Comparison of two optimized machine learning models for predicting displacement of rainfall-induced landslide: A case study in Sichuan Province, China

详细信息    查看全文

• 作者：Xing Zhu^a ; ^b ; Qiang Xu^a ; ^{xuqiang_68@126.com} ; Minggao Tang^a ; Wen Nie^b ; Shuqi Ma^b ; Zhipeng Xu^c
• 关键词：Genetic Algorithm ; Least Squares Support Vector Machines ; Double Exponential Smoothing ; Landslide ; High-accuracy prediction
• 刊名：Engineering Geology
• 出版年：2017
• 出版时间：23 February 2017
• 年：2017
• 卷：218
• 期：Complete
• 页码：213-222
• 全文大小：2106 K
• 卷排序：218

文摘

A hybrid model is proposed to predict displacement of rainfall-triggered landslide. It includes Least Square Support Vector Machines and Double Exponential Smoothing. Hodrick-Prescott filter decomposes displacement into periodic and trend components. The models show high accuracy.