Abstract: [Objective] Rainfall is one of the important factors that induce geological disasters such as landslides and collapses, posing a great threat to the safety of people's lives and property. Therefore, it is necessary to take effective prevention and control measures as well as to avoid and relocate. [Methods] This article takes Yezhi Town as the study area, the grid unit is used as the evaluation unit. 9 evaluation factors including elevation, land use type, slope, aspect, elevation, landform type, engineering geological rock group, land use type, distance from river, distance from fault, curvature were selected. Using Pearson correlation analysis, the correlation between the 9 factors is weak, can participate in subsequent calculations. The Random Forest algorithm was used to analyze the feature importance of 9 factors, based on the feature importance, obtain a weighted information model that combines subjective and objective factors, using this model as a susceptibility evaluation for collapses and landslides. Then select rainfall as the risk assessment factor. Predicting the rainfall of the study area once in 10 years, once in 20 years, once in 50 years, once in 100 years through calculation and P-III curve, and import the data into ArcGIS, utilizing the raster calculator function, four different rainfall conditions were obtained. Then superimposing the rainfall conditions and the susceptibility assessment model to obtain the risk assessment. [Results] According to the statistics, he susceptibility assessment results are divided into four levels using the natural discontinuity method: low, medium, high, and extremely high susceptibility areas, which occupied 32.8%, 34.02%, 21.96% and 11.22% of the study area respectively. ROC curve was used to verify the accuracy, and the AUC value was 89.2%, falling into a better range. The risk assessment results of the four rainfall conditions were divided into four grades according to a certain range: low, medium, high and extremely high risk zones. The results of geological hazard risk assessment under different rainfall conditions is determined. [Conclusion] By comparing with the actual investigation, the landslide and collapse risk assessment results under different rainfall conditions are highly consistent with the actual situation. This article can provide a basis for reasonable disaster prevention and mitigation, as well as risk avoidance and relocation. Subsequently, a comparative analysis will be conducted on the selection of evaluation units to select the most suitable evaluation unit for the study area. I will also apply InSAR to identify hidden danger points of geological disasters in high altitude areas that are difficult for people to reach in the study area, and apply hidden danger point data to the susceptibility evaluation and risk assessment system.