Comparison of model evaluation indicators.

Landslides are frequent and hazardous geological disasters, posing significant risks to human safety and infrastructure. Accurate assessments of landslide susceptibility are crucial for risk management and mitigation. However, geological surveys of landslide areas are typically conducted at the township level, have lowsample sizes, and rely on experience. This study proposes a framework for assessing landslide susceptibility in Taiping Township, Zhejiang Province, China, using data balancing, machine learning, and data from 1,325 slope units with nine slope characteristics. The dataset was balanced using the Synthetic Minority Oversampling Technique and the Tomek link undersampling method (SMOTE-Tomek). A comparative analysis of six machine learning models was performed, and the SHapley Additive exPlanation (SHAP) method was used to assess the influencing factors. The results indicate that the machine learning algorithms provide high accuracy, and the random forest (RF) algorithm achieves the optimum model accuracy (0.791, F1 = 0.723). The very low, low, medium, and high sensitivity zones account for 92.27%, 5.12%, 1.78%, and 0.83% of the area, respectively. The height of cut slopes has the most significant impact on landslide sensitivity, whereas the altitude has a minor impact. The proposed model accurately assesses landslide susceptibility at the township scale, providing valuable insights for risk management and mitigation.