actions that individual practitioners as well as organizations can take to mitigate their carbon emissions.

Authors: Sasha Luccioni (Mila); Victor Schmidt (Mila); Alexandre Lacoste (Element AI); Thomas Dandres (Polytechnique Montreal)

Societal adaptation Power and energy
NeurIPS 2019 Measuring Impact of Climate Change on Tree Species: analysis of JSDM on FIA data (Papers Track) Honorable Mention
Abstract and authors: (click to expand)

Abstract: One of the first beings affected by changes in the climate are trees, one of our most vital resources. In this study tree species interaction and the response to climate in different ecological environments is observed by applying a joint species distribution model to different ecological domains in the United States. Joint species distribution models are useful to learn inter-species relationships and species response to the environment. The climates’ impact on the tree species is measured through species abundance in an area. We compare the model’s performance across all ecological domains and study the sensitivity of the climate variables. With the prediction of abundances, tree species populations can be predicted in the future and measure the impact of climate change on tree populations.

Authors: Hyun Choi (University of Florida); Sergio Marconi (University of Florida); Ali Sadeghian (University of Florida); Ethan White (University of Florida); Daisy Zhe Wang (Univeresity of Florida)

Agriculture, forestry and other land use Climate and Earth science
NeurIPS 2019 A Global Census of Solar Facilities Using Deep Learning and Remote Sensing (Papers Track) Honorable Mention
Abstract and authors: (click to expand)

Abstract: We present a comprehensive global census of solar power facilities using deep learning and remote sensing. We search imagery from the Airbus SPOT 6/7 and European Space Agency Sentinel-2 satellites covering more than 48% of earth’s land-surface using a combination of deep-learning models, image processing, and hand-verification. We locate solar facilities and measure their footprints and installation dates. The resulting dataset of 68,797 facilities has an estimated generating capacity of 209 GW; 78% of this capacity was not previously reported in public databases. These asset-level data are critical for understanding energy infrastructure, evaluate climate risk, and efficiently use intermittent solar energy - ultimately enabling the transition to a predominantly renewable energy system.

Authors: Lucas Kruitwagen (University of Oxford); Kyle Story (Descartes Labs); Johannes Friedrich (World Resource Institute); Sam Skillman (Descartes Labs); Cameron Hepburn (University of Oxford)

Power and energy Data presentation and management
NeurIPS 2019 Machine Learning for Precipitation Nowcasting from Radar Images (Papers Track)
Abstract and authors: (click to expand)

Abstract: High-resolution nowcasting is an essential tool needed for effective adaptation to climate change, particularly for extreme weather. As Deep Learning (DL) techniques have shown dramatic promise in many domains, including the geosciences, we present an application of DL to the problem of precipitation nowcasting, i.e., high-resolution (1 km x 1 km) short-term (1 hour) predictions of precipitation. We treat forecasting as an image-to-image translation problem and leverage the power of the ubiquitous UNET convolutional neural network. We find this performs favorably when compared to three commonly used models: optical flow, persistence and NOAA's numerical one-hour HRRR nowcasting prediction.

Authors: Shreya Agrawal (Google); Luke Barrington (Google); Carla Bromberg (Google); John Burge (Google); Cenk Gazen (Google); Jason Hickey (Google)

Climate and Earth science Extreme weather events
NeurIPS 2019 Enhancing Stratospheric Weather Analyses and Forecasts by Deploying Sensors from a Weather Balloon (Papers Track)
Abstract and authors: (click to expand)

Abstract: The ability to analyze and forecast stratospheric weather conditions is fundamental to addressing climate change. However, our capacity to collect data in the stratosphere is limited by sparsely deployed weather balloons. We propose a framework to collect stratospheric data by releasing a contrail of tiny sensor devices as a weather balloon ascends. The key machine learning challenges are determining when and how to deploy a finite collection of sensors to produce a useful data set. We decide when to release sensors by modeling the deviation of a forecast from actual stratospheric conditions as a Gaussian process. We then implement a novel hardware system that is capable of optimally releasing sensors from a rising weather balloon. We show that this data engineering framework is effective through real weather balloon flights, as well as simulations.

Authors: Kiwan Maeng (Carnegie Mellon University); Iskender Kushan (Microsoft); Brandon Lucia (Carnegie Mellon University); Ashish Kapoor (Microsoft)

Climate and Earth science
NeurIPS 2019 Automatic data cleaning via tensor factorization for large urban environmental sensor networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: The US Environmental Protection Agency identifies that urban heat islands can negatively impact a community’s environment and quality of life. Using low cost urban sensing networks, it is possible to measure the impacts of mitigation strategies at a fine-grained scale, informing context-aware policies and infrastructure design. However, fine-grained city-scale data analysis is complicated by tedious data cleaning including removing outliers and imputing missing data. To address the challenge of data cleaning, this article introduces a robust low-rank tensor factorization method to automatically correct anomalies and impute missing entries for high-dimensional urban environmental datasets. We validate the method on a synthetically degraded National Oceanic and Atmospheric Administration temperature dataset, with a recovery error of 4%, and apply it to the Array of Things city-scale sensor network in Chicago, IL.

Authors: Yue Hu (Vanderbilt University); Yanbing Wang (Vanderbilt University); Canwen Jiao (Vanderbilt University); Rajesh Sankaran (Argonne National Lab); Charles Catlett (Argonne National Lab); Daniel Work (Vanderbilt University)

Buildings and cities
NeurIPS 2019 Identify Solar Panels in Low Resolution Satellite Imagery with Siamese Architecture and Cross-Correlation (Papers Track)
Abstract and authors: (click to expand)

Abstract: Understanding solar adoption trends and their underlying dynamics requires a comprehensive and granular time-series solar installation database which is unavailable today and expensive to create manually. To this end, we leverage a deep siamese network that automatically identifies solar panels in historical low-resolution (LR) satellite images by comparing the target image with its high-resolution exemplar at the same location. To resolve the potential displacement between solar panels in the exemplar image and that in the target image, we use a cross-correlation module to collate the spatial features learned from each input and measure their similarity. Experimental result shows that our model significantly outperforms baseline methods on a dataset of historical LR images collected in California.

Authors: Zhengcheng Wang (Tsinghua University); Zhecheng Wang (Stanford University); Arun Majumdar (Stanford University); Ram Rajagopal (Stanford University)

Power and energy
NeurIPS 2019 VideoGasNet: Deep Learning for Natural Gas Methane Leak Classification Using An Infrared Camera (Papers Track)
Abstract and authors: (click to expand)

Abstract: Mitigating methane leakage from the natural gas system have become an increasing concern for climate change. Efficacious methane leak detection and classification can make the mitigation process more efficient and cost effective. Optical gas imaging is widely used for the purpose of leak detection, but it cannot directly provide detection results and leak sizes. Few studies have examined the possibility of leak classification using videos taken by the infrared camera (IR), an optical gas imaging device. In this study, we consider the leak classification problem as a video classification problem and investigated the application of deep learning techniques in methane leak detection. Firstly we collected the first methane leak video dataset - GasVid, which has ~1 M frames of labeled videos of methane leaks from different leaking equipment, covering a wide range of leak sizes (5.3-2051.6 g\ce{CH4}/h) and imaging distances (4.6-15.6 m). Secondly, we studied three deep learning algorithms, including 2D Convolutional Neural Networks (CNN) model, 3D CNN and the Convolutional Long Short Term Memory (ConvLSTM). We find that 3D CNN is the most outstanding and robust architecture, which was named VideoGasNet. The leak-non-leak detection accuracy can reach 100%, and the highest small-medium-large classification accuracy is 78.2% with our 3D CNN network. In summary, VideoGasNet greatly extends the capabilities of IR camera-based leak monitoring system from leak detection only to automated leak classification with high accuracy and fast processing speed, significant mitigation efficiency.

Authors: Jingfan Wang (Stanford University)

Climate and Earth science Ecosystems and natural resources
NeurIPS 2019 Detecting Avalanche Deposits using Variational Autoencoder on Sentinel-1 Satellite Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Avalanche monitoring is a crucial safety challenge, especially in a changing climate. Remote sensing of avalanche deposits can be very useful to identify avalanche risk zones and time periods, which can in turn provide insights about the effects of climate change. In this work, we use Sentinel-1 SAR (synthetic aperture radar) data on the French Alps for the exceptional winter of 2017-18, with the goal of automatically detecting avalanche deposits. We address our problem with an unsupervised learning technique. We treat an avalanche as a rare event, or an anomaly, and we learn a variational autoencoder, in order to isolate the anomaly. We then evaluate our method on labeled test data, using an independent in-situ avalanche inventory as ground truth. Our empirical results show that our unsupervised method obtains comparable performance to a recent supervised learning approach that trained a convolutional neural network on an artificially balanced version of the same SAR data set along with the corresponding ground-truth labels. Our unsupervised approach outperforms the standard CNN in terms of balanced accuracy (63% as compared to 55%). This is a significant improvement, as it allows our method to be used in-situ by climate scientists, where the data is always very unbalanced (< 2% positives). This is the first application of unsupervised deep learning to detect avalanche deposits.

Authors: Saumya Sinha (University of Colorado, Boulder); Sophie Giffard-Roisin (University of Colorado Boulder); Fatima Karbou (Meteo France); Michael Deschatres (Irstea); Nicolas Eckert (Irstea); Anna Karas (Meteo France); Cécile Coléou (Meteo France); Claire Monteleoni (University of Colorado Boulder)

Extreme weather events Climate and Earth science
NeurIPS 2019 Fine-Grained Distribution Grid Mapping Using Street View Imagery (Papers Track)
Abstract and authors: (click to expand)

Abstract: Fine-grained distribution grid mapping is essential for power system operation and planning in the aspects of renewable energy integration, vegetation management, and risk assessment. However, currently such information can be inaccurate, outdated, or incomplete. Existing grid topology reconstruction methods heavily rely on various assumptions and measurement data that is not widely available. To bridge this gap, we propose a machine-learning-based method that automatically detects, localizes, and estimates the interconnection of distribution power lines and utility poles using readily-available street views in the upward perspective. We demonstrate the superior image-level and region-level accuracy of our method on a real-world distribution grid test case.

Authors: Qinghu Tang (Tsinghua University); Zhecheng Wang (Stanford University); Arun Majumdar (Stanford University); Ram Rajagopal (Stanford University)

Power and energy
NeurIPS 2019 Bayesian optimization with theory-based constraints accelerates search for stable photovoltaic perovskite materials (Papers Track)
Abstract and authors: (click to expand)

Abstract: Bringing a new photovoltaic technology from materials research stage to the market has historically taken decades, and the process has to be accelerated for increasing the share of renewables in energy production. We demonstrate Bayesian optimization for accelerating stability research. Convergence is reached even faster when using a constraint for integrating physical knowledge into the model. In our test case, we optimize the stability of perovskite compositions for perovskite solar cells, an efficient new solar cell technology suffering from limited lifetime of devices.

Authors: Armi Tiihonen (Massachusetts Institute of Technology)

Power and energy
NeurIPS 2019 Increasing performance of electric vehicles in ride-hailing services using deep reinforcement learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: New forms of on-demand transportation such as ride-hailing and connected autonomous vehicles are proliferating, yet are a challenging use case for electric vehicles (EV). This paper explores the feasibility of using deep reinforcement learning (DRL) to optimize a driving and charging policy for a ride-hailing EV agent, with the goal of reducing costs and emissions while increasing transportation service provided. We introduce a data-driven simulation of a ride-hailing EV agent that provides transportation service and charges energy at congested charging infrastructure. We then formulate a test case for the sequential driving and charging decision making problem of the agent and apply DRL to optimize the agent's decision making policy. We evaluate the performance against heuristic policies and show that our agent learns to act competitively without any prior knowledge.

Authors: Jon Donadee (LLNL); Jacob Pettit (LLNL); Ruben Glatt (LLNL); Brenden Petersen (Lawrence Livermore National Laboratory)

Transportation Power and energy
NeurIPS 2019 Stripping off the implementation complexity of physics-based model predictive control for buildings via deep learning (Papers Track)
Abstract and authors: (click to expand)

Abstract: Over the past decade, model predictive control (MPC) has been considered as the most promising solution for intelligent building operation. Despite extensive effort, transfer of this technology into practice is hampered by the need to obtain an accurate controller model with minimum effort, the need of expert knowledge to set it up, and the need of increased computational power and dedicated software to run it. A promising direction that tackles the last two problems was proposed by approximate explicit MPC where the optimal control policies are learned from MPC data via a suitable function approximator, e.g., a deep learning (DL) model. The main advantage of the proposed approach stems from simple evaluation at execution time leading to low computational footprints and easy deployment on embedded HW platforms. We present the energy savings potential of physics-based (also called 'white-box') MPC applied to an office building in Belgium. Moreover, we demonstrate how deep learning approximators can be used to cut the implementation and maintenance costs of MPC deployment without compromising performance. We also critically assess the presented approach by pointing out the major challenges and remaining open-research questions.

Authors: Jan Drgona (Pacific Northwest National Laboratory); Lieve Helsen (KU Leuven); Draguna Vrabie (PNNL)

Buildings and cities Reinforcement learning and control
NeurIPS 2019 Machine learning identifies the most valuable synthesis conditions for next-generation photovoltaics (Papers Track) Best Paper Award
Abstract and authors: (click to expand)

Abstract: Terawatts of next-generation photovoltaics (PV) are necessary to mitigate climate change. The traditional R&D paradigm leads to high efficiency / high variability solar cells, limiting industrial scaling of novel PV materials. In this work, we propose a machine learning approach for early-stage optimization of solar cells, by combining a physics-informed deep autoencoder and a manufacturing-relevant Bayesian optimization objective. This framework allows to: 1) Co-optimize solar cell performance and variability under techno-economic revenue constrains, and 2) Infer the effect of process conditions over key latent physical properties. We test our approach by synthesizing 135 perovskite solar cells, and finding the optimal points under various techno-economic assumptions.

Authors: Felipe Oviedo (MIT) and Zekun Ren (MIT)

Power and energy Industry
NeurIPS 2019 Helping Reduce Environmental Impact of Aviation with Machine Learning (Papers Track) Best Paper Award
Abstract and authors: (click to expand)

Abstract: Commercial aviation is one of the biggest contributors towards climate change. We propose to reduce environmental impact of aviation by considering solutions that would reduce the flight time. Specifically, we first consider improving winds aloft forecast so that flight planners could use better information to find routes that are efficient. Secondly, we propose an aircraft routing method that seeks to find the fastest route to the destination by considering uncertainty in the wind forecasts and then optimally trading-off between exploration and exploitation. Both these ideas were previously published in [5] and [8] and contain further technical details.

Authors: Ashish Kapoor (Microsoft)

Transportation Aviation
NeurIPS 2019 Machine Learning for Generalizable Prediction of Flood Susceptibility (Papers Track)
Abstract and authors: (click to expand)

Abstract: Flooding is a destructive and dangerous hazard and climate change appears to be increasing the frequency of catastrophic flooding events around the world. Physics-based flood models are costly to calibrate and are rarely generalizable across different river basins, as model outputs are sensitive to site-specific parameters and human-regulated infrastructure. Statistical models trained primarily from remotely-sensed Earth observation data could reduce the need for extensive in-situ measurements. In this work, we develop generalizable, multi-basin models of river flooding susceptibility using geographically-distributed data from the USGS stream gauge network. Machine learning models are trained in a supervised framework to predict two measures of flood susceptibility from a mix of river basin attributes, impervious surface cover information derived from satellite imagery, and historical records of rainfall and stream height. We report prediction performance of multiple models using precision-recall curves, and compare with performance of naive baselines. This work on multi-basin flood prediction represents a step in the direction of making flood prediction accessible to all at-risk communities.

Authors: Dylan Fitzpatrick (Carnegie Mellon University); Chelsea Sidrane (Stanford University); Andrew Annex (Johns Hopkins University); Diane O'Donoghue (kx); Piotr Bilinski (University of Warsaw)

Disaster prediction, management, and relief Extreme weather events
NeurIPS 2019 A Deep Learning-based Framework for the Detection of Schools of Herring in Echograms (Papers Track)
Abstract and authors: (click to expand)

Abstract: Tracking the abundance of underwater species is crucial for understanding the effects of climate change on marine ecosystems. Biologists typically monitor underwater sites with echosounders and visualize data as 2D images (echograms); they interpret these data manually or semi-automatically, which is time-consuming and prone to inconsistencies. This paper proposes a deep learning framework for the automatic detection of schools of herring from echograms. Experiments demonstrated that our approach outperforms a traditional machine learning algorithm that uses hand-crafted features. Our framework could easily be expanded to detect more species of interest to sustainable fisheries.

Authors: Alireza Rezvanifar (University of Victoria); Tunai Porto Marques (University of Victoria ); Melissa Cote (University of Victoria); Alexandra Branzan Albu (University of Victoria); Alex Slonimer (ASL Environmental Sciences); Thomas Tolhurst (ASL Environmental Sciences ); Kaan Ersahin (ASL Environmental Sciences ); Todd Mudge (ASL Environmental Sciences ); Stephane Gauthier (Fisheries and Oceans Canada)

Ecosystems and natural resources Climate and Earth science
NeurIPS 2019 Emulating Numeric Hydroclimate Models with Physics-Informed cGANs (Papers Track) Honorable Mention
Abstract and authors: (click to expand)

Abstract: Process-based numerical simulations, including those for climate modeling applications, are compute and resource intensive, requiring extensive customization and hand-engineering for encoding governing equations and other domain knowledge. On the other hand, modern deep learning employs a significantly simpler and more efficient computational workflow, and has been shown impressive results across a myriad of applications in the computational sciences. In this work, we investigate the potential of deep generative learning models, specifically conditional Generative Adversarial Networks (cGANs), to simulate the output of a physics-based model of the spatial distribution of the water content of mountain snowpack - the snow water equivalent (SWE). We show preliminary results indicating that the cGAN model is able to learn diverse mappings between meteorological forcings and SWE output. Thus physics based cGANs provide a means for fast and accurate SWE modeling that can have significant impact in a variety of applications (e.g., hydropower forecasting, agriculture, and water supply management). In climate science, the Snowpack and SWE are seen as some of the best indicative variables for investigating climate change and its impact. The massive speedups, diverse sampling, and sensitivity/saliency modelling that cGANs can bring to SWE estimation will be extremely important to investigating variables linked to climate change as well as predicting and forecasting the potential effects of climate change to come.

Authors: Ashray Manepalli (terrafuse); Adrian Albert (terrafuse, inc.); Alan Rhoades (Lawrence Berkeley National Lab); Daniel Feldman (Lawrence Berkeley National Lab)

Ecosystems and natural resources Climate and Earth science
NeurIPS 2019 Forecasting El Niño with Convolutional and Recurrent Neural Networks (Papers Track)
Abstract and authors: (click to expand)

Abstract: The El Niño Southern Oscillation (ENSO) is the dominant mode of variability in the climate system on seasonal to decadal timescales. With foreknowledge of the state of ENSO, stakeholders can anticipate and mitigate impacts in climate-sensitive sectors such as agriculture and energy. Traditionally, ENSO forecasts have been produced using either computationally intensive physics-based dynamical models or statistical models that make limiting assumptions, such as linearity between predictors and predictands. Here we present a deep-learning-based methodology for forecasting monthly ENSO temperatures at various lead times. While traditional statistical methods both train and validate on observational data, our method trains exclusively on physical simulations. With the entire observational record as an out-of-sample validation set, the method’s skill is comparable to that of operational dynamical models. The method is also used to identify disagreements among climate models about the predictability of ENSO in a world with climate change.

Authors: Ankur Mahesh (ClimateAi); Maximilian Evans (ClimateAi); Garima Jain (ClimateAi); Mattias Castillo (ClimateAi); Aranildo Lima (ClimateAi); Brent Lunghino (ClimateAi); Himanshu Gupta (ClimateAi); Carlos Gaitan (ClimateAi); Jarrett Hunt (ClimateAi); Omeed Tavasoli (ClimateAi); Patrick Brown (ClimateAi, San Jose State University); V. Balaji (Geophysical Fluid Dynamics Laboratory)

Climate and Earth science Forecasting
NeurIPS 2019 Deep learning predictions of sand dune migration (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Climate change is making many desert regions warmer, drier, and sandier. These conditions kill vegetation, and release once-stable sand into the wind, allowing it to form dunes that threaten roads, farmland, and solar panel installations. With enough warning, people can mitigate dune damages by moving infrastructure or restoring vegetation. Current dune simulations, however, do not scale well enough to provide useful forecasts for the ~5% of Earth's land surface that is covered by mobile sands. We propose to train a deep learning simulation to emulate the output of a community-standard physics-based dune simulation. We will base the new model on a GAN-based video prediction model with an excellent track record for predicting spatio-temporal patterns to model, and use it to simulate dune topographies over time. Our preliminary work indicates that the new model will run up to ten million times faster than existing dune simulations, which would turn dune modelling from an exercise that covers a handful of dunes to a practical forecast for large desert regions.

Authors: Kelly Kochanski (University of Colorado Boulder); Divya Mohan (University of California Berkeley); Jenna Horrall (James Madison University); Ghaleb Abdulla (Lawrence Livermore National Laboratory)

Climate and Earth science Extreme weather events
NeurIPS 2019 Predictive Inference of a Wildfire Risk Pipeline in the United States (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Wildfires are rare events that present severe threats to life and property. Understanding their propagation is of key importance to mitigate and contain their impact, especially since climate change is increasing their occurrence. We propose an end-to-end sequential model of wildfire risk components, including wildfire location, size, duration, and risk exposure. We do so through a combination of marked spatio-temporal point processes and conditional density estimation techniques. Unlike other approaches that use regression-based methods, this approach allows both predictive accuracy and an associated uncertainty measure for each risk estimate, accounting for the uncertainty in prior model components. This is particularly beneficial for timely decision-making by different wildfire risk management stakeholders. To allow us to build our models without limiting them to a specific state or county, we have collected open wildfire and climate data for the entire continental United States. We are releasing this aggregated dataset to enable further o pen research on wildfire models at a national scale.

Authors: Shamindra Shrotriya (Carnegie Mellon University); Niccolo Dalmasso (Carnegie Mellon University); Alex Reinhart (Carnegie Mellon University)

Extreme weather events Data presentation and management Disaster prediction, management, and relief
NeurIPS 2019 FutureArctic - beyond Computational Ecology (Proposals Track)
Abstract and authors: (click to expand)

Abstract: This paper presents the Future Arctic initiative, a multi-disciplinary training network where machine learning researchers and ecologists cooperatively study both long- and short-term responses to future climate in Iceland.

Authors: Steven Latre (UAntwerpen); Dimitri Papadimitriou (UAntwerpen); Ivan Janssens (UAntwerpen); Eric Struyf (UAntwerpen); Erik Verbruggen (UAntwerpen); Ivika Ostonen (UT); Josep Penuelas (UAB); Boris Rewald (RootEcology); Andreas Richter (University of Vienna); Michael Bahn (University of Innsbruck)

Climate and Earth science Data presentation and management Ecosystems and natural resources
NeurIPS 2019 Machine Learning-based Estimation of Forest Carbon Stocks to increase Transparency of Forest Preservation Efforts (Proposals Track)
Abstract and authors: (click to expand)

Abstract: An increasing amount of companies and cities plan to become CO2-neutral, which requires them to invest in renewable energies and carbon emission offsetting solutions. One of the cheapest carbon offsetting solutions is preventing deforestation in developing nations, a major contributor in global greenhouse gas emissions. However, forest preservation projects historically display an issue of trust and transparency, which drives companies to invest in transparent, but expensive air carbon capture facilities. Preservation projects could conduct accurate forest inventories (tree diameter, species, height etc.) to transparently estimate the biomass and amount of stored carbon. However, current rainforest inventories are too inaccurate, because they are often based on a few expensive ground-based samples and/or low-resolution satellite imagery. LiDAR-based solutions, used in US forests, are accurate, but cost-prohibitive, and hardly-accessible in the Amazon rainforest. We propose accurate and cheap forest inventory analyses through Deep Learning-based processing of drone imagery. The more transparent estimation of stored carbon will create higher transparency towards clients and thereby increase trust and investment into forest preservation projects.

Authors: Björn Lütjens (MIT); Lucas Liebenwein (Massachusetts Institute of Technology); Katharina Kramer (Massachusetts Institute of Technology)

Agriculture, forestry and other land use Carbon capture and sequestration
NeurIPS 2019 DeepRI: End-to-end Prediction of Tropical Cyclone Rapid Intensification from Climate Data (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Predicting rapid intensification (RI) is extremely critical in tropical cyclone forecasting. Existing deep learning models achieve promising results, however still rely on hand-craft feature. We propose to design an end-to-end deep learning architecture that directly predict RI from raw climate data without intermediate heuristic feature, which allows joint optimization of the whole system for higher performance.

Authors: Renzhi Jing (Princeton University); Ning Lin (Princeton University); Yinda Zhang (Google LLC)

Extreme weather events Climate and Earth science
NeurIPS 2019 Autonomous Sensing and Scientific Machine Learning for Monitoring Greenhouse Gas Emissions (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Greenhouse gas emissions are a key driver of climate change. In order to develop and tune climate models, measurements of natural and anthropogenic phenomenon are necessary. Traditional methods (i.e., physical sample collection and ex situ analysis) tend to be sample sparse and low resolution, whereas global remote sensing methods tend to miss small- and mid-scale dynamic phenomenon. In situ instrumentation carried by a robotic platform is suited to study greenhouse gas emissions at unprecedented spatial and temporal resolution. However, collecting scientifically rich datasets of dynamic or transient emission events requires accurate and flexible models of gas emission dynamics. Motivated by applications in seasonal Arctic thawing and volcanic outgassing, we propose the use of scientific machine learning, in which traditional scientific models (in the form of ODEs/PDEs) are combined with machine learning techniques (generally neural networks) to better incorporate data into a structured, interpretable model. Our technical contributions will primarily involve developing these hybrid models and leveraging model uncertainty estimates during sensor planning to collect data that efficiently improves gas emission models in small-data domains.

Authors: Genevieve Flaspohler (MIT); Victoria Preston (MIT); Nicholas Roy (MIT); John Fisher (MIT); Adam Soule (Woods Hole Oceanographic Institution); Anna Michel (Woods Hole Oceanographic Institution)

Climate and Earth science Ecosystems and natural resources
NeurIPS 2019 Optimizing trees for carbon sequestration (Proposals Track)
Abstract and authors: (click to expand)

Abstract: In the IPCC models of climate change mitigation, most scenarios ensuring less than 2ºC of warming assume deployment of some form of “negative emissions technology,” alongside dramatic reductions in emissions and other major societal changes. Proposed negative emissions technologies include bioenergy with carbon capture and storage, enhanced weathering of minerals, direct air capture, and afforestation / reforestation. Among these technologies, the use of trees for carbon sequestration through photosynthesis is well established, requires little energy, has comparable sequestration potential, and can be deployed at scale for relatively low cost. The primary constraint on using trees for sequestration is land, which is limited and increasingly subject to competitive demand. Thus, maximizing the capacity and long-term stability of every hectare used for planting would bolster the critical role of trees in a broad negative emissions strategy. Here, we propose to build a new data resource and optimization tool that leverages modern measurements and machine learning to help address this need.

Authors: Jeremy Freeman

Agriculture, forestry and other land use Carbon capture and sequestration
NeurIPS 2019 Toward Resilient Cities: Using Deep Learning to Downscale Climate Model Projections (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Climate projections from Earth System Models (ESM) are widely used to assess climate change impacts. These projections, however, are too coarse in spatial and temporal resolution (e.g. 25-50 kms, monthly) to be used in local scale resilience studies. High-resolution (<4 km) climate projections at dense temporal resolution (hourly) from multiple Earth System models under various scenarios are necessary to assess potential future changes in climate variables and perform meaningful and robust climate resilience studies. Running ESMs in high-resolution is computationally too expensive, therefore downscaling methods are applied to ESM projections to produce high-resolution projections. Using a regional climate model to downscale climate projections is preferred but dynamically downscaling several ESM projections to < 4km resolution under different scenarios is currently not feasible. In this study, we propose to use a 60 year dynamically downscaled climate dataset with hourly output for the Northeastern United States to train Deep Learning models and achieve a computationally efficient method of downscaling climate projections. This method will allow for more ESM projections to be downscaled to local scales under more scenarios in an efficient manner and significantly improve robustness of regional resilience studies.

Authors: Muge Komurcu (MIT); Zikri Bayraktar (IEEE)

Climate and Earth science Extreme weather events
NeurIPS 2019 Towards self-adaptive building energy control in smart grids (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Energy consumption in buildings greatly contributes to worldwide CO2 emissions and thus any improvement in HVAC operation will greatly help tackling global climate change. We are putting forward a proposal for self-adaptive energy control in smart grids based on Deep Learning, Deep Reinforcement Learning and Multi-Agent technologies. Particularly, we introduce the concept of Deep Neural Simulation Model (DNSM) as a way of generating digital twins of buildings in which the agent can test and learn optimal operations by itself and by collaborating with other agents. Not only do we expect a reduction on energy consumption and an increment on the use of renewable sources, but also a reduction on the cost of controlling energy in buildings.

Authors: Juan Gómez-Romero (Universidad de Granada); Miguel Molina-Solana (Imperial College London)

Buildings and cities Power and energy
NeurIPS 2019 Predicting Arctic Methane Seeps via Satellite Imagery (Proposals Track)
Abstract and authors: (click to expand)

Abstract: The arctic has seen significant warming and releases of methane, a potent greenhouse gas have been reported. We aim to apply computer vision to satellite imagery in order to quantify geological methane emissions from the permafrost as well as track and predict their change due to increasing temperatures.

Authors: Olya (Olga) Irzak (Frost Methane Labs); Amber Leigh Thomas (Stanford); Stephanie Schneider (Stanford); Catalin Voss (Stanford University)

Climate and Earth science
NeurIPS 2019 GeoLabels: Towards Efficient Ecosystem Monitoring using Data Programming on Geospatial Information (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Monitoring, Reporting and Verification (MRV) systems for land use play a key role in the decision-making of climate investors, policymakers and conservationists. Remote sensing is commonly used for MRV but practical solutions are constrained by a lack of labels to train machine learning-based downstream tasks. GeoLabels is an automated MRV system that can rapidly adapt to novel applications by leveraging existing geospatial information and domain expertise to quickly create training sets through data programming. Moreover, GeoLabels uses dimensionality reduction interfaces, allowing non-technical users to create visual labeling functions.

Authors: David Dao (ETH); Johannes Rausch (ETH Zurich); Ce Zhang (ETH)

Data presentation and management Agriculture, forestry and other land use
NeurIPS 2019 A deep learning approach for classifying black carbon aerosol morphology (Proposals Track)
Abstract and authors: (click to expand)

Abstract: Black carbon (BC) is a sub-micron aerosol sourced from incomplete combustion which strongly absorbs solar radiation, leading to both direct and indirect climate impacts. The state-of-the-art technique for characterizing BC is the single particle soot photometer (SP2) instrument, which detects these aerosols in real time via laser-induced incandescence (L-II). This measurement technique allows for quantification of BC mass on a single particle basis, but time-resolved signals may also provide constraints on BC morphology, which impacts both its optical properties and atmospheric lifetime. No methods currently exist to use this information. I propose applying a deep learning based approach to classify the fractal dimension of single BC particles from time-resolved L-II signals. This method would provide the first on-line measurement technique for quantifying BC morphology. These observations could be used to improve representations of BC optical properties and atmospheric processing in climate models.

Authors: Kara Lamb (Cooperative Institute for Research in the Environmental Sciences)

Climate and Earth science
ICML 2019 Policy Search with Non-uniform State Representations for Environmental Sampling (Research Track)
Abstract and authors: (click to expand)

Abstract: Surveying fragile ecosystems like coral reefs is important to monitor the effects of climate change. We present an adaptive sampling technique that generates efficient trajectories covering hotspots in the region of interest at a high rate. A key feature of our sampling algorithm is the ability to generate action plans for any new hotspot distribution using the parameters learned on other similar looking distributions.

Authors: Sandeep Manjanna (McGill University); Herke van Hoof (University of Amsterdam); Gregory Dudek (McGill University)

Ecosystems and natural resources Data presentation and management
ICML 2019 Modelling GxE with historical weather information improves genomic prediction in new environments (Research Track)
Abstract and authors: (click to expand)

Abstract: Interaction between the genotype and the environment ($G \times E$) has a strong impact on the yield of major crop plants. Recently $G \times E$ has been predicted from environmental and genomic covariates, but existing works have not considered generalization to new environments and years without access to in-season data. We study \textit{in silico} the viability of $G \times E$ prediction under realistic constraints. We show that the environmental response of a new generation of untested Barley cultivars can be predicted in new locations and years using genomic data, machine learning and historical weather observations. Our results highlight the need for models of $G \times E$: non-linear effects clearly dominate linear ones and the interaction between the soil type and daily rain is identified as the main driver for $G \times E$. Our study implies that genomic selection can be used to capture the yield potential in $G \times E$ effects for future growth seasons, providing a possible means to achieve yield improvements. $G \times E$ models are also needed to select for varieties that react favourably to the altering climate conditions. For this purpose, the historical weather observations could be replaced by climate simulations to study the yield potential under various climate scenarios.This abstract summarizes the findings of a recently published article.

Authors: Jussi Gillberg (Aalto University); Pekka Marttinen (Aalto University); Hiroshi Mamitsuka (Kyoto University); Samuel Kaski (Aalto University)

Agriculture, forestry and other land use
ICML 2019 Machine Learning empowered Occupancy Sensing for Smart Buildings (Research Track)
Abstract and authors: (click to expand)

Abstract: Over half of the global electricity consumption is attributed to buildings, which are often operated poorly from an energy perspective. Significant improvements in energy efficiency can be achieved via intelligent building control techniques. To realize such advanced control schemes, accurate and robust occupancy information is highly valuable. In this work, we present a cutting-edge WiFi sensing platform and state-of-the-art machine learning methods to address longstanding occupancy sensing challenges in smart buildings. Our systematic solution provides comprehensive fine-grained occupancy information in a non-intrusive and privacy-preserving manner, which facilitates eco-friendly and sustainable buildings.

Authors: Han Zou (UC Berkeley); Hari Prasanna Das (UC Berkeley ); Jianfei Yang (Nanyang Technological University); Yuxun Zhou (UC Berkeley); Costas Spanos (UC Berkeley)

Buildings and cities Data presentation and management
ICML 2019 Focus and track: pixel-wise spatio-temporal hurricane tracking (Research Track)
Abstract and authors: (click to expand)

Abstract: We tackle extreme climate event tracking problem. It has unique challenges to other visual object tracking problems, including wider range of spatio-temporal dynamics, blur boundary of the target, and shortage of labeled dataset. In this paper, we propose a simple but robust end-to-end model based on multi-layered ConvLSTM, suitable for the climate event tracking problem. It first learns to imprint location and appearance of the target at the first frame with one-shot auto-encoding fashion, and then, the learned feature is consumed by the tracking module to track the target in subsequent time frames. To tackle the data shortage problem, we propose data augmentation based on Social GAN. Extensive experiments show that the proposed framework significantly improves tracking performance on hurricane tracking task over several state-of-the-art methods.

Authors: Sookyung Kim (Lawrence Livermore National Laboratory); Sunghyun Park (Korea University); Sunghyo Chung (Korea University); Yunsung Lee (Korea University); Hyojin Kim (LLNL); Joonseok Lee (Google Research); Jaegul Choo (Korea University); Mr Prabhat (Lawrence Berkeley National Laboratory)

Climate and Earth science Extreme weather events
ICML 2019 Recovering the parameters underlying the Lorenz-96 chaotic dynamics (Research Track)
Abstract and authors: (click to expand)

Abstract: Climate projections suffer from uncertain equilibrium climate sensitivity. The reason behind this uncertainty is the resolution of global climate models, which is too coarse to resolve key processes such as clouds and convection. These processes are approximated using heuristics in a process called parameterization. The selection of these parameters can be subjective, leading to significant uncertainties in the way clouds are represented in global climate models. Here, we explore three deep network algorithms to infer these parameters in an objective and data-driven way. We compare the performance of a fully-connected network, a one-dimensional and, a two-dimensional convolutional networks to recover the underlying parameters of the Lorenz-96 model, a non-linear dynamical system that has similar behavior to the climate system.

Authors: Soukayna Mouatadid (University of Toronto); Pierre Gentine (Columbia University); Wei Yu (University of Toronto); Steve Easterbrook (University of Toronto)

Climate and Earth science Extreme weather events
ICML 2019 Using Bayesian Optimization to Improve Solar Panel Performance by Developing Antireflective, Superomniphobic Glass (Research Track)
Abstract and authors: (click to expand)

Abstract: Photovoltaic solar panel efficiency is dependent on photons transmitting through the glass sheet covering and into the crystalline silicon solar cells within. However, complications such as soiling and light reflection degrade performance. Our goal is to identify a fabrication process to produce glass which promotes photon transmission and is superomniphobic (repels fluids), for easier cleaning. In this paper, we propose adapting Bayesian optimization to efficiently search the space of possible glass fabrication strategies; in this search we balance three competing objectives (transmittance, haze and oil contact angle). We present the glass generated from this Bayesian optimization strategy and detail its properties relevant to photovoltaic solar power.

Authors: Sajad Haghanifar (University of Pittsburgh); Bolong Cheng (SigOpt); Mike Mccourt (SigOpt); Paul Leu (University of Pittsburgh)

Power and energy
ICML 2019 A quantum mechanical approach for data assimilation in climate dynamics (Research Track)
Abstract and authors: (click to expand)

Abstract: A framework for data assimilation in climate dynamics is presented, combining aspects of quantum mechanics, Koopman operator theory, and kernel methods for machine learning. This approach adapts the Dirac-von Neumann formalism of quantum dynamics and measurement to perform data assimilation (filtering) of climate dynamics, using the Koopman operator governing the evolution of observables as an analog of the Heisenberg operator in quantum mechanics, and a quantum mechanical density operator to represent the data assimilation state. The framework is implemented in a fully empirical, data-driven manner, using kernel methods for machine learning to represent the evolution and measurement operators via matrices in a basis learned from time-ordered observations. Applications to data assimilation of the Nino 3.4 index for the El Nino Southern Oscillation (ENSO) in a comprehensive climate model show promising results.

Authors: Dimitrios Giannakis (Courant Institute of Mathematical Sciences, New York University); Joanna Slawinska (University of Wisconsin-Milwaukee); Abbas Ourmazd (University of Wisconsin-Milwaukee)

Data assimilation Climate and Earth science
ICML 2019 Data-driven Chance Constrained Programming based Electric Vehicle Penetration Analysis (Research Track)
Abstract and authors: (click to expand)

Abstract: Transportation electrification has been growing rapidly in recent years. The adoption of electric vehicles (EVs) could help to release the dependency on oil and reduce greenhouse gas emission. However, the increasing EV adoption will also impose a high demand on the power grid and may jeopardize the grid network infrastructures. For certain high EV penetration areas, the EV charging demand may lead to transformer overloading at peak hours which makes the maximal EV penetration analysis an urgent problem to solve. This paper proposes a data-driven chance constrained programming based framework for maximal EV penetration analysis. Simulation results are presented for a real-world neighborhood level network. The proposed framework could serve as a guidance for utility companies to schedule infrastructure upgrades.

Authors: Di Wu (McGill); Tracy Cui (Google NYC); Doina Precup (McGill University); Benoit Boulet (McGill)

Data presentation and management Power and energy
ICML 2019 Machine Learning for AC Optimal Power Flow (Research Track) Honorable Mention
Abstract and authors: (click to expand)

Abstract: F( We explore machine learning methods for AC Optimal Powerflow (ACOPF) - the task of optimizing power generation in a transmission network according while respecting physical and engineering constraints. We present two formulations of ACOPF as a machine learning problem: 1) an end-to-end prediction task where we directly predict the optimal generator settings, and 2) a constraint prediction task where we predict the set of active constraints in the optimal solution. We validate these approaches on two benchmark grids.

Authors: Neel Guha (Carnegie Mellon University); Zhecheng Wang (Stanford University); Arun Majumdar (Stanford University)

Power and energy Industry
ICML 2019 Targeted Meta-Learning for Critical Incident Detection in Weather Data (Research Track)
Abstract and authors: (click to expand)

Abstract: Due to imbalanced or heavy-tailed nature of weather- and climate-related datasets, the performance of standard deep learning models significantly deviates from their expected behavior on test data. Classical methods to address these issues are mostly data or application dependent, hence burdensome to tune. Meta-learning approaches, on the other hand, aim to learn hyperparameters in the learning process using different objective functions on training and validation data. However, these methods suffer from high computational complexity and are not scalable to large datasets. In this paper, we aim to apply a novel framework named as targeted meta-learning to rectify this issue, and show its efficacy in dealing with the aforementioned biases in datasets. This framework employs a small, well-crafted target dataset that resembles the desired nature of test data in order to guide the learning process in a coupled manner. We empirically show that this framework can overcome the bias issue, common to weather-related datasets, in a bow echo detection case study.

Authors: Mohammad Mahdi Kamani (The Pennsylvania State University); Sadegh Farhang (Pennsylvania State University); Mehrdad Mahdavi (Penn State); James Z Wang (The Pennsylvania State University)

Extreme weather events Climate and Earth science
ICML 2019 ClimateNet: Bringing the power of Deep Learning to weather and climate sciences via open datasets and architectures (Research Track)
Abstract and authors: (click to expand)

Abstract: Pattern recognition tasks such as classification, object detection and segmentation have remained challenging problems in the weather and climate sciences. While there exist many empirical heuristics for detecting weather patterns and extreme events, the disparities between the output of these different methods even for a single event are large and often difficult to reconcile. Given the success of Deep Learning in tackling similar problems in computer vision, we advocate a DL-based approach. However, DL works best in the context of supervised learning, when labeled datasets are readily available. Reliable, labeled training data is scarce in climate science. `ClimateNet' is an effort to solve this problem by creating open, community-sourced expert-labeled datasets that capture information pertaining to class or pattern labels, bounding boxes and segmentation masks. In this paper we present the motivation, design and status of the ClimateNet dataset and associated model architecture.

Authors: Karthik Kashinath (Lawrence Berkeley National Laboratory); Mayur Mudigonda (UC Berkeley); Kevin Yang (UC Berkeley); Jiayi Chen (UC Berkeley); Annette Greiner (Lawrence Berkeley National Laboratory); Mr Prabhat (Lawrence Berkeley National Laboratory)

Extreme weather events Data presentation and management
ICML 2019 Improving Subseasonal Forecasting in the Western U.S. with Machine Learning (Research Track)
Abstract and authors: (click to expand)

Abstract: Water managers in the western United States (U.S.) rely on longterm forecasts of temperature and precipitation to prepare for droughts and other wet weather extremes. To improve the accuracy of these long-term forecasts, the Bureau of Reclamation and the National Oceanic and Atmospheric Administration (NOAA) launched the Subseasonal Climate Forecast Rodeo, a year-long real-time forecasting challenge, in which participants aimed to skillfully predict temperature and precipitation in the western U.S. two to four weeks and four to six weeks in advance. We present and evaluate our machine learning approach to the Rodeo and release our SubseasonalRodeo dataset, collected to train and evaluate our forecasting system. Our predictive system is an ensemble of two regression models, and exceeds that of the top Rodeo competitor as well as the government baselines for each target variable and forecast horizon.

Authors: Paulo Orenstein (Stanford); Jessica Hwang (Stanford); Judah Cohen (AER); Karl Pfeiffer (AER); Lester Mackey (Microsoft Research New England)

Extreme weather events Climate and Earth science
ICML 2019 Unsupervised Temporal Clustering to Monitor the Performance of Alternative Fueling Infrastructure (Research Track)
Abstract and authors: (click to expand)

Abstract: Zero Emission Vehicles (ZEV) play an important role in the decarbonization of the transportation sector. For a wider adoption of ZEVs, providing a reliable infrastructure is critical. We present a machine learning approach that uses unsupervised temporal clustering algorithm along with survey analysis to determine infrastructure performance and reliability of alternative fuels. We illustrate this approach for the hydrogen fueling stations in California, but this can be generalized for other regions and fuels.

Authors: Kalai Ramea (PARC)

Transportation Societal adaptation
ICML 2019 A Flexible Pipeline for Prediction of Tropical Cyclone Paths (Research Track)
Abstract and authors: (click to expand)

Abstract: Hurricanes and, more generally, tropical cyclones (TCs) are rare, complex natural phenomena of both scientific and public interest. The importance of understanding TCs in a changing climate has increased as recent TCs have had devastating impacts on human lives and communities. Moreover, good prediction and understanding about the complex nature of TCs can mitigate some of these human and property losses. Though TCs have been studied from many different angles, more work is needed from a statistical approach of providing prediction regions. The current state-of-the-art in TC prediction bands comes from the National Hurricane Center at NOAA, whose proprietary model provides "cones of uncertainty" for TCs through an analysis of historical forecast errors. The contribution of this paper is twofold. We introduce a new pipeline that encourages transparent and adaptable prediction band development by streamlining cyclone track simulation and prediction band generation. We also provide updates to existing models and novel statistical methodologies in both areas of the pipeline respectively.

Authors: Niccolo Dalmasso (Carnegie Mellon University); Robin Dunn (Carnegie Mellon University); Benjamin LeRoy (Carnegie Mellon University); Chad Schafer (Carnegie Mellon University)

Extreme weather events Climate and Earth science Data presentation and management
ICML 2019 Mapping land use and land cover changes faster and at scale with deep learning on the cloud (Research Track)
Abstract and authors: (click to expand)

Abstract: Policymakers rely on Land Use and Land Cover (LULC) maps for evaluation and planning. They use these maps to plan climate-smart agriculture policy, improve housing resilience (to earthquakes or other natural disasters), and understand how to grow commerce in small communities. A number of institutions have created global land use maps from historic satellite imagery. However, these maps can be outdated and are often inaccurate, particularly in their representation of developing countries. We worked with the European Space Agency (ESA) to develop a LULC deep learning workflow on the cloud that can ingest Sentinel-2 optical imagery for a large scale LULC change detection. It’s an end-to-end workflow that sits on top of two comprehensive tools, SentinelHub, and eo-learn, which seamlessly link earth observation data with machine learning libraries. It can take in the labeled LULC and associated AOI in shapefiles, set up a task to fetch cloud-free, time series imagery stacks within the defined time interval by the users. It will pair the satellite imagery tile with it’s labeled LULC mask for the supervised deep learning model training on the cloud. Once a well-performing model is trained, it can be exported as a Tensorflow/Pytorch serving docker image to work with our cloud-based model inference pipeline. The inference pipeline can automatically scale with the number of images to be processed. Changes in land use are heavily influenced by human activities (e.g. agriculture, deforestation, human settlement expansion) and have been a great source of greenhouse gas emissions. Sustainable forest and land management practices vary from region to region, which means having flexible, scalable tools will be critical. With these tools, we can empower analysts, engineers, and decision-makers to see where contributions to climate-smart agricultural, forestry and urban resilience programs can be made.

Authors: Zhuangfang Yi (Development Seed); Drew Bollinger (Development Seed); Devis Peressutti (Sinergise)

Agriculture, forestry and other land use Ecosystems and natural resources Buildings and cities
ICML 2019 Achieving Conservation of Energy in Neural Network Emulators for Climate Modeling (Research Track)
Abstract and authors: (click to expand)

Abstract: Artificial neural-networks have the potential to emulate cloud processes with higher accuracy than the semi-empirical emulators currently used in climate models. However, neural-network models do not intrinsically conserve energy and mass, which is an obstacle to using them for long-term climate predictions. Here, we propose two methods to enforce linear conservation laws in neural-network emulators of physical models: Constraining (1) the loss function or (2) the architecture of the network itself. Applied to the emulation of explicitly-resolved cloud processes in a prototype multi-scale climate model, we show that architecture constraints can enforce conservation laws to satisfactory numerical precision, while all constraints help the neural-network better generalize to conditions outside of its training set, such as global warming.

Authors: Tom G Beucler (Columbia University & UCI); Stephan Rasp (Ludwig-Maximilian University of Munich); Michael Pritchard (UCI); Pierre Gentine (Columbia University)

Climate and Earth science Extreme weather events
ICML 2019 The Impact of Feature Causality on Normal Behaviour Models for SCADA-based Wind Turbine Fault Detection (Research Track)
Abstract and authors: (click to expand)

Abstract: The cost of wind energy can be reduced by using SCADA data to detect faults in wind turbine components. Normal behavior models are one of the main fault detection approaches, but there is a lack of work in how different input features affect the results. In this work, a new taxonomy based on the causal relations between the input features and the target is presented. Based on this taxonomy, the impact of different input feature configurations on the modelling and fault detection performance is evaluated. To this end, a framework that formulates the detection of faults as a classification problem is also presented.

Authors: Telmo Felgueira (IST)

Power and energy Industry
ICML 2019 Predicting CO2 Plume Migration using Deep Neural Networks (Research Track)
Abstract and authors: (click to expand)

Abstract: Carbon capture and sequestration (CCS) is an essential climate change mitigation technology for achieving the 2 degree C target. Numerical simulation of CO2 plume migration in the subsurface is a prerequisite to effective CCS projects. However, stochastic high spatial resolution simulations are currently limited by computational resources. We propose a deep neural network approach to predict the CO2 plume migration in high dimensional systems with complex geology. Upon training, the network is able to give accurate predictions that are 6 orders of magnitude faster than traditional numerical simulators. This approach can be easily adopted to history-matching and uncertainty analysis problems to support the scale-up of CCS deployment.

Authors: Gege Wen (Stanford University)

Carbon capture and sequestration
ICML 2019 Truck Traffic Monitoring with Satellite Images (Research Track)
Abstract and authors: (click to expand)

Abstract: The road freight sector is responsible for a large and growing share of greenhouse gas emissions, but reliable data on the amount of freight that is moved on roads in many parts of the world are scarce. Many low- and middle-income countries have limited ground-based traffic monitoring and freight surveying activities. In this proof of concept, we show that we can use an object detection network to count trucks in satellite images and predict average annual daily truck traffic from those counts. We describe a complete model, test the uncertainty of the estimation, and discuss the transfer to developing countries.

Authors: Lynn Kaack (ETH Zurich); George H Chen (Carnegie Mellon University); Granger Morgan (Carnegie Mellon University)

Transportation Data presentation and management
ICML 2019 Evaluating aleatoric and epistemic uncertainties of time series deep learning models for soil moisture predictions (Research Track)
Abstract and authors: (click to expand)

Abstract: Soil moisture is an important variable that determines floods, vegetation health, agriculture productivity, and land surface feedbacks to the atmosphere, etc.. The recently available satellite-based observations give us a unique opportunity to directly build data-driven models to predict soil moisture instead of using land surface models, but previously there was no uncertainty estimate. We tested Monte Carlo dropout with an aleatoric term (MCD+A) for our long short-term memory models for this problem, and ask if the uncertainty terms behave as they were argued to. We show that MCD+A indeed gave a good estimate of our predictive error, provided we tune a hyperparameter and use a representative training dataset. The aleatoric term responded strongly to observational noise and the epistemic term clearly acted as a detector for physiographic dissimilarity from the training data. However, when the training and test data are characteristically different, the aleatoric term could be misled, undermining its reliability. We will also discuss some of the major challenges for which we anticipate the geoscientific communities will need help from computer scientists in applying AI to climate or hydrologic modeling.

Authors: Chaopeng Shen (Pennsylvania State University)

Climate and Earth science Disaster prediction, management, and relief Extreme weather events
ICML 2019 Detecting anthropogenic cloud perturbations with deep learning (Research Track) Best Paper Award
Abstract and authors: (click to expand)

Abstract: One of the most pressing questions in climate science is that of the effect of anthropogenic aerosol on the Earth's energy balance. Aerosols provide the `seeds' on which cloud droplets form, and changes in the amount of aerosol available to a cloud can change its brightness and other physical properties such as optical thickness and spatial extent. Clouds play a critical role in moderating global temperatures and small perturbations can lead to significant amounts of cooling or warming. Uncertainty in this effect is so large it is not currently known if it is negligible, or provides a large enough cooling to largely negate present-day warming by CO2. This work uses deep convolutional neural networks to look for two particular perturbations in clouds due to anthropogenic aerosol and assess their properties and prevalence, providing valuable insights into their climatic effects.

Authors: Duncan Watson-Parris (University of Oxford); Sam Sutherland (University of Oxford); Matthew Christensen (University of Oxford); Anthony Caterini (University of Oxford); Dino Sejdinovic (University of Oxford); Philip Stier (University of Oxford)

Computer vision and remote sensing Climate and Earth science
ICML 2019 Data-driven surrogate models for climate modeling: application of echo state networks, RNN-LSTM and ANN to the multi-scale Lorenz system as a test case (Research Track)
Abstract and authors: (click to expand)

Abstract: Understanding the effects of climate change relies on physics driven computationally expensive climate models which are still imperfect owing to ineffective subgrid scale parametrization. An effective way to treat these ineffective parametrization of largely uncertain subgrid scale processes are data-driven surrogate models with machine learning techniques. These surrogate models train on observational data capturing either the embed- dings of their (subgrid scale processes’) underlying dynamics on the large scale processes or to simulate the subgrid processes accurately to be fed into the large scale processes. In this paper an extended version of the Lorenz 96 system is studied, which consists of three equations for a set of slow, intermediate, and fast variables, providing a fitting prototype for multi-scale, spatio-temporal chaos, and in particular, the complex dynamics of the climate system. In this work, we have built a data-driven model based on echo state net- works (ESN) aimed, specifically at climate modeling. This model can predict the spatio-temporal chaotic evolution of the Lorenz system for several Lyapunov timescales. We show that the ESN model outperforms, in terms of the prediction horizon, a deep learning technique based on recurrent neural network (RNN) with long short-term memory (LSTM) and an artificial neural network by factors between 3 and 10. The results suggest that ESN has the potential for being a powerful method for surrogate modeling and data-driven prediction for problems of interest to the climate community.

Authors: Ashesh K Chattopadhyay (Rice University); Pedram Hassanzadeh (Rice University); Devika Subramanian (Rice University); Krishna Palem (Rice University); Charles Jiang (Rice University); Adam Subel (Rice University)

Climate and Earth science Extreme weather events
ICML 2019 Learning Radiative Transfer Models for Climate Change Applications in Imaging Spectroscopy (Research Track)
Abstract and authors: (click to expand)

Abstract: According to a recent investigation, an estimated 33-50% of the world's coral reefs have undergone degradation, believed to be as a result of climate change. A strong driver of climate change and the subsequent environmental impact are greenhouse gases such as methane. However, the exact relation climate change has to the environmental condition cannot be easily established. Remote sensing methods are increasingly being used to quantify and draw connections between rapidly changing climatic conditions and environmental impact. A crucial part of this analysis is processing spectroscopy data using radiative transfer models (RTMs) which is a computationally expensive process and limits their use with high volume imaging spectrometers. This work presents an algorithm that can efficiently emulate RTMs using neural networks leading to a multifold speedup in processing time, and yielding multiple downstream benefits.

Authors: Shubhankar V Deshpande (Carnegie Mellon University), Brian D Bue (NASA JPL/Caltech), David R Thompson (NASA JPL/Caltech), Vijay Natraj (NASA JPL/Caltech), Mario Parente (UMass Amherst)

Computer vision and remote sensing Climate and Earth science
ICML 2019 Planetary Scale Monitoring of Urban Growth in High Flood Risk Areas (Research Track)
Abstract and authors: (click to expand)

Abstract: Climate change is increasing the incidence of flooding. Many areas in the developing world are experiencing strong population growth but lack adequate urban planning. This represents a significant humanitarian risk. We explore the use of high-cadence satellite imagery provided by Planet, who’s flock of over one hundred ’Dove’ satellites image the entire earth’s landmass everyday at 3-5m resolution. We use a deep learning-based computer vision approach to measure flood-related humanitarian risk in 5 cities in Africa.

Authors: Christian F Clough (Planet); Ramesh Nair (Planet); Gopal Erinjippurath (Planet); Matt George (Planet); Jesus Martinez Manso (Planet)

Extreme weather events Disaster prediction, management, and relief
ICML 2019 Efficient Multi-temporal and In-season Crop Mapping with Landsat Analysis Ready Data via Long Short-term Memory Networks (Research Track)
Abstract and authors: (click to expand)

Abstract: Globe crop analysis from plentiful satellite images yields state-of-the-art results about estimating climate change impacts on agriculture with modern machine learning technology. Generating accurate and timely crop mapping across years remains a scientific challenge since existing non-temporal classifiers are hardly capable of capturing complicated temporal links from multi-temporal remote sensing data and adapting to interannual variability. We developed an LSTM-based model trained by previous years to distinguish corn and soybean for the current year. The results showed that LSTM outperformed random forest baseline in both in-season and end-of-the-season crop type classification. The improved performance is a result of the cumulative effect of remote sensing information that has been learned by LSTM model structure. The work pF(24rovides a valuable opportunity for estimating the impact of climate change on crop yield and early warning of extreme weather events in the future.

Authors: Jinfan Xu (Zhejiang University); Renhai Zhong (Zhejiang University); Jialu Xu (Zhejiang University); Haifeng Li (Central South University); Jingfeng Huang (Zhejiang University); Tao Lin (Zhejiang University)

Agriculture, forestry and other land use
ICML 2019 Autopilot of Cement Plants for Reduction of Fuel Consumption and Emissions (Deployed Track)
Abstract and authors: (click to expand)

Abstract: The cement manufacturing industry is an essential component of the global economy and infrastructure. However, cement plants inevitably produce hazardous air pollutants, including greenhouse gases, and heavy metal emissions as byproducts of the process. Byproducts from cement manufacturing alone accounts for approximately 5% of global carbon dioxide (CO2) emissions. We have developed "Autopilot" - a machine learning based Software as a Service (SaaS) to learn manufacturing process dynamics and optimize the operation of cement plants - in order to reduce the overall fuel consumption and emissions of cement production. Autopilot is able to increase the ratio of alternative fuels (including biowaste and tires) to Petroleum coke, while optimizing operation of pyro, the core process of cement production that includes the preheater, kiln and cooler. Emissions of gases such as NOx and SOx, and heavy metals such as mercury and lead which are generated through burning petroleum coke can be reduced through the use of Autopilot. Our system has been proven to work in real world deployments and an analysis of cement plant performance with Autopilot enabled shows energy consumption savings and a decrease of up to 28,000 metric tons of CO2 produced per year.

Authors: Prabal Acharyya (Petuum Inc); Sean D Rosario (Petuum Inc); Roey Flor (Petuum Inc); Ritvik Joshi (Petuum Inc); Dian Li (Petuum Inc); Roberto Linares (Petuum Inc); Hongbao Zhang (Petuum Inc)

Industry
ICML 2019 Towards a Sustainable Food Supply Chain Powered by Artificial Intelligence (Deployed Track) Honorable Mention
Abstract and authors: (click to expand)

Abstract: About 30-40% of food produced worldwide is wasted. This puts a severe strain on the environment and represents a $165B loss to the US economy. This paper explores how artificial intelligence can be used to automate decisions across the food supply chain in order to reduce waste and increase the quality and affordability of food. We focus our attention on supermarkets — combined with downstream consumer waste, these contribute to 40% of total US food losses — and we describe an intelligent decision support system for supermarket operators that optimizes purchasing decisions and minimizes losses. The core of our system is a model-based reinforcement learn- ing engine for perishable inventory management; in a real-world pilot with a US supermarket chain, our system reduced waste by up to 50%. We hope that this paper will bring the food waste problem to the attention of the broader machine learning research community.

Authors: Volodymyr Kuleshov (Stanford University)

Industry Agriculture, forestry and other land use
ICML 2019 PVNet: A LRCN Architecture for Spatio-Temporal Photovoltaic Power Forecasting from Numerical Weather Prediction (Deployed Track)
Abstract and authors: (click to expand)

Abstract: Photovoltaic (PV) power generation has emerged as one of the leading renewable energy sources. Yet, its production is characterized by high uncertainty, being dependent on weather conditions like solar irradiance and temperature. Predicting PV production, even in the 24-hour forecast, remains a challenge and leads energy providers to left idling - often carbon-emitting - plants. In this paper, we introduce a Long-Term Recurrent Convolutional Network using Numerical Weather Predictions (NWP) to predict, in turn, PV production in the 24-hour and 48-hour forecast horizons. This network architecture fully leverages both temporal and spatial weather data, sampled over the whole geographical area of interest. We train our model on a prediction dataset from the National Oceanic and Atmospheric Administration (NOAA) to predict spatially aggregated PV production in Germany. We compare its performance to the persistence model and state-of-the-art methods.

Authors: Johan Mathe (Frog Labs)

Power and energy
ICML 2019 Finding Ship-tracks Using Satellite Data to Enable Studies of Climate and Trade Related Issues (Deployed Track)
Abstract and authors: (click to expand)

Abstract: Ship-tracks appear as long winding linear features in satellite images and are produced by aerosols from ship exhausts changing low cloud properties. They are one of the best examples of aerosol-cloud interaction experiments, which is currently the largest source of uncertainty in our understanding of climate forcing. Manually finding ship-tracks from satellite data on a large-scale is prohibitively costly while a large number of samples are required to better understand aerosol-cloud interactions. Here we train a deep neural network to automate finding ship-tracks. The neural network model generalizes well as it not only finds ship-tracks labeled by human experts, but also detects those that are occasionally missed by humans. It increases our sampling capability of ship-tracks by orders of magnitude and produces a first global map of ship-track distributions using satellite data. Major shipping routes that are mapped by the algorithm correspond well with available commercial data. There are also situations where commercial data are missing shipping routes that are detected by our algorithm. Our technique will enable studying aerosol effects on low clouds using ship-tracks on a large-scale, which will potentially narrow the uncertainty of the aerosol-cloud interactions. The product is also useful for applications such as coastal air pollution and trade.

Authors: Tianle Yuan (NASA)

Transportation Climate and Earth science
ICML 2019 Using Smart Meter Data to Forecast Grid Scale Electricity Demand (Deployed Track)
Abstract and authors: (click to expand)

Abstract: Highly accurate electricity demand forecasts represent a major opportunity to create grid stability in light of the concurrent deployment of distributed renewables and energy storage, as well as the increasing occurrence of extreme weather events caused by climate change. We present an overview of a deployed machine learning system that accomplishes this task by using smart meter data (AMI) within the region governed by the Electric Reliability Council of Texas (ERCOT).

Authors: Abraham Stanway (Amperon Holdings, Inc); Ydo Wexler (Amperon)

Power and energy Data presentation and management Extreme weather events
ICML 2019 Deep Learning for Wildlife Conservation and Restoration Efforts (Deployed Track)
Abstract and authors: (click to expand)

Abstract: Climate change and environmental degradation are causing species extinction worldwide. Automatic wildlife sensing is an urgent requirement to track biodiversity losses on Earth. Recent improvements in machine learning can accelerate the development of large-scale monitoring systems that would help track conservation outcomes and target efforts. In this paper, we present one such system we developed. 'Tidzam' is a Deep Learning framework for wildlife detection, identification, and geolocalization, designed for the Tidmarsh Wildlife Sanctuary, the site of the largest freshwater wetland restoration in Massachusetts.

Authors: Clement Duhart (MIT Media Lab)

Ecosystems and natural resources Agriculture, forestry and other land use
ICML 2019 Reinforcement Learning for Sustainable Agriculture (Ideas Track)
Abstract and authors: (click to expand)

Abstract: The growing population and the changing climate will push modern agriculture to its limits in an increasing number of regions on earth. Establishing next-generation sustainable food supply systems will mean producing more food on less arable land, while keeping the environmental impact to a minimum. Modern machine learning methods have achieved super-human performance on a variety of tasks, simply learning from the outcomes of their actions. We propose a path towards more sustainable agriculture, considering plant development an optimization problem with respect to certain parameters, such as yield and environmental impact, which can be optimized in an automated way. Specifically, we propose to use reinforcement learning to autonomously explore and learn ways of influencing the development of certain types of plants, controlling environmental parameters, such as irrigation or nutrient supply, and receiving sensory feedback, such as camera images, humidity, and moisture measurements. The trained system will thus be able to provide instructions for optimal treatment of a local population of plants, based on non-invasive measurements, such as imaging.

Authors: Jonathan Binas (Mila, Montreal); Leonie Luginbuehl (Department of Plant Sciences, University of Cambridge); Yoshua Bengio (Mila)

Agriculture, forestry and other land use Ecosystems and natural resources Extreme weather events
ICML 2019 Stratospheric Aerosol Injection as a Deep Reinforcement Learning Problem (Ideas Track) Honorable Mention
Abstract and authors: (click to expand)

Abstract: As global greenhouse gas emissions continue to rise, the use of geoengineering in order to artificially mitigate climate change effects is increasingly considered. Stratospheric aerosol injection (SAI), which reduces solar radiative forcing and thus can be used to offset excess radiative forcing due to the greenhouse effect, is both technically and economically feasible. However, naive deployment of SAI has been shown in simulation to produce highly adversarial regional climatic effects in regions such as India and West Africa. Wealthy countries would most likely be able to trigger SAI unilaterally, i.e. China, Russia or US could decide to fix their own climates and, by collateral damage, drying India out by disrupting the monsoon or inducing termination effects with rapid warming. Understanding both how SAI can be optimised and how to best react to rogue injections is therefore of crucial geostrategic interest. In this paper, we argue that optimal SAI control can be characterised as a high-dimensional Markov Decision Process. This motivates the use of deep reinforcement learning in order to automatically discover non-trivial, and potentially time-varying, optimal injection policies or identify catastrophic ones. To overcome the inherent sample inefficiency of deep reinforcement learning, we propose to emulate a Global Circulation Model using deep learning techniques. To our knowledge, this is the first proposed application of deep reinforcement learning to the climate sciences.

Authors: Christian A Schroeder (University of Oxford); Thomas Hornigold (University of Oxford)

Geoengineering Climate and Earth science
ICML 2019 Using Natural Language Processing to Analyze Financial Climate Disclosures (Ideas Track)
Abstract and authors: (click to expand)

Abstract: According to U.S. financial legislation, companies traded on the stock market are obliged to regularly disclose risks and uncertainties that are likely to affect their operations or financial position. Since 2010, these disclosures must also include climate-related risk projections. These disclosures therefore present a large quantity of textual information on which we can apply NLP techniques in order to pinpoint the companies that divulge their climate risks and those that do not, the types of vulnerabilities that are disclosed, and to follow the evolution of these risks over time.

Authors: Sasha Luccioni (Mila); Hector Palacios (Element AI)

Climate finance
ICML 2019 Machine Learning-based Maintenance for Renewable Energy: The Case of Power Plants in Morocco (Ideas Track)
Abstract and authors: (click to expand)

Abstract: In this project, the focus will be on the reduction of the overall electricity cost by the reduction of operating expenditures, including maintenance costs. We propose a predictive maintenance (PdM) framework for multi-component systems in renewables power plants based on machine learning (ML) and optimization approaches. This project would benefit from a real database acquired from the Moroccan Agency Of Sustainable Energy (MASEN) that own and operate several wind, solar and hydro power plants spread over Moroccan territory. Morocco has launched an ambitious energy strategy since 2009 that aims to ensure the energy security of the country, diversify the source of energy and preserve the environment. Ultimately, Morocco has set the target of 52% of renewables by 2030 with a large capital investment of USD 30 billion. To this end, Morocco will install 10 GW allocated as follows: 45% for solar, 42% for wind and 13% for hydro. Through the commitment of many actors, in particular in Research and Development, Morocco intends to become a regional leader and a model to follow in its climate change efforts. MASEN is investing in several strategies to reduce the cost of renewables, including the cost of operations and maintenance. Our project will provide a ML predictive maintenance framework to support these efforts.

Authors: Kris Sankaran (Montreal Institute for Learning Algorithms); Zouheir Malki (Polytechnique Montréal); Loubna Benabou (UQAR); Hicham Bouzekri (MASEN)

Power and energy
ICML 2019 GainForest: Scaling Climate Finance for Forest Conservation using Interpretable Machine Learning on Satellite Imagery (Ideas Track)
Abstract and authors: (click to expand)

Abstract: Designing effective REDD+ policies, assessing their GHG impact, and linking them with the corresponding payments, is a resource intensive and complex task. GainForest leverages video prediction with remote sensing to monitor and forecast forest change at high resolution. Furthermore, by viewing payment allocation as a feature selection problem, GainForest can efficiently design payment schemes based on the Shapley value.

Authors: David Dao (ETH); Ce Zhang (ETH); Nick Beglinger (Cleantech21); Catherine Cang (UC Berkeley); Reuven Gonzales (OasisLabs); Ming-Da Liu Zhang (ETHZ); Nick Pawlowski (Imperial College London); Clement Fung (University of British Columbia)

Agriculture, forestry and other land use Climate finance
ICML 2019 Machine Intelligence for Floods and the Built Environment Under Climate Change (Ideas Track)
Abstract and authors: (click to expand)

Abstract: While intensification of precipitation extremes has been attributed to anthropogenic climate change using statistical analysis and physics-based numerical models, understanding floods in a climate context remains a grand challenge. Meanwhile, an increasing volume of Earth science data from climate simulations, remote sensing, and Geographic Information System (GIS) tools offers opportunity for data-driven insight and action plans. Defining Machine Intelligence (MI) broadly to include machine learning and network science, here we develop a vision and use preliminary results to showcase how scientific understanding of floods can be improved in a climate context and translated to impacts with a focus on Critical Lifeline Infrastructure Networks (CLIN).

Authors: Kate Duffy (Northeastern University); Auroop Ganguly (Northeastern University)

Disaster prediction, management, and relief Extreme weather events
ICML 2019 Predicting Marine Heatwaves using Global Climate Models with Cluster Based Long Short-Term Memory (Ideas Track)
Abstract and authors: (click to expand)

Abstract: Marine heatwaves make human and natural systems vulnerable to disaster risk through the disruption of ecological services and biological function. These extreme warming events in sea surface temperature are expected to become more frequent and longer lasting as a result of climate change. Large ensembles of global climate models now provide petabytes of climate-relevant data and an opportunity to probe machine learning to glean new insights about the climate conditions that cause marine heatwaves. Here we propose a k-means cluster based learning objective to map the geography of marine heatwave drivers globally to build a forecast for extreme sea surface temperatures using Long Short-Term Memory. We describe our machine learning approach to predict when and where future marine heatwaves will occur while leveraging the massive output of data from global climate models where traditional forecasting approaches fall short. The impacts of this work could warn coastal communities by providing a forecast for marine heatwaves, which would mitigate the negative effects on fishery productivity, ecosystem health, and tourism.

Authors: Hillary S Scannell (University of Washington); Chris Fraley (Tableau Software); Nathan Mannheimer (Tableau Software); Sarah Battersby (Tableau Software); LuAnne Thompson (University of Washington)

Extreme weather events Climate and Earth science
ICML 2019 ML-driven search for zero-emissions ammonia production materials (Ideas Track)
Abstract and authors: (click to expand)

Abstract: Ammonia (NH3) production is an industrial process that consumes between 1-2% of global energy annually and is responsible for 2-3% of greenhouse gas emissions (Van der Ham et al.,2014). Ammonia is primarily used for agricultural fertilizers, but it also conforms to the US-DOE targets for hydrogen storage materials (Lanet al., 2012). Modern industrial facilities use the century-old Haber-Bosch process, whose energy usage and carbon emissions are strongly dominated by the use of methane as the combined energy source and hydrogen feedstock, not by the energy used to maintain elevated temperatures and pressures (Pfromm, 2017). Generating the hydrogen feedstock with renewable electricity through water electrolysis is an option that would allow retrofitting the billions of dollars of invested capital in Haber-Bosch production capacity. Economic viability is however strongly dependent on the relative regional prices of methane and renewable energy; renewables have been trending lower in cost but forecasting methane prices is difficult (Stehly et al., 2018; IRENA, 2017; Wainberg et al., 2017). Electrochemical ammonia production, which can use aqueous or steam H2O as its hydrogen source (first demonstrated ̃20years ago) is a promising means of emissions-free ammonia production. Its viability is also linked to the relative price of renewable energy versus methane, but in principle it can be significantly more cost-effective than Haber-Bosch (Giddeyet al., 2013) and also downscale to developing areas lacking ammonia transport infrastructure(Shipman & Symes, 2017). However to date it has only been demonstrated at laboratory scales with yields and Faradaic efficiencies insufficient to be economically competitive. Promising machine-learning approaches to fix this are discussed.

Authors: Kevin McCloskey (Google)

Industry Agriculture, forestry and other land use Transportation
ICML 2019 Low-carbon urban planning with machine learning (Ideas Track)
Abstract and authors: (click to expand)

Abstract: Widespread climate action is urgently needed, but current solutions do not account enough for local differences. Here, we take the example of cities to point to the potential of machine learning (ML) for generating at scale high-resolution information on energy use and greenhouse gas (GHG) emissions, and make this information actionable for concrete solutions. We map the existing relevant ML literature and articulate ML methods that can make sense of spatial data for climate solutions in cities. Machine learning has the potential to find solutions that are tailored for each settlement, and transfer solutions across the world.

Authors: Nikola Milojevic-Dupont (Mercator Research Institute on Global Commons and Climate Change (MCC)); Felix Creutzig (Mercator Research Institute on Global Commons and Climate Change (MCC))

Buildings and cities Transportation
ICML 2019 The Grid Resilience & Intelligence Platform (GRIP) (Ideas Track)
Abstract and authors: (click to expand)

Abstract: Extreme weather events pose an enormous and increasing threat to the nation’s electric power systems and the associated socio-economic systems that depend on reliable delivery of electric power. The US Department of Energy reported in 2015, almost a quarter of unplanned grid outages were caused by extreme weather events and variability in the environment. Because climate change increases the frequency and severity of extreme weather events, communities everywhere will need to take steps to better prepare for, and if possible prevent major outages. While utilities have software tools available to help plan their daily and future operations, these tools do not include capabilities to help them plan for and recover from extreme events. Software for resilient design and recovery is not available commercially and research efforts in this area are preliminary. In this project, we are developing and deploying a suite of novel software tools to anticipate, absorb and recover from extreme events. The innovations in the project include the application of artificial intelligence and machine learning for distribution grid resilience, specifically, by using predictive analytics, image recognition and classification, and increased learning and problem-solving capabilities for the anticipation of grid events.

Authors: Ashley Pilipiszyn (Stanford University)

Power and energy Extreme weather events
ICML 2019 Meta-Optimization of Optimal Power Flow (Ideas Track)
Abstract and authors: (click to expand)

Abstract: The planning and operation of electricity grids is carried out by solving various forms of con- strained optimization problems. With the increasing variability of system conditions due to the integration of renewable and other distributed energy resources, such optimization problems are growing in complexity and need to be repeated daily, often limited to a 5 minute solve-time. To address this, we propose a meta-optimizer that is used to initialize interior-point solvers. This can significantly reduce the number of iterations to converge to optimality.

Authors: Mahdi Jamei (Invenia Labs); Letif Mones (Invenia Labs); Alex Robson (Invenia Labs); Lyndon White (Invenia Labs); James Requeima (Invenia Labs); Cozmin Ududec (Invenia Labs)

Power and energy Industry
ICML 2019 Learning representations to predict landslide occurrences and detect illegal mining across multiple domains (Ideas Track)
Abstract and authors: (click to expand)

Abstract: Modelling landslide occurrences is challenging due to lack of valuable prior information on the trigger. Satellites can provide crucial insights for identifying landslide activity and characterizing patterns spatially and temporally. We propose to analyze remote sensing data from affected regions using deep learning methods, find correlation in the changes over time, and predict future landslide occurrences and their potential causes. The learned networks can then be applied to generate task-specific imagery, including but not limited to, illegal mining detection and disaster relief modelling.

Authors: Aneesh Rangnekar (Rochester Institute of Technology); Matthew J Hoffman (Rochester Institute of Technology)

Disaster prediction, management, and relief Agriculture, forestry and other land use
ICML 2019 Harness the Power of Artificial intelligence and -Omics to Identify Soil Microbial Functions in Climate Change Projection (Ideas Track)
Abstract and authors: (click to expand)

Abstract: Contemporary Earth system models (ESMs) omit one of the significant drivers of the terrestrial carbon cycle, soil microbial communities. Soil microbial community not only directly emit greenhouse gasses into the atmosphere through the respiration process, but also release diverse enzymes to catalyze the decomposition of soil organic matter and determine nutrient availability for aboveground vegetation. Therefore, soil microbial community control over terrestrial carbon dynamics and their feedbacks to climate. Currently, inadequate representation of soil microbial communities in ESMs has introduced significant uncertainty in current terrestrial carbon-climate feedbacks. Mitigation of this uncertainty requires to identify functions, diversity, and environmental adaptation of soil microbial communities under global climate change. The revolution of -omics technology allows high throughput quantification of diverse soil enzymes, enabling large-scale studies of microbial functions in climate change. Such studies may lead to revolutionary solutions to predicting microbial-mediated climate-carbon feedbacks at the global scale based on gene-level environmental adaptation strategies of the microbial community. A key initial step in this direction is to identify the biogeography and environmental adaptation of soil enzyme functions based on the massive amount of data generated by -omics technologies. Here we propose to make this step. Artificial intelligence is a powerful, ideal tool for this leap forward. Our project is to integrate Artificial intelligence technologies and global -omics data to represent climate controls on microbial enzyme functions and mapping biogeography of soil enzyme functional groups at global scale. This outcome of this study will allow us to improve the representation of microbial function in earth system modeling and mitigate uncertainty in current climate projection.

Authors: Yang Song (Oak Ridge National Lab); Dali Wang (Oak Ridge National Lab); Melanie Mayes (Oak Ridge National Lab)

Climate and Earth science Carbon capture and sequestration Data presentation and management Ecosystems and natural resources