Abstract: Located in Boai County of Jiaozuo City, the Qingtian River Scenic Area is prone to disaster due to the dual factors of natural conditions and human construction activities. In the summer of 2021, extreme weather occurred on July 20 and September 30, resulting in frequent geological disasters in the scenic area. Although the sizes of disaster sites are not big enough, hidden and sudden disasters can cause great damage to the personnel and facilities in the area, therefore the study on the assessment of geological disaster vulnerability is of great significance. Based on the comparison between two-period remote sensing image data and field survey verification before and after the storm, and timely acquisition of the disaster site data after the storm, the geological disaster susceptibility evaluation model is established through the construction of random forest (RF) model by the support vector machine (SVM) learning model based on multiple kernel functions. Based on the comprehensive consideration of regional background of the area, seven eigenfactors are selected from natural and human activity conditions and processed as input values for model training, and four SVM kernel functions including linear, poly, rbf and sigmoid are used respectively for model training to generate 40 SVM models. Four RF models are obtained by selecting four different model parameter seeds. Finally, the weighted fusion of two predicted model results is made to get the prediction probability of final model, and the prediction results are output and partitioned in GIS, so as to ensure the stability of the model and avoid overfitting. The zoning results are consistent with the distribution rule of disaster sites in the area, which can simulate the regularity of disaster susceptibility well, fill in the detailed study of disaster susceptibility, and provide valuable basis for scientific prevention of disaster in Qingtian River Scenic Area.