Near Real-Time Flood Mapping from Sentinel Data Using Machine Learning Techniques

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

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.

Multi-Temporal Flood Mapping and Prediction using Sentinel-1 and Landsat-8 Data Fusion

Comparative Analysis of Urban Flood Mapping Using Sentinel‐1 SAR Imagery and Machine Learning

Flood mapping using remote sensing data has the potential to play a crucial role in monitoring and assessing flood events, particularly in urban environments, where complex infrastructure creates significant challenges. While Synthetic Aperture Radar (SAR) has promising potential for flood mapping, current methods struggle in the urban landscape due to the presence of heterogeneous surfaces and complex infrastructure, which can create double‐bounce effects and alter reflectance. This research advances urban flood mapping through a comprehensive comparative analysis of traditional change detection and Machine Learning (ML) methods, including the MultiSenseRF multi‐source feature‐fusion workflow. The study analyzes five geographically distinct urban areas—Houston, Texas, USA, Dhaka, Bangladesh, Iwaki, Japan, Lumberton, North Carolina, USA, and Beira, Mozambique—during flood events to evaluate method performance across diverse urban settings. Traditional change detection methods and ML techniques were evaluated alongside integrated approaches. Combining temporal change‐detection signals with landscape features using ML improved flood‐mapping performance, with average F1 scores of about 0.75 and a range of 0.58 in dense urban areas to 0.93 in peri‐urban regions. These findings provide a robust framework for improving urban flood mapping accuracy and have significant implications for urban flood management.

Deep Learning Models for Flood Detection in Nepal: Challenges and Insights

Climate-driven increases in flood frequency and intensity have made rapid and reliable flood monitoring essential for effective emergency response. Synthetic Aperture Radar (SAR) imagery from Sentinel-1 is particularly valuable for this purpose because it operates independently of cloud cover and illumination conditions, enabling flood observation during extreme weather events. In this study, a 5-channel U-Net was developed for flood mapping in Nepal, using multi-temporal Sentinel-1 SAR data and hydrologically relevant topographic information. The input configuration combined pre-flood VV and VH backscatter, post-flood VV and VH backscatter, and Height Above the Nearest Drainage (HAND) data to improve the discrimination of flooded and non-flooded areas. The model demonstrated stable convergence during training, with continuously decreasing loss and improving Dice and IoU scores on both training and validation datasets. Quantitative evaluation showed that the proposed model achieved an Intersection over Union (IoU) of approximately 0.51, an F1-score of 0.67, precision of 0.68, recall of 0.66, near-perfect specificity, and an AUC of 0.996, indicating excellent class separability and strong suppression of false positives. Qualitative assessment further confirmed that the predicted inundation patterns were spatially coherent and closely matched the reference flood masks, although some local boundary overestimation and omission of small fragmented flood patches remained. These results demonstrate that integrating multi-temporal SAR backscatter with HAND in a U-Net framework provides a robust and operationally relevant approach for flood extent mapping in cloud-prone regions.

GEOID-Flood: A Large-Scale Multi-Modal Benchmark Dataset for Flood Segmentation

Geospatial foundation models aim to learn representations that transfer across regions and sensors, yet evaluating them on specific tasks requires large, high-quality, multi-modal benchmarks that measure how well such models extract value from data. Concerning flood mapping, existing datasets rarely combine bi-temporal SAR and co-registered optical imagery at scale, leaving the value of foundation models for this downstream task largely untested. We introduce GEOID-Flood, a large-scale multi-modal flood segmentation benchmark, derived from Copernicus Emergency Management Service activations, spanning 219 events across 65 countries over ten years. The dataset provides more than 14,000 tiles with co-registered pre- and post-event Sentinel-1, in GRD and RTC format, pre-event Sentinel-2 composite, and DEM, including manually validated labels that separate background from permanent water and flooded water. Using this benchmark, we evaluate foundation models against conventional encoders across single-image, multi-temporal, and multi-modal protocols. We report three main findings: foundation models offer a consistent but modest advantage; optical-SAR fusion with finetuning best resolves transient flooding; and models trained on GEOID-Flood transfer to unseen events better than those trained on existing datasets. Dataset and code available at https://github.com/links-ads/geoid-flood.

Unsupervised Estimation of Post-Event Standing Urban Floodwater Depth Using Aerial Imagery and Digital Terrain Models

This study proposes a fully unsupervised, training-free framework for rapid depth estimation of standing or slowly receding residual floodwater using post-event remote sensing imagery and DTMs, and offers a scalable, rapidly deployable solution for first-order flood mapping and depth estimation.