期刊
GEOMORPHOLOGY
卷 297, 期 -, 页码 69-85出版社
ELSEVIER
DOI: 10.1016/j.geomorph.2017.09.007
关键词
Landslide spatial modeling; ANFIS-FR; GAM; SVM; China
资金
- China Postdoctoral Science Foundation [2017M613168]
- Shaanxi Provincial Education Department [17JK0511]
- Shandong Provincial Key Laboratory of Depositional Mineralization AMP
- Sedimentary Minerals [DMSM2017029]
The spatial prediction of landslide susceptibility is an important prerequisite for the analysis of landslide hazards and risks inany area. This research uses three data mining techniques, such as an adaptive neuro-fuzzy inference system combined with frequency ratio (ANFIS-FR), a generalized additive model (GAM), and a support vector machine (SVM), for landslide susceptibility mapping in Hanyuan County,. China. In the first step, in accordance with a review of the previous literature, twelve conditioning factors, including slope aspect, altitude, slope angle, topographic wetness index (TWI), plan curvature, profile curvature, distance to rivers, distance to faults, distance to roads, land use, normalized difference vegetation index (NDVI), and lithology, were selected. In the second step, a collinearity test and correlation analysis between the conditioning factors and landslides were applied. In the third step, we used three advanced methods, namely, ANFIS-FR, GAM, and SVM, for landslide susceptibility modeling. Subsequently, the results of their accuracy were validated using a receiver operating characteristic curve. The results showed that all three models have good prediction capabilities, while the SVM model has the highest prediction rate of 0.875, followed by the ANFIS-FR and GAM models with prediction rates of 0.851 and 0.846, respectively. Thus, the landslide susceptibility maps produced in the study area can be applied for management of hazards and risks in landslide-prone Hanyuan County. (C) 2017 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据