Monitoring the 2024 Abrupt Flood Event in East Dongting Lake via Deep Learning and Multisource Remote Sensing Data

Heavy rainfall in June 2024 caused a dramatic expansion of East Dongting Lake, located in northeastern Hunan Province, central China, and a breach occurred at Tuanzhouyuan within the lake region on July 5th. Optical remote sensing, synthetic aperture radar (SAR), and satellite altimetry provided essential data on inundation and water level changes. Using bitemporal Sentinel-1 SAR data, this study constructed a water body change detection dataset and applied the MambaBCD change detection models. The results showed that MambaBCD, based on state space models, showed superior performance, achieving an F1 score of 91.9% and demonstrates superior ability in identifying boundaries and small change areas. The inundation extent of East Dongting Lake from April to August 2024 was mapped using the MambaBCD model and bitemporal Sentinel-1 imagery. A sharp increase in inundation was observed in late June, with the water body expanding to 1142.4 ± 98 km² by July 4. In late July, the water body area began to decrease rapidly. Additionally, the latest radar altimeter, surface water and ocean topography (SWOT) surpassed Sentinel-3 in monitoring water levels, capturing a peak of 34 m in early July during this flood event, with levels returning to normal by late August. This flooding event was caused by heavy rainfall over 600 km² of cropland, with 95% of the buildings in Tuanzhouyuan being inundated, resulting in significant economic losses.