File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China

TitleLandslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China
Authors
KeywordsHong Kong
Landslide Susceptibility Mapping
Logistic Regression Method
One-Class Sample
Support Vector Machine (Svm)
Two-Class Sample
Issue Date2008
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/geomorph
Citation
Geomorphology, 2008, v. 101 n. 4, p. 572-582 How to Cite?
AbstractThe Support Vector Machine (SVM) is an increasingly popular learning procedure based on statistical learning theory, and involves a training phase in which the model is trained by a training dataset of associated input and target output values. The trained model is then used to evaluate a separate set of testing data. There are two main ideas underlying the SVM for discriminant-type problems. The first is an optimum linear separating hyperplane that separates the data patterns. The second is the use of kernel functions to convert the original non-linear data patterns into the format that is linearly separable in a high-dimensional feature space. In this paper, an overview of the SVM, both one-class and two-class SVM methods, is first presented followed by its use in landslide susceptibility mapping. A study area was selected from the natural terrain of Hong Kong, and slope angle, slope aspect, elevation, profile curvature of slope, lithology, vegetation cover and topographic wetness index (TWI) were used as environmental parameters which influence the occurrence of landslides. One-class and two-class SVM models were trained and then used to map landslide susceptibility respectively. The resulting susceptibility maps obtained by the methods were compared to that obtained by the logistic regression (LR) method. It is concluded that two-class SVM possesses better prediction efficiency than logistic regression and one-class SVM. However, one-class SVM, which only requires failed cases, has an advantage over the other two methods as only "failed" case information is usually available in landslide susceptibility mapping. © 2008 Elsevier B.V. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/150472
ISSN
2023 Impact Factor: 3.1
2023 SCImago Journal Rankings: 1.056
ISI Accession Number ID
Funding AgencyGrant Number
Research Grants CouncilHKU 7176/05E
Funding Information:

The authors would like to thank Jack Shroder, Blaz Komac and Takashi Oguchi for useful comments which improved the manuscript. The financial support of the Research Grants Council (Project No. HKU 7176/05E) is also acknowledged.

References
Grants

 

DC FieldValueLanguage
dc.contributor.authorYao, Xen_US
dc.contributor.authorTham, LGen_US
dc.contributor.authorDai, FCen_US
dc.date.accessioned2012-06-26T06:04:59Z-
dc.date.available2012-06-26T06:04:59Z-
dc.date.issued2008en_US
dc.identifier.citationGeomorphology, 2008, v. 101 n. 4, p. 572-582en_US
dc.identifier.issn0169-555Xen_US
dc.identifier.urihttp://hdl.handle.net/10722/150472-
dc.description.abstractThe Support Vector Machine (SVM) is an increasingly popular learning procedure based on statistical learning theory, and involves a training phase in which the model is trained by a training dataset of associated input and target output values. The trained model is then used to evaluate a separate set of testing data. There are two main ideas underlying the SVM for discriminant-type problems. The first is an optimum linear separating hyperplane that separates the data patterns. The second is the use of kernel functions to convert the original non-linear data patterns into the format that is linearly separable in a high-dimensional feature space. In this paper, an overview of the SVM, both one-class and two-class SVM methods, is first presented followed by its use in landslide susceptibility mapping. A study area was selected from the natural terrain of Hong Kong, and slope angle, slope aspect, elevation, profile curvature of slope, lithology, vegetation cover and topographic wetness index (TWI) were used as environmental parameters which influence the occurrence of landslides. One-class and two-class SVM models were trained and then used to map landslide susceptibility respectively. The resulting susceptibility maps obtained by the methods were compared to that obtained by the logistic regression (LR) method. It is concluded that two-class SVM possesses better prediction efficiency than logistic regression and one-class SVM. However, one-class SVM, which only requires failed cases, has an advantage over the other two methods as only "failed" case information is usually available in landslide susceptibility mapping. © 2008 Elsevier B.V. All rights reserved.en_US
dc.languageengen_US
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/geomorphen_US
dc.relation.ispartofGeomorphologyen_US
dc.subjectHong Kongen_US
dc.subjectLandslide Susceptibility Mappingen_US
dc.subjectLogistic Regression Methoden_US
dc.subjectOne-Class Sampleen_US
dc.subjectSupport Vector Machine (Svm)en_US
dc.subjectTwo-Class Sampleen_US
dc.titleLandslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, Chinaen_US
dc.typeArticleen_US
dc.identifier.emailTham, LG:hrectlg@hkucc.hku.hken_US
dc.identifier.authorityTham, LG=rp00176en_US
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1016/j.geomorph.2008.02.011en_US
dc.identifier.scopuseid_2-s2.0-52949147068en_US
dc.identifier.hkuros212152-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-52949147068&selection=ref&src=s&origin=recordpageen_US
dc.identifier.volume101en_US
dc.identifier.issue4en_US
dc.identifier.spage572en_US
dc.identifier.epage582en_US
dc.identifier.eissn1872-695X-
dc.identifier.isiWOS:000260897100004-
dc.publisher.placeNetherlandsen_US
dc.relation.projectField monitoring and modeling of hydrological processes of a hillslope prone to landsliding-
dc.identifier.scopusauthoridYao, X=7402530301en_US
dc.identifier.scopusauthoridTham, LG=7006213628en_US
dc.identifier.scopusauthoridDai, FC=7102055666en_US
dc.identifier.issnl0169-555X-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats