Deep Neural Network Framework for Inverting Remotely Sensed CO2 Measurements (Papers Track)
Garvit Agarwal (IISER, Pune); shailesh deshpande (Tata Research Development and Design Centre, Tata Consultancy Services)
Abstract
We propose a deep learning framework for the inversion of CO2 concentration measurements from satellites to estimate the CO2 emissions. Our algorithm starts with informed guess of emission distributions of CO2 and keeps on correcting it till it is consistent with outcome of transportation model and CO2 measurements by satellite. We found that our inversion method is capable of identifying emission sources of CO2 that are not considered in the prior.