Abstract: The frequent occurrence of geological disasters poses severe impacts on the social economy and urban development, presenting a significant threat to human lives and property. Therefore, accurate assessment of geological disaster susceptibility is crucial for disaster prevention and urban spatial planning. The Bailong River Basin is characterized by steep slopes, high relative relief, deep incised valleys, and weak lithologic features, along with a complex regional dynamic environment and extreme climatic conditions, making it a highly prone area for geological disasters in China. In this paper, nine evaluation factors, including elevation, lithology, relief, river buffer distance, fault buffer distance, slope, aspect, and slope type, are selected. The Weight of Evidence (WOE) model,Support Vector Machine (SVM), WOE-SVM coupled model, Random Forest (RF) model, and WOE-RF coupled model are used to study the susceptibility assessment model of landslide and collapse disasters, and the prediction effects of these models are compared and analyzed. The results indicate that the prediction accuracy of the machine learning-based susceptibility models is significantly improved compared to the WOE model. The AUC of the coupled models reaches a maximum of 0.9999, with 98% of geological disasters occurring in high and medium susceptibility zones. The assessment results are consistent with the spatial location distribution of disasters. The WOE-RF coupled model demonstrates the highest prediction accuracy, exhibiting superior predictive performance and generalization capability. The assessment result is more suitable as a reference for disaster prevention and long-term major project planning and construction.