Tracking and predicting post-Disaster structural resilience via physics-informed deep learning and polarimetric SAR (resaerch data)

The study investigates the impact of extreme rainfall-induced landslides on vegetation dynamics, using Sentinel-1 dual-polarization SAR data to analyze surface vegetation changes before and after a major rainfall event in Longchuan County, Guangdong Province, China. The dataset provided here includes the following components: 1. Downscaled Rainfall Data 2. Vegetation Scattering Descriptors Dataset 3. Urban Area Identification Results The dataset is intended to support research on vegetation growth monitoring before and after the disasters, as well as post-disaster vegetation recovery using remote sensing technology. It aims to provide valuable data for enhancing land use planning, disaster risk management, and environmental governance, particularly in areas prone to rainfall-induced landslides. Researchers and environmental planners can utilize this data to improve strategies for ecosystem restoration and resilience.