Performance Evaluation of Five GIS-Based Models for Landslide Susceptibility Prediction and Mapping: A Case Study of Kaiyang County, China

This study evaluated causative factors in landslide susceptibility assessments and compared the performance of five models based on certainty factor (CF), logistic regression (LR), analytic hierarchy process (AHP), coupled CF–analytic (CF-AHP), CF–logistic (CF-LR). Kaiyang County, China, has complex geological conditions frequent disasters. Based field observations, nine influencing factors, namely, altitude, slope, topographic relief, aspect, engineering rock group, slope structure, distance to faults, rivers, normalized difference vegetation index, were extracted using raster data model. The precision was tested distribution disaster points for each grade receiver operating characteristic curve. results showed that frequency ratios accounted more than 75% within high very zones according model prediction, AUC evaluating 0.853, 0.712, 0.871, 0.873, 0.895, respectively. accuracy sequencing CF-LR > CF-AHP LR CF AHP, indicating are better others. provides a reliable method mapping at county-level resolution.