Daily Flood Mapping at 90 m Resolution Through Physically-Constrained CYGNSS–SAR Fusion
Abstract
Satellite flood mapping faces a fundamental spatiotemporal trade-off: Synthetic Aperture Radar (SAR) missions provide high-resolution flood masks but revisit any given location only every 6–12 days, while GNSS Reflectometry observations from the CYGNSS constellation are available daily but at kilometer scale. Neither sensor alone suffices to track flood events evolving over 24–72 hours. We propose a physically-constrained deep learning framework that fuses daily CYGNSS inundation signals with Sentinel-1 SAR temporal anchors, conditioned on MERIT Hydro topographic variables, to produce daily flood maps at 90 m resolution. Flood observations are organized as temporal triplets (A→B→C), where B is the target date and A and C are SAR acquisitions bracketing B by 5–7 days. A temporal U-Net with three parallel encoding branches and learnable cross-attention gates fuses these inputs into spatially explicit flood probability maps. Trained and evaluated on a 47,653-tile dataset spanning seven flood-prone regions across three continents and seven years (2019–2025), the framework achieves a micro-averaged IoU of 0.703, outperforming the SARonly state of the art (IoU = 0.67) despite solving a harder downscaling problem. Ablation establishes that SAR temporal anchors dominate performance, while the CYGNSS contribution is driven by the climatological anomaly channel and peaks on moderately fast-changing flood scenes. A conditional diffusion model trained as a post-processing module produces calibrated ensemble flood maps with spatially explicit uncertainty estimates, a capability absent from existing operational systems. The framework is designed for direct transfer to the NASA-ISRO NISAR L-band mission, extending applicability to forested tropical floodplains inaccessible to C-band SAR.
Related
- Physically constrained Mamba forecasting supports multiobjective reservoir water quality decisions
- Technical note: A physically based correction of WRF temperature using atmospheric lapse rates for high-resolution hydrological simulations in a glacierized catchment
- Automatic mapping of urban heat islands based on high-resolution climate simulations with application to French cities
- High-resolution mapping of pluvial flooding in ungauged agricultural catchments
- High-resolution mapping of urban wet-bulb temperature and its intra-urban variability: A London case study
BibTeX
@misc{malandrin2026daily,
title = {{Daily Flood Mapping at 90 m Resolution Through Physically-Constrained CYGNSS–SAR Fusion}},
author = {Gauthier Malandrin and Cynthia Gerlein-Safdi},
howpublished = {EarthArXiv},
year = {2026},
month = sep,
doi = {10.31223/x5222g},
url = {https://eartharxiv.org/repository/view/14940/},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Daily Flood Mapping at 90 m Resolution Through Physically-Constrained CYGNSS–SAR Fusion
AU - Gauthier Malandrin
AU - Cynthia Gerlein-Safdi
PY - 2026
DA - 2026/09/11
PB - EarthArXiv
DO - 10.31223/x5222g
UR - https://eartharxiv.org/repository/view/14940/
AB - Satellite flood mapping faces a fundamental spatiotemporal trade-off: Synthetic Aperture Radar (SAR) missions provide high-resolution flood masks but revisit any given location only every 6–12 days, while GNSS Reflectometry observations from the CYGNSS constellation are available daily but at kilometer scale. Neither sensor alone suffices to track flood events evolving over 24–72 hours. We propose a physically-constrained deep learning framework that fuses daily CYGNSS inundation signals with Sentinel-1 SAR temporal anchors, conditioned on MERIT Hydro topographic variables, to produce daily flood maps at 90 m resolution. Flood observations are organized as temporal triplets (A→B→C), where B is the target date and A and C are SAR acquisitions bracketing B by 5–7 days. A temporal U-Net with three parallel encoding branches and learnable cross-attention gates fuses these inputs into spatially explicit flood probability maps. Trained and evaluated on a 47,653-tile dataset spanning seven flood-prone regions across three continents and seven years (2019–2025), the framework achieves a micro-averaged IoU of 0.703, outperforming the SARonly state of the art (IoU = 0.67) despite solving a harder downscaling problem. Ablation establishes that SAR temporal anchors dominate performance, while the CYGNSS contribution is driven by the climatological anomaly channel and peaks on moderately fast-changing flood scenes. A conditional diffusion model trained as a post-processing module produces calibrated ensemble flood maps with spatially explicit uncertainty estimates, a capability absent from existing operational systems. The framework is designed for direct transfer to the NASA-ISRO NISAR L-band mission, extending applicability to forested tropical floodplains inaccessible to C-band SAR.
ER -