A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility

详细信息    查看全文

• 作者：Wei Chen^a ; ^{chenwei.0930@163.com} ; Xiaoshen Xie^a ; Jiale Wang^a ; Biswajeet Pradhan^b ; ^c ; Haoyuan Hong^d ; ^{honghaoyuan333@gmail.com} ; ^{hong_haoyuan@outlook.com} ; Dieu Tien Bui^e ; Zhao Duan^a ; Jianquan Ma^a
• 关键词：Logistic model tree ; Random forest ; Classification and regression tree ; Landslide ; China
• 刊名：CATENA
• 出版年：2017
• 出版时间：April 2017
• 年：2017
• 卷：151
• 期：Complete
• 页码：147-160
• 全文大小：3301 K
• 卷排序：151

文摘

In this paper, LMT, RF, and CART models were compared for landslide prediction. LSVM method was used to select the conditioning factors. RF shows the best results in landslide prediction.