IMHE OpenIR  > Journal of Mountain Science  > Journal of Mountain Science-2015  > Vol12 No.2
Using Statistical Learning Algorithms in Regional Landslide Susceptibility Zonation with Limited Landslide Field Data
WANG Yi-ting; SEIJMONSBERGEN Arie Christoffel3; BOUTEN Willem; CHEN Qing-tao
Corresponding AuthorWANG Yi-ting
2015-03
Source PublicationJournal of Mountain Science
ISSN1672-6316
Volume12Issue:2Pages:268-288
Subtype期刊论文
AbstractRegional Landslide Susceptibility Zonation (LSZ) is always challenged by the available amount of field data, especially in southwestern China where large mountainous areas and limited field information coincide. Statistical learning algorithms are believed to be superior to traditional statistical algorithms for their data adaptability. The aim of the paper is to evaluate how statistical learning algorithms perform on regional LSZ with limited field data. The focus is on three statistical learning algorithms, Logistic Regression (LR), Artificial Neural Networks (ANN) and Support Vector Machine (SVM). Hanzhong city, a landslide prone area in southwestern China is taken as a study case. Nine environmental factors are selected as inputs. The accuracies of the resulting LSZ maps are evaluated through landslide density analysis (LDA), receiver operating characteristic (ROC) curves and Kappa index statistics. The dependence of the algorithm on the size of field samples is examined by varying the sizes of the training set. The SVM has proven to be the most accurate and the most stable algorithm at small training set sizes and on all known landslide sizes. The accuracy of SVM shows a steadily increasing trend and reaches a high level at a small size of the training set, while accuracies of LR and ANN algorithms show distinct fluctuations. The geomorphological interpretations confirm the strength of SVM on all landslide sizes.Our results show that the strengths of SVM in generalization capability and model robustness make it an appropriate and efficient tool for regional LSZ with limited landslide field samples.
KeywordLandslide Susceptibility Zonation (Lsz) Logistic Regression (Lr) Artificial Neural Network (Ann) Support Vector Machine (Svm) Regional Scale Southwest China
DOI10.1007/s11629-014-3134-x
Indexed BySCI
Language英语
Citation statistics
Cited Times:10[WOS]   [WOS Record]     [Related Records in WOS]
Document Type期刊论文
Identifierhttp://ir.imde.ac.cn/handle/131551/7967
CollectionJournal of Mountain Science_Journal of Mountain Science-2015_Vol12 No.2
Corresponding AuthorWANG Yi-ting
Recommended Citation
GB/T 7714
WANG Yi-ting,SEIJMONSBERGEN Arie Christoffel3,BOUTEN Willem,et al. Using Statistical Learning Algorithms in Regional Landslide Susceptibility Zonation with Limited Landslide Field Data[J]. Journal of Mountain Science,2015,12(2):268-288.
APA WANG Yi-ting,SEIJMONSBERGEN Arie Christoffel3,BOUTEN Willem,&CHEN Qing-tao.(2015).Using Statistical Learning Algorithms in Regional Landslide Susceptibility Zonation with Limited Landslide Field Data.Journal of Mountain Science,12(2),268-288.
MLA WANG Yi-ting,et al."Using Statistical Learning Algorithms in Regional Landslide Susceptibility Zonation with Limited Landslide Field Data".Journal of Mountain Science 12.2(2015):268-288.
Files in This Item:
File Name/Size DocType Version Access License
Using Statistical Le(9190KB) 开放获取ODC PDDLView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[WANG Yi-ting]'s Articles
[SEIJMONSBERGEN Arie Christoffel3]'s Articles
[BOUTEN Willem]'s Articles
Baidu academic
Similar articles in Baidu academic
[WANG Yi-ting]'s Articles
[SEIJMONSBERGEN Arie Christoffel3]'s Articles
[BOUTEN Willem]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[WANG Yi-ting]'s Articles
[SEIJMONSBERGEN Arie Christoffel3]'s Articles
[BOUTEN Willem]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Using Statistical Learning Algorithms.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.