Large scale cross-regional remote sensing flood monitoring framework for operative mapping and impact analysis

2026-07-30

AI Summary

This study addresses the challenges of weak model generalization and scarce labeled data in large-scale, multi-regional remote sensing-based flood monitoring. The authors propose an end-to-end multimodal fusion framework that integrates synthetic aperture radar (SAR), multispectral imagery, digital elevation models (DEMs), and their derivatives. A novel multimodal fusion strategy tailored for data-scarce scenarios is introduced, and the performance of supervised (U-Net++) and self-supervised (AnySat) approaches is systematically compared for cross-regional flood detection. Disaster impact assessments—including affected area, casualties, and ecological and agricultural consequences—are conducted following standards from Russia’s Ministry of Emergency Situations. Applied to the 2019 Turyan River flood event, the framework yields results highly consistent with official reports, except for material loss estimates, which exhibit bias due to limitations in open-source data availability.

Abstract

Effective flood monitoring is critical for minimizing the impacts of flood disasters on populations and infrastructure. Yet reliable remote sensing across extensive and environmentally diverse regions remains challenging, as most segmentation algorithms lack the generalisation capacity required for large-scale application, while annotated flood data are scarce and unevenly distributed. This study presents an end-to-end multimodal framework for Russian Federation territories sustainable flood monitoring and damage assessment based on synthetic aperture radar data, multispectral imagery, and digital elevation models with their derivatives, forming a 21-channel input. Using a self-collected multimodal dataset covering seven Russian regions, two strategies for water surface detection under limited data conditions were compared: a supervised U-Net++ model and the self-supervised AnySat architecture pre-trained and fine-tuned for the segmentation task. Under the data conditions of this study, supervised learning proved more effective, while the AnySat-based approach offered greater stability and retains advantages for settings where larger unlabelled data or missing modalities at inference are expected. The best flood area predictions were used to estimate flood impact in urban areas in terms of the area affected, material damage, casualties, and ecological and agricultural impact. The estimations were conducted following the official methodology of the Russian Ministry of Emergency Situations. Applied to the 2019 Tulun flood, the obtained results closely matched official assessments, except for material damage, due to the open-source databases usage. The results demonstrate the potential of deep learning and multimodal satellite data integration for scalable, reliable flood monitoring across diverse environmental and data-limited conditions.

Problem

• flood monitoring
• remote sensing
• large-scale
• data scarcity
• cross-regional

Innovation

• multimodal remote sensing
• flood monitoring
• self-supervised learning
• U-Net++
• satellite data fusion