Theory-Guided Deep Learning with AlphaEarth Embeddings for Flash Flood Prediction in Data-Scarce Regions (Papers Track)

Hassan Ashfaq (Ghulam Ishaq Khan Institute of Engineering Sciences and Technology); Muhammad Arsal (Ghulam Ishaq Khan Institute of Engineering Sciences and Technolo); Anas Ashfaq (Cornell University)

Paper PDF Slides PDF Poster File Cite
Computer Vision & Remote Sensing Cities & Urban Planning Disaster Management and Relief Earth Observation & Monitoring Climate Science & Modeling Extreme Weather Active Learning Generative Modeling Hybrid Physical Models Interpretable ML

Abstract

Flash floods are increasing in frequency and intensity due to climate change, yet reliable prediction remains difficult in regions with sparse hydrometeorological observations. Traditional hydrological models struggle without dense gauge networks, while purely data-driven approaches often produce implausible outputs. In this work, we introduce a theory-guided deep learning framework that integrates physics-inspired constraints with AlphaEarth satellite embeddings, a newly released global representation of multi-sensor Earth observation data available in Google Earth Engine. Our model combines dynamic drivers (rainfall, antecedent soil moisture) with static context (topography, land cover, and AlphaEarth embeddings) while enforcing monotonicity with rainfall, topographic consistency, and a rainfall–runoff budget. Using Sentinel-1 SAR flood masks from Pakistan as ground truth, we demonstrate that AlphaEarth embeddings improve spatial detail, and physics constraints enhance both accuracy and calibration. Our results highlight the potential of embedding-driven, physics-consistent ML to support climate adaptation by enabling trustworthy flood prediction in data-scarce regions.