Application of coupling physics–based model TRIGRS with random forest in rainfall-induced landslide-susceptibility assessment

Most data-driven landslide-susceptibility assessment models heavily rely on statistical analyses based on geological and environmental similarity principles. These models often struggle to establish connections with landslide destruction processes and mechanisms effectively. In response to this challenge, this study introduces a hybrid approach that combines the transient rainfall infiltration, regional slope-stability physics–based model (TRIGRS) and the random forest (RF) model. Initially, to calculate the safety coefficients of the study area, the TRIGRS model was employed, and appropriate non-landslide samples were selected based on these coefficients. Subsequently, to enable learning and fitting of the nonlinear relationships between sample points and geological environmental factors, historical landslide data and safety coefficient-filtered non-landslide point data were input into the RF model, ultimately generating landslide probability values that represent the magnitude of landslide occurrences. The coupled model demonstrated excellent predictive performance using the landslides induced by the 2019 “Lekima” typhoon in Yongjia, Zhejiang Province, as a case study. The results indicated that the evaluation effect of the TRIGRS and RF coupled model was satisfactory, achieving an accuracy (ACC) rate of 77.6% and an area under the curve (AUC) of 0.873. Furthermore, the ACC and AUC of the TRIGRS and RF coupled model increased by 8.22% and 9.20%, respectively, compared with those of the traditional buffering sampling method. Therefore, the TRIGRS and RF coupled model better evaluates regional landslide susceptibility than the traditional buffering sampling method.