Deep Learning for Remote Sensing to Improve Flood Inundation Mapping
2026-06-01 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors developed a new method to remove clouds from satellite images used for flood mapping, because clouds often block the view during heavy rain. Their approach uses a type of AI called Denoising Diffusion Probabilistic Models combined with Masked Diffusion Transformers to fill in the cloud-covered parts more accurately. Trained on real flood images, their method produces clearer and more accurate images of flooded areas while keeping important water details intact. This improves the ability to monitor floods continuously and better supports disaster management efforts.
Flood inundation mappingOptical satellite imageryCloud removalDenoising Diffusion Probabilistic ModelsMasked Diffusion TransformerSelf-attention mechanismMultispectral imagingSentinel-2BFlood detectionHydrological consistency
Authors
Yogesh Bhattarai, Vijay Chaudhary, Wai Lim Kim, Sanjib Sharma
Abstract
Flooding is the most pervasive natural disaster worldwide. Timely and accurate flood inundation mapping are essential for informing disaster risk management. Optical satellite missions provide high-resolution, multispectral observations critical for flood detection and inundation mapping. However, their operational utility is severely constrained by cloud cover during extreme precipitation events. Conventional cloud-removal techniques based on temporal compositing or interpolation often fail to capture inundation dynamics. In this study, we introduce a cloud-removal framework for flood imagery based on Denoising Diffusion Probabilistic Models, leveraging the Masked Diffusion Transformer architecture. The proposed approach exploits self-attention mechanisms to capture wider spatial context and employs masked token modeling to explicitly learn the reconstruction of cloud-obscured regions. Trained on multispectral Sentinel-2B flood scenes with realistic cloud patterns, the model generates cloud-free image realizations that preserve both visual fidelity and hydrological consistency. Reconstruction performance is evaluated using standard image quality metrics alongside flood-specific hydrological measures, demonstrating improved continuity of water bodies and preservation of spectral signatures critical for water detection indices. The results indicate that diffusion-based generative modeling offers a robust and physically consistent alternative for cloud removal in optical flood monitoring, enabling more reliable, continuous observations to support disaster risk management and flood-related decision making.