Landslide susceptibility analysis can provide theoretical support for landslide risk management. However, some susceptibility analyses are not sufficiently interpretable. Moreover, the accuracy of many research methods needs to be improved. Therefore, this study can supplement these deficiencies. This study aims to research the evaluation effects of random forest (RF) and extreme gradient boosting (XGBoost) classifier models on landslide susceptibility, and to compare their applicability in Fengjie County, Chongqing, a typical landslide‐prone area in southwest of China. Firstly, 1624 landslides information from 1980 to 2020 were obtained through field investigation, and a geospatial database of 16 conditional factors had been constructed. Secondly, non‐landslide points were selected to form a complete data set and RF and XGBoost models were established. Finally, the area under the ROC curve (AUC) value, accuracy, and F‐score were used to compare the two models. The results show that even though both classifiers have a highly accurate evaluation of landslide susceptibility, the RF model performs better. In comparison, the RF model has a higher AUC value of 0.866, and its accuracy and F‐score are approximately 2% higher than XGBoost. The land use, elevation, and lithology of Fengjie County contribute to the occurrence of landslides. This is due to human engineering activities (such as land reclamation, and housing construction) resulting in low slope stability and landslides in widely distributed sandstone, siltstone, and mudstone layers owing to their low permeability and planes of weakness.

No abstract

Reservoir bank slopes with weak interlayers are common in the Three Gorges Reservoir area. Their stabilities are affected by multi-coupled factors (e.g., reservoir water fluctuations, rainfall, and earthquakes in the reservoir area). Meanwhile, the differences in mechanical parameters of reservoir banks make it more difficult to determine the dynamic stability of bank slopes under complex mechanical environments. In this paper, the multiple disaster-causing factors and spatial variability of the landslide were comprehensively considered to study the long-term evolution trend of the bank slopes with weak interlayers. Specifically, the limit equilibrium method combined with the random field was performed to calculate the reliability. Furthermore, the long-term effects of dry-wet cycles on reservoir bank landslides and the sensitivity analysis of the statistical parameters of the random field were discussed. The results show that the earthquake action had the most significant impact on the failure probability of the landslide. The failure probability was more significantly affected by the vertical fluctuation range of the parameters and the coefficient of variation of the internal friction angle. The increase in failure probability under the action of dry-wet cycles was mainly caused by the reduction of the parameters of the weak interlayer. The reliability evaluation method of reservoir bank slopes can be applied to predict the long-term stability of the coastal banks.