A REVIEW OF REGIONAL LANDSLIDE HAZARD ASSESSMENT MODELS BASED ON DATA-DRIVEN MODELS
As one of the most common geological disasters,landslide has the characteristics of sudden,random,wide range and great harm.In this study,the advantages and limitations of the application of different models were summarized,including the data-driven regional landslide risk assessment model,models of mathematical statistics method such as information model,logistic regression model,rough set theory,evidence weight model,frequency ratio model,and entropy index model,models of machine learning method such as support vector machine,decision tree,random forest,XGboost,Catboost and neural network,and convolutional neural network model of deep learning method.Based on this,some problems existing in the data-driven regional landslide prediction model were analyzed and discussed.
NETL
NSTL
万方数据
