Deep Learning-Based Flood Detection Using Multi-Temporal Sentinel-1 SAR Data: A Case Study in Beijing Area, 2023

Floods inflict widespread and severe damage on human lives, property, ecosystems, and economies. Remote sensing technology is crucial in monitoring flood disasters, offering critical information and data to support decision-making, disaster response planning, and resource allocation. Leveraging deep learning techniques for the timely detection and targeted response to disasters in affected areas represents a cost-effective approach to reducing economic losses resulting from flood disasters. This study utilized four Sentinel-1 Synthetic Aperture Radar (SAR) images from July to August 2023 to analyze flood disasters in Beijing and Hebei province. The research introduced a framework for flood detection. It analyzed the disaster situation in urban zones, agricultural land, and reservoir affected by the extraordinary rainfall on July 23rd in Beijing. This study offers valuable insights for effectively reducing disaster-related losses. It is a reference point for future disaster management and mitigation efforts.