Landslide Hazard Assessment Under Record-Breaking Extreme Rainfall: Integration of SBAS-InSAR and Machine Learning Models

Global climate change has led to a marked increase in the frequency of record-breaking extreme rainfall events, which often surpass historical benchmarks and pose significant challenges to conventional geological hazard risk assessment methods. This study used a record-breaking extreme rainfall event in Zhenba County, Shaanxi Province, in July 2023 as a case study to develop a tailored risk assessment framework for geological hazards under extreme rainfall conditions. By integrating high-resolution Planet satellite imagery, millimeter-scale surface deformation data derived from SBAS-InSAR, and detailed field investigation results, a comprehensive disaster inventory containing 1012 landslides was compiled. The proposed framework integrates cumulative extreme rainfall metrics with subtle ground deformation indicators and applies four advanced machine learning algorithms—DNN, XGBoost, RF, and LightGBM—for multidimensional hazard assessment. Among these, the DNN model exhibited the highest performance, achieving an AUC of 0.82 and Kappa coefficients of 0.833 (training) and 0.812 (prediction). Further analysis using SHAP values identified distance to rivers, cumulative rainfall, and the Topographic Wetness Index (TWI) as the most influential factors governing landslide occurrence under extreme rainfall conditions. Validation using representative case studies confirmed that the framework effectively identifies high-hazard zones, particularly in areas severely impacted by debris flows and landslide deformation zones. These findings provide a robust scientific foundation and technical basis for early warning, disaster prevention, and mitigation strategies in geologically complex regions increasingly affected by extreme rainfall events.