Comparisons of several methods for landslide susceptibility mapping: case of the Benzilan and Waka Towns, Southwest China

被引：3

作者：

Chen J. ^{[1
]}

Peng W. ^{[1
]}

Sun X. ^{[2
]}

Wang Q. ^{[1
]}

Han X. ^{[3
]}

机构：

[1] College of Construction Engineering, Jilin University, Changchun

[2] Department of Earth Sciences and Engineering, Taiyuan University of Technology, Taiyuan

[3] Center for Hydrogeology and Environmental Geology, CGS, Baoding

来源：

Arabian Journal of Geosciences | 2021年 / 14卷 / 16期

基金：

中国国家自然科学基金;

关键词：

Bivariate statistical analysis; Evaluation precision analysis; Landslide susceptibility mapping; Multi-criteria analysis; Support vector machine;

D O I：

10.1007/s12517-021-08092-1

中图分类号：

学科分类号：

摘要：

Making accurate and effective landslide susceptibility maps (LSMs) can effectively reduce the harm of landslide disasters and provide guidance to protect people’s life and property. Choosing the appropriate modeling method is the key to establish an accurate and practical landslide susceptibility evaluation model. Therefore, in order to find the optimal modeling method, multiple mathematical statistical methods were used for landslide susceptibility mapping, and the prediction performances of the various methods were evaluated and compared. First, according to the field survey and the previous literature, 10 conditioning factors were selected as the analysis data. Second, three different bivariate statistical methods (the frequency ratio (FR), statistical index (SI), and certainty factor (CF)) were used to judge the influence of different characteristic intervals within the conditioning factors on landslide susceptibility and export the LSMs of Benzilan Town and Waka Town, in the southwest of China. The predictive precisions of the FR, SI, and CF method were 83.62%, 83.29%, and 83.55%, respectively. Third, in order to find a method with higher prediction accuracy, multi-criteria analysis methods (the analytical hierarchy process (AHP) and logistics regression (LR)) and the support vector machine (SVM) were selected to combine with bivariate statistical methods to export LSMs. A total of nine ensemble methods (AHP–FR, AHP–SI, AHP–CF, LR–FR, LR–SI, LR–CF, SVM–FR, SVM–SI, and SVM–CF) are generated. Finally, the performances of these methods were evaluated by the receiver operating characteristic curve (ROC). The result shows that the AHP, LR, and SVM methods based on the bivariate statistical methods are slightly better than the single bivariate statistical methods. The combination of the SVM model and bivariate statistical methods improves the accuracy the most, and the prediction accuracy of SVM-FR is the highest among these methods. The SVM-FR method has the highest prediction precision and is the most suitable method for landslide susceptibility evaluation. © 2021, Saudi Society for Geosciences.

引用

共 46 条

[1]

Akinwande O., Dikko H.G., Agboola S., Variance inflation factor: as a condition for the inclusion of suppressor variable(s) in regression analysis, Open J Stat, 5, pp. 754-767, (2015)

[2]

Bai S., Wang J., Lu G., Zhou P., Hou S., Xu S., GIS-based and logistic regression for landslide susceptibility mapping of Zhongxian segment in the Three Gorge area, China, Geomorphology, 115, pp. 23-31, (2010)

[3]

Byun H., Lee S.-W., A survey on pattern recognition applications of support vector machines, Int J Pattern Recognit, 17, pp. 459-486, (2003)

[4]

Can T., Nefeslioglu H.A., Gokceoglu C., Sonmez H., Duman T.Y., Susceptibility assessments of shallow earthflows triggered by heavy rainfall at three catchments by logistic regression analyses, Geomorphology, 72, pp. 250-271, (2005)

[5]

Cao C., Wang Q., Chen J., Ruan Y., Zheng L., Song S., Niu C., Landslide susceptibility mapping in vertical distribution law of precipitation area: case of the Xulong Hydropower Station Reservoir, Southwestern China, Water-Sui, 8, (2016)

[6]

Cao C., Xu P., Wang Y., Chen J., Zheng L., Niu C., Flash flood hazard susceptibility mapping using frequency ratio and statistical index methods in coalmine subsidence areas, Sustainsability-Basel, 8, (2016)

[7]

Chen W., Li W., Chai H., Hou E., Li X., Ding X., GIS-based landslide susceptibility mapping using analytical hierarchy process (AHP) and certainty factor (CF) models for the Baozhong region of Baoji City, China, Environ Earth Sci, (2016)

[8]

The Wenchuan Earthquake of 2008: Anatomy of a Disaster. Science Press: Beijing, China, Startfragmentstartfragmentendfragment, (2011)

[9]

Chen W., Li W., Hou E., Zhao Z., Deng N., Bai H., Wang D., Landslide susceptibility mapping based on GIS and information value model for the Chencang District of Baoji, China, Arab J Geosci, 7, pp. 4499-4511, (2014)

[10]

Chhetri S., Kayastha P., Manifestation of an Analytic Hierarchy Process (AHP) model on fire potential zonation mapping in Kathmandu Metropolitan City, Nepal, ISPRS Int J Geo Inf, 4, pp. 400-417, (2015)

← 1 2 3 4 5 →