Buchumschlag

Mapping global floods with 10 years of satellite radar data

Gespeichert in:
Veröffentlicht in:Nature Communications vol. 16, no. 1 (2025), p. 5762
1. Verfasser: Misra, Amit
Weitere Verfasser: White, Kevin, Nsutezo, Simone Fobi, Straka, William, Lavista, Juan
Veröffentlicht:
Nature Publishing Group
Schlagworte:
Europe
Climate change
Surface water
Deep learning
Datasets
Flood damage
Trends
Radar
Radar data
Floods
Cloud cover
Flood mapping
Satellite imagery
Historic floods
Disaster management
Radar imaging
Monitoring
Disasters
Predictions
Synthetic aperture radar
Sensors
Maps
Mapping
Emergency communications systems
Archives & records
Satellite observation
Public access
Real time
Satellites
Flood predictions
Environmental
Online-Zugang:Citation/Abstract
Full Text
Full Text - PDF
Tags: Tag hinzufügen
Keine Tags, Fügen Sie das erste Tag hinzu!
Abstract:Floods cause extensive global damage annually, making effective monitoring essential. While satellite observations have proven invaluable for flood detection and tracking, comprehensive global flood datasets spanning extended time periods remain scarce. In this study, we introduce a deep learning flood detection model that leverages the cloud-penetrating capabilities of Sentinel-1 Synthetic Aperture Radar (SAR) satellite imagery, enabling consistent flood extent mapping through cloud cover and in both day and night conditions. By applying this model to 10 years of SAR data, we create a unique, longitudinal global flood extent dataset with predictions unaffected by cloud coverage, offering comprehensive and consistent insights into historically flood-prone areas over the past decade. We use our model predictions to identify historically flood-prone areas in Ethiopia and demonstrate real-time disaster response capabilities during the May 2024 floods in Kenya. Additionally, our longitudinal analysis reveals potential increasing trends in global flood extent over time, although further validation is required to explore links to climate change. To maximize impact, we provide public access to both our model predictions and a code repository, empowering researchers and practitioners worldwide to advance flood monitoring and enhance disaster response strategies.Analysis of 10 years of satellite radar data with a deep learning model reveals historical flood patterns often missed in prior datasets. This dataset also enables analysis of trends in flooding, showing hints of increases in flood extent over time.
ISSN:2041-1723
DOI:10.1038/s41467-025-60973-1
Quelle:Health & Medical Collection