Research on improved SegFormer with multi-module fusion for landslide remote sensing image recognition

Research on improved SegFormer with multi-module fusion for landslide remote sensing image recognition | 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 Research Article Research on improved SegFormer with multi-module fusion for landslide remote sensing image recognition Minghua Luo, Canming Yuan, Rui Ma, Bibo Dai, Jinxin Huang, Xin Pan, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8711252/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 Landslides pose severe threats to life and property, necessitating rapid and accurate identification for effective hazard assessment and emergency response. This study proposes an improved SegFormer model designed for precise landslide extraction from high-resolution remote sensing imagery. To address the limitations of existing segmentation methods in handling complex backgrounds and irregular boundaries, the proposed framework integrates several structural enhancements. These include a squeeze-and-excitation module to suppress background noise, an auxiliary edge-fusion branch to capture explicit boundary details, and an adaptive feature gating mechanism to refine feature representation. The model is trained using focal loss to mitigate class imbalance and employs a three-stage recognition process, culminating in post-processing via dense conditional random fields for boundary refinement. Experimental results on a dataset of 100 high-resolution satellite images demonstrate that this approach significantly outperforms the classical U-Net architecture and traditional thresholding techniques. The model achieved an accuracy of 0.976, a precision of 0.918, a recall of 0.947, and an F1-score of 0.932. These findings confirm that the proposed method offers exceptional accuracy and robustness, providing an effective automated tool for large-scale landslide detection in complex terrain. Landslide identification SegFormer Transformer Dense conditional random fields Full Text Additional Declarations No competing interests reported. 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-8711252","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":582313726,"identity":"4e783158-6e7d-4bb9-99c8-0ed2177dd3f9","order_by":0,"name":"Minghua Luo","email":"","orcid":"","institution":"State key Laboratory of Metal Mine Mining Safety and Disaster Prevention and Control","correspondingAuthor":false,"prefix":"","firstName":"Minghua","middleName":"","lastName":"Luo","suffix":""},{"id":582313727,"identity":"7fe850da-c7a6-44aa-bae6-b719fb3f4ac2","order_by":1,"name":"Canming Yuan","email":"","orcid":"","institution":"College of Safety and Environmental Engineering, Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Canming","middleName":"","lastName":"Yuan","suffix":""},{"id":582313728,"identity":"ed332756-0dc5-44b4-aaeb-f3a6353e63ca","order_by":2,"name":"Rui Ma","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYNACAwk7NvbmAwc+VBCvxSaZj+dY4sEZZ4i3Jo1xnoSP8WHeFiLU6rYfYPvMU3CYmU2C58MB3gYGeX6xA/i1mJ1JYJ7NY3CYj026d8MByR0MhjNnJxDQciCBmRmohZlN5uyGA4ZnGBIMbhPScv4BWAtjm0TOgwOJbcRouQG2JQ2kheHAQeK0PGBmnAMMZDaeYwYHG85IEOGX8wnMDG/+SNjJtzc//vynwkaeX5qAFgYG/g/IPAlCykfBKBgFo2AUEAMAoLxDIjv4GDMAAAAASUVORK5CYII=","orcid":"","institution":"State Key Laboratory of Coal Mine Disaster Dynamics and Control, Chongqing University","correspondingAuthor":true,"prefix":"","firstName":"Rui","middleName":"","lastName":"Ma","suffix":""},{"id":582313729,"identity":"cc6f6cc4-abe8-4af9-9259-ae35613cd617","order_by":3,"name":"Bibo Dai","email":"","orcid":"","institution":"State key Laboratory of Metal Mine Mining Safety and Disaster Prevention and Control","correspondingAuthor":false,"prefix":"","firstName":"Bibo","middleName":"","lastName":"Dai","suffix":""},{"id":582313730,"identity":"4ab200a2-e53e-4f47-a673-cb16f003bfb2","order_by":4,"name":"Jinxin Huang","email":"","orcid":"","institution":"Jurong Water Conservancy Bureau","correspondingAuthor":false,"prefix":"","firstName":"Jinxin","middleName":"","lastName":"Huang","suffix":""},{"id":582313731,"identity":"6c971064-2a1f-46b2-b50d-4e5dd59906da","order_by":5,"name":"Xin Pan","email":"","orcid":"","institution":"Jurong Water Conservancy Bureau","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Pan","suffix":""},{"id":582313732,"identity":"6a00d6d0-be0d-4f3a-9c64-faacf9ddc190","order_by":6,"name":"Xu Wu","email":"","orcid":"","institution":"State key Laboratory of Metal Mine Mining Safety and Disaster Prevention and Control","correspondingAuthor":false,"prefix":"","firstName":"Xu","middleName":"","lastName":"Wu","suffix":""},{"id":582313733,"identity":"4be9de59-6847-40ef-952e-b5034742c1fa","order_by":7,"name":"Zhixin Zhang","email":"","orcid":"","institution":"China energy deep undergroud technology(Hubei)CO., LTD","correspondingAuthor":false,"prefix":"","firstName":"Zhixin","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-01-27 13:55:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8711252/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8711252/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102399847,"identity":"14731420-9bbb-4b74-8368-08beb5d09a0a","added_by":"auto","created_at":"2026-02-11 10:37:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1366922,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8711252/v1_covered_b13e1548-6d4f-4c9d-896a-da7531acc38a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on improved SegFormer with multi-module fusion for landslide remote sensing image recognition","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"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 identification, SegFormer, Transformer, Dense conditional random fields","lastPublishedDoi":"10.21203/rs.3.rs-8711252/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8711252/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLandslides pose severe threats to life and property, necessitating rapid and accurate identification for effective hazard assessment and emergency response. This study proposes an improved SegFormer model designed for precise landslide extraction from high-resolution remote sensing imagery. To address the limitations of existing segmentation methods in handling complex backgrounds and irregular boundaries, the proposed framework integrates several structural enhancements. These include a squeeze-and-excitation module to suppress background noise, an auxiliary edge-fusion branch to capture explicit boundary details, and an adaptive feature gating mechanism to refine feature representation. The model is trained using focal loss to mitigate class imbalance and employs a three-stage recognition process, culminating in post-processing via dense conditional random fields for boundary refinement. Experimental results on a dataset of 100 high-resolution satellite images demonstrate that this approach significantly outperforms the classical U-Net architecture and traditional thresholding techniques. The model achieved an accuracy of 0.976, a precision of 0.918, a recall of 0.947, and an F1-score of 0.932. These findings confirm that the proposed method offers exceptional accuracy and robustness, providing an effective automated tool for large-scale landslide detection in complex terrain.\u003c/p\u003e","manuscriptTitle":"Research on improved SegFormer with multi-module fusion for landslide remote sensing image recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-03 04:46:43","doi":"10.21203/rs.3.rs-8711252/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":"e64b3be2-5bf6-4534-ad75-de93b8e5f1f0","owner":[],"postedDate":"February 3rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-11T05:39:47+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-03 04:46:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8711252","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8711252","identity":"rs-8711252","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}