Integrating time-series InSAR deformation and LightGBM for landslide susceptibility assessment

Existing landslide susceptibility models typically rely on static predisposing factors, to effectively capture the relationship between landslides and geographic variables but neglecting dynamic features like surface deformation． Time-series interferometric synthetic aperture radar (TS-InSAR) is applied in this study to obtain line-of-sight deformation rates in Yunyang county, breaking into vertical and slope-direction components as InSAR factors． These are combined with static predisposing factors to develop a LightGBM model for landslide susceptibility． Shapley additive explanations (SHAP) algorithm is used to identify key influencing factors. It is found that 28.15% of Yunyang is moderately susceptible, with high and very high susceptibility areas concentrated along the Yangtze River, in line with historical landslide distributions． SHAP analysis highlights elevation, land use, and proximity to rivers as primary factors． Incorporation of InSAR data improves model AUC from 0.819 5 to 0.830 2, with enhanced landslide susceptibility prediction． This study confirms the significant role of time-series InSAR deformation data to improve susceptibility assessments．