Evaluation of Landslide Susceptibility to Heavy Rainfall in Sanming City,Fujian Province Based on Machine Learning Modeling
The evaluation of landslide susceptibility is a fundamental work of regional geohazard risk management.Taking the southeastern mountainous area of Sanming City in Fujian Province as the research object,we select ten influence factors,such as elevation,slope direction,slope gradient,curvature,lithology,normalized vegetation index,average rainfall,distance from faults,distance from roads,and distance from water systems,and then evaluate the landslide susceptibility by using the logistic regression model and the random forest model.The evaluation results of the model are categorized into five susceptibility level zones,namely lower,low,medium,high and higher,with the high and higher susceptibility zones being mainly located in the northeastern direction of the study area.As the study shows,AUC values of the logistic regression model and the random forest model are 0.830 and 0.862 respectively.The plausibility and accuracy of two models meet the requirement of general consistency with historical landslides,and the prediction accuracy of the random forest model is higher and the generalization ability of it is better.
万方数据
维普
