Landslide susceptibility mapping based on convolutional neural network and conventional machine learning methods

Landslide susceptibility mapping based on convolutional neural network and conventional machine learning methods | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Manuscript Landslide susceptibility mapping based on convolutional neural network and conventional machine learning methods Rui Liu, Xin Yang, Chong Xu, Luyao Li, Xiangqiang Zeng This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-190195/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Landslide susceptibility mapping (LSM) is a useful tool to estimate the probability of landslide occurrence, providing a scientific basis for natural hazards prevention, land use planning, and economic development in landslide-prone areas. To date, a large number of machine learning methods have been applied to LSM, and recently the advanced Convolutional Neural Network (CNN) has been gradually adopted to enhance the prediction accuracy of LSM. The objective of this study is to introduce a CNN based model in LSM and systematically compare its overall performance with the conventional machine learning models of random forest, logistic regression, and support vector machine. Herein, we selected the Jiuzhaigou region in Sichuan Province, China as the study area. A total number of 710 landslides and 12 predisposing factors were stacked to form spatial datasets for LSM. The ROC analysis and several statistical metrics, such as accuracy, root mean square error (RMSE), Kappa coefficient, sensitivity, and specificity were used to evaluate the performance of the models in the training and validation datasets. Finally, the trained models were calculated and the landslide susceptibility zones were mapped. Results suggest that both CNN and conventional machine-learning based models have a satisfactory performance (AUC: 85.72% − 90.17%). The CNN based model exhibits excellent good-of-fit and prediction capability, and achieves the highest performance (AUC: 90.17%) but also significantly reduces the salt-of-pepper effect, which indicates its great potential of application to LSM. Planetary Geology Physical Geography Geographic Information Systems Landslide susceptibility mapping Convolutional neural network Machine learning GIS Jiuzhaigou region Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Full Text Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-190195","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Manuscript","associatedPublications":[],"authors":[{"id":9722775,"identity":"727fa5f2-dcb7-4bee-913a-dc356281757f","order_by":0,"name":"Rui Liu","email":"","orcid":"","institution":"Chengdu University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Liu","suffix":""},{"id":9722776,"identity":"4b24e04c-ce17-4e00-8d4b-0f0828f3064f","order_by":1,"name":"Xin Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAsklEQVRIiWNgGAWjYBACCR4GNoYEIIOfdC2SDSRpAQGDA8Rqkew5/uzBwx02iZuPJ29g+FGxjbAWad4ec4PEM2mJ2848K2DsOXObsBY5fh42icS2w4nbbuQYMDO2EaWF/RlQy//EzTOI1SLN22AG1HIgcYMEsVoke86AtCQbzwD65SBRfpE4k/5M8mebnWx/e/LGBz8qiNACA44NDAnERw0Y2DMAtZCkYxSMglEwCkYOAABaNDzN2Wa5ywAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-4599-530X","institution":"Chengdu University of Technology","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Yang","suffix":""},{"id":9722777,"identity":"34a3d80e-ee87-4635-a2c4-392489ca4921","order_by":2,"name":"Chong Xu","email":"","orcid":"","institution":"National Institute of Natural Hazards, Ministry of Emergency Management of China","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Chong","middleName":"","lastName":"Xu","suffix":""},{"id":9722778,"identity":"879e8024-6ddc-45e0-b2f7-7861c5dca727","order_by":3,"name":"Luyao Li","email":"","orcid":"","institution":"Chengdu University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Luyao","middleName":"","lastName":"Li","suffix":""},{"id":9722779,"identity":"4b9009f3-f788-42d9-ba14-129f5816931e","order_by":4,"name":"Xiangqiang Zeng","email":"","orcid":"","institution":"Chengdu University of Technology","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Xiangqiang","middleName":"","lastName":"Zeng","suffix":""}],"badges":[],"createdAt":"2021-01-30 09:52:25","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-190195/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-190195/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":5751467,"identity":"c6d44f24-6c69-4a24-91b9-1f18f7f2361c","added_by":"auto","created_at":"2021-02-08 20:17:14","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":375375,"visible":true,"origin":"","legend":"Location of the study area. Note: The designations employed and the presentation of the material on this map do not imply the expression of any opinion whatsoever on the part of Research Square concerning the legal status of any country, territory, city or area or of its authorities, or concerning the delimitation of its frontiers or boundaries. This map has been provided by the authors.\n","description":"","filename":"Fig1.png","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/355d92866aa86861f875857e.png"},{"id":5751466,"identity":"95ca295a-304e-4e64-82f5-80fe726ae5df","added_by":"auto","created_at":"2021-02-08 20:17:13","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":4249114,"visible":true,"origin":"","legend":"Maps showing landslide predisposing factors used in this study. (a) PGA, (b) TWI, (c) distance to rivers, (d) distance to roads, (e) NDVI, (f) land use, (g) lithology, (h) distance to faults, (i) elevation, (j) slope angle, (k) slope aspect, (l) TRI","description":"","filename":"Fig2final.jpg","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/28b67416c8554b01080d3442.jpg"},{"id":5751315,"identity":"2be6a78f-a6fd-4ecf-93d1-3e816b7ad6ba","added_by":"auto","created_at":"2021-02-08 20:14:13","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":66635,"visible":true,"origin":"","legend":"Schematic diagram of spatial datasets generation process ","description":"","filename":"Fig3.png","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/b72d4e508f9812a8b51bb5b1.png"},{"id":5751464,"identity":"c7450e33-8cfe-44d3-b7be-a943ae9aae54","added_by":"auto","created_at":"2021-02-08 20:17:13","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":49142,"visible":true,"origin":"","legend":"The CNN architecture ","description":"","filename":"Fig4.png","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/de2e7dfe8172a256e3cea6eb.png"},{"id":5751639,"identity":"d31d603e-4f4e-4c05-9818-f25025d2d39b","added_by":"auto","created_at":"2021-02-08 20:20:13","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":84672,"visible":true,"origin":"","legend":"The ROC curves of models on (a) training dataset, and (b) validation dataset","description":"","filename":"Fig5.png","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/c7466140fc6ce7860510487e.png"},{"id":5751320,"identity":"2d42b427-7b15-460f-8ba8-ece0ae2b07dd","added_by":"auto","created_at":"2021-02-08 20:14:13","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":891942,"visible":true,"origin":"","legend":"Landslide susceptibility maps of Jiuzhaigou region using (a) convolutional neural network, (b) ","description":"","filename":"Fig6.png","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/87c8fb081b3f6ce6caf753ca.png"},{"id":5751318,"identity":"454da0dc-55dd-4ce2-89ce-2fd1dbd2ba78","added_by":"auto","created_at":"2021-02-08 20:14:13","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":25651,"visible":true,"origin":"","legend":"Landslide susceptibility zones","description":"","filename":"Fig7.png","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/fd1cb0d6a8615b9e1a42c518.png"},{"id":5751321,"identity":"f3bd605c-06ad-4870-b70f-6cbb24684901","added_by":"auto","created_at":"2021-02-08 20:14:13","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":336968,"visible":true,"origin":"","legend":"The local magnification of the Fig. 6 (a), (b), (c) and (d)","description":"","filename":"Fig8.png","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1/cb63121f215110d38f6205ae.png"},{"id":13582418,"identity":"fc3fcce4-b3bb-4c7a-b2f7-ad05128f177c","added_by":"auto","created_at":"2021-09-17 04:31:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3019831,"visible":true,"origin":"","legend":"","description":"","filename":"LSMXYNHAZ1211.pdf","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1_covered.pdf"},{"id":11617192,"identity":"e6f6173d-2a08-4d0e-8647-3c3d680d09de","added_by":"auto","created_at":"2021-07-20 04:40:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3016041,"visible":true,"origin":"","legend":"","description":"","filename":"LSMXYNHAZ1211.pdf","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1_covered.pdf"},{"id":5751789,"identity":"5fee075f-b64f-4d49-bc4d-7d9896a00c46","added_by":"auto","created_at":"2021-02-08 20:23:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2452404,"visible":true,"origin":"","legend":"","description":"","filename":"LSMXYNHAZ1211.pdf","url":"https://assets-eu.researchsquare.com/files/rs-190195/v1_stamped.pdf"}],"financialInterests":"","formattedTitle":"Landslide susceptibility mapping based on convolutional neural network and conventional machine learning methods","fulltext":[{"header":"Full Text","content":"\u003cp\u003eThis preprint is available for \u003ca href='/article/rs-190195/latest.pdf' target='_blank'\u003edownload as a PDF\u003c/a\u003e.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Landslide susceptibility mapping, Convolutional neural network, Machine learning, GIS, Jiuzhaigou region","lastPublishedDoi":"10.21203/rs.3.rs-190195/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-190195/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLandslide susceptibility mapping (LSM) is a useful tool to estimate the probability of landslide occurrence, providing a scientific basis for natural hazards prevention, land use planning, and economic development in landslide-prone areas. To date, a large number of machine learning methods have been applied to LSM, and recently the advanced Convolutional Neural Network (CNN) has been gradually adopted to enhance the prediction accuracy of LSM. The objective of this study is to introduce a CNN based model in LSM and systematically compare its overall performance with the conventional machine learning models of random forest, logistic regression, and support vector machine. Herein, we selected the Jiuzhaigou region in Sichuan Province, China as the study area. A total number of 710 landslides and 12 predisposing factors were stacked to form spatial datasets for LSM. The ROC analysis and several statistical metrics, such as accuracy, root mean square error (RMSE), Kappa coefficient, sensitivity, and specificity were used to evaluate the performance of the models in the training and validation datasets. Finally, the trained models were calculated and the landslide susceptibility zones were mapped. Results suggest that both CNN and conventional machine-learning based models have a satisfactory performance (AUC: 85.72% \u0026minus;\u0026thinsp;90.17%). The CNN based model exhibits excellent good-of-fit and prediction capability, and achieves the highest performance (AUC: 90.17%) but also significantly reduces the salt-of-pepper effect, which indicates its great potential of application to LSM.\u003c/p\u003e","manuscriptTitle":"Landslide susceptibility mapping based on convolutional neural network and conventional machine learning methods","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2021-02-08 20:14:11","doi":"10.21203/rs.3.rs-190195/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"6c0c427e-3a42-4add-baa8-aa8ed189e6ae","owner":[],"postedDate":"February 8th, 2021","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":2272485,"name":"Planetary Geology"},{"id":2272486,"name":"Physical Geography"},{"id":2272487,"name":"Geographic Information Systems"}],"tags":[],"updatedAt":"2021-07-20T04:40:36+00:00","versionOfRecord":[],"versionCreatedAt":"2021-02-08 20:14:11","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-190195","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-190195","identity":"rs-190195","version":["v1"]},"buildId":"7rjqhiLT3MXkJMwkYKINL","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}