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

The 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 s...

Full description

Saved in:
Bibliographic Details
Published in:Geomorphology (Amsterdam, Netherlands) Netherlands), 2008-11, Vol.101 (4), p.572-582
Main Authors: Yao, X., Tham, L.G., Dai, F.C.
Format: Article
Language:English
Subjects:
Earth sciences
Earth, ocean, space
Engineering and environment geology. Geothermics
Exact sciences and technology
Geomorphology, landform evolution
Hong Kong
Landslide susceptibility mapping
Logistic regression method
Marine and continental quaternary
Natural hazards: prediction, damages, etc
One-class sample
Support Vector Machine (SVM)
Surficial geology
Two-class sample
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-a396t-d9adb6345e9aacd0d7245794f5b9658f3d65364d953f95df4aab819bfdafd3b63
cites cdi_FETCH-LOGICAL-a396t-d9adb6345e9aacd0d7245794f5b9658f3d65364d953f95df4aab819bfdafd3b63
container_end_page 582
container_issue 4
container_start_page 572
container_title Geomorphology (Amsterdam, Netherlands)
container_volume 101
creator Yao, X.
Tham, L.G.
Dai, F.C.
description The 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.
doi_str_mv 10.1016/j.geomorph.2008.02.011
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_proquest_miscellaneous_21059547</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S0169555X08000585</els_id><sourcerecordid>21059547</sourcerecordid><originalsourceid>FETCH-LOGICAL-a396t-d9adb6345e9aacd0d7245794f5b9658f3d65364d953f95df4aab819bfdafd3b63</originalsourceid><addsrcrecordid>eNqFkE1P3DAQhi3USmxp_0LlC5xIsJPYiTmBVrRU3aqHfoibNfEHeJWNXduptP--Xi3lymXm8rzvaB6EPlJSU0L51bZ-NH7nY3iqG0KGmjQ1ofQErejQNxUX7OENWhVQVIyxh1P0LqUtIaTrBVmhvIFZp8lpg9OSlAnZjW5yeY93EIKbH_EIyWjsZ_xjCcHHjH8blX3E30A9udlc41usCoJTXvT-wM2QlwgTTpMPJmFv8b0vPV_LuMTrkoH36K2FKZkPz_sM_fp093N9X22-f_6yvt1U0AqeKy1Aj7ztmBEAShPdNx3rRWfZKDgbbKs5a3mnBWutYNp2AONAxWg1WN2W5Bm6OPaG6P8sJmW5c-XHaYLZ-CXJhhImWNcXkB9BFX1K0VgZottB3EtK5EGy3Mr_kuVBsiSNLJJL8Pz5AiQFk40wK5de0g0ZKOFkKNzNkTPl3b_ORJmUM7My2sWiU2rvXjv1D6XdmEQ</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>21059547</pqid></control><display><type>article</type><title>Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China</title><source>ScienceDirect Freedom Collection 2022-2024</source><creator>Yao, X. ; Tham, L.G. ; Dai, F.C.</creator><creatorcontrib>Yao, X. ; Tham, L.G. ; Dai, F.C.</creatorcontrib><description>The 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.</description><identifier>ISSN: 0169-555X</identifier><identifier>EISSN: 1872-695X</identifier><identifier>DOI: 10.1016/j.geomorph.2008.02.011</identifier><language>eng</language><publisher>Amsterdam: Elsevier B.V</publisher><subject>Earth sciences ; Earth, ocean, space ; Engineering and environment geology. Geothermics ; Exact sciences and technology ; Geomorphology, landform evolution ; Hong Kong ; Landslide susceptibility mapping ; Logistic regression method ; Marine and continental quaternary ; Natural hazards: prediction, damages, etc ; One-class sample ; Support Vector Machine (SVM) ; Surficial geology ; Two-class sample</subject><ispartof>Geomorphology (Amsterdam, Netherlands), 2008-11, Vol.101 (4), p.572-582</ispartof><rights>2008 Elsevier B.V.</rights><rights>2009 INIST-CNRS</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-a396t-d9adb6345e9aacd0d7245794f5b9658f3d65364d953f95df4aab819bfdafd3b63</citedby><cites>FETCH-LOGICAL-a396t-d9adb6345e9aacd0d7245794f5b9658f3d65364d953f95df4aab819bfdafd3b63</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>315,786,790,27957,27958</link.rule.ids><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&amp;idt=20810608$$DView record in Pascal Francis$$Hfree_for_read</backlink></links><search><creatorcontrib>Yao, X.</creatorcontrib><creatorcontrib>Tham, L.G.</creatorcontrib><creatorcontrib>Dai, F.C.</creatorcontrib><title>Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China</title><title>Geomorphology (Amsterdam, Netherlands)</title><description>The 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.</description><subject>Earth sciences</subject><subject>Earth, ocean, space</subject><subject>Engineering and environment geology. Geothermics</subject><subject>Exact sciences and technology</subject><subject>Geomorphology, landform evolution</subject><subject>Hong Kong</subject><subject>Landslide susceptibility mapping</subject><subject>Logistic regression method</subject><subject>Marine and continental quaternary</subject><subject>Natural hazards: prediction, damages, etc</subject><subject>One-class sample</subject><subject>Support Vector Machine (SVM)</subject><subject>Surficial geology</subject><subject>Two-class sample</subject><issn>0169-555X</issn><issn>1872-695X</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><recordid>eNqFkE1P3DAQhi3USmxp_0LlC5xIsJPYiTmBVrRU3aqHfoibNfEHeJWNXduptP--Xi3lymXm8rzvaB6EPlJSU0L51bZ-NH7nY3iqG0KGmjQ1ofQErejQNxUX7OENWhVQVIyxh1P0LqUtIaTrBVmhvIFZp8lpg9OSlAnZjW5yeY93EIKbH_EIyWjsZ_xjCcHHjH8blX3E30A9udlc41usCoJTXvT-wM2QlwgTTpMPJmFv8b0vPV_LuMTrkoH36K2FKZkPz_sM_fp093N9X22-f_6yvt1U0AqeKy1Aj7ztmBEAShPdNx3rRWfZKDgbbKs5a3mnBWutYNp2AONAxWg1WN2W5Bm6OPaG6P8sJmW5c-XHaYLZ-CXJhhImWNcXkB9BFX1K0VgZottB3EtK5EGy3Mr_kuVBsiSNLJJL8Pz5AiQFk40wK5de0g0ZKOFkKNzNkTPl3b_ORJmUM7My2sWiU2rvXjv1D6XdmEQ</recordid><startdate>20081101</startdate><enddate>20081101</enddate><creator>Yao, X.</creator><creator>Tham, L.G.</creator><creator>Dai, F.C.</creator><general>Elsevier B.V</general><general>Elsevier</general><scope>IQODW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7UA</scope><scope>C1K</scope><scope>F1W</scope><scope>H96</scope><scope>L.G</scope></search><sort><creationdate>20081101</creationdate><title>Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China</title><author>Yao, X. ; Tham, L.G. ; Dai, F.C.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a396t-d9adb6345e9aacd0d7245794f5b9658f3d65364d953f95df4aab819bfdafd3b63</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Earth sciences</topic><topic>Earth, ocean, space</topic><topic>Engineering and environment geology. Geothermics</topic><topic>Exact sciences and technology</topic><topic>Geomorphology, landform evolution</topic><topic>Hong Kong</topic><topic>Landslide susceptibility mapping</topic><topic>Logistic regression method</topic><topic>Marine and continental quaternary</topic><topic>Natural hazards: prediction, damages, etc</topic><topic>One-class sample</topic><topic>Support Vector Machine (SVM)</topic><topic>Surficial geology</topic><topic>Two-class sample</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Yao, X.</creatorcontrib><creatorcontrib>Tham, L.G.</creatorcontrib><creatorcontrib>Dai, F.C.</creatorcontrib><collection>Pascal-Francis</collection><collection>CrossRef</collection><collection>Water Resources Abstracts</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy &amp; Non-Living Resources</collection><collection>Aquatic Science &amp; Fisheries Abstracts (ASFA) Professional</collection><jtitle>Geomorphology (Amsterdam, Netherlands)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Yao, X.</au><au>Tham, L.G.</au><au>Dai, F.C.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China</atitle><jtitle>Geomorphology (Amsterdam, Netherlands)</jtitle><date>2008-11-01</date><risdate>2008</risdate><volume>101</volume><issue>4</issue><spage>572</spage><epage>582</epage><pages>572-582</pages><issn>0169-555X</issn><eissn>1872-695X</eissn><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>The 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.</abstract><cop>Amsterdam</cop><pub>Elsevier B.V</pub><doi>10.1016/j.geomorph.2008.02.011</doi><tpages>11</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0169-555X
ispartof Geomorphology (Amsterdam, Netherlands), 2008-11, Vol.101 (4), p.572-582
issn 0169-555X
1872-695X
language eng
recordid cdi_proquest_miscellaneous_21059547
source ScienceDirect Freedom Collection 2022-2024
subjects Earth sciences
Earth, ocean, space
Engineering and environment geology. Geothermics
Exact sciences and technology
Geomorphology, landform evolution
Hong Kong
Landslide susceptibility mapping
Logistic regression method
Marine and continental quaternary
Natural hazards: prediction, damages, etc
One-class sample
Support Vector Machine (SVM)
Surficial geology
Two-class sample
title Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T09%3A30%3A31IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Landslide%20susceptibility%20mapping%20based%20on%20Support%20Vector%20Machine:%20A%20case%20study%20on%20natural%20slopes%20of%20Hong%20Kong,%20China&rft.jtitle=Geomorphology%20(Amsterdam,%20Netherlands)&rft.au=Yao,%20X.&rft.date=2008-11-01&rft.volume=101&rft.issue=4&rft.spage=572&rft.epage=582&rft.pages=572-582&rft.issn=0169-555X&rft.eissn=1872-695X&rft_id=info:doi/10.1016/j.geomorph.2008.02.011&rft_dat=%3Cproquest_cross%3E21059547%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-a396t-d9adb6345e9aacd0d7245794f5b9658f3d65364d953f95df4aab819bfdafd3b63%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=21059547&rft_id=info:pmid/&rfr_iscdi=true