Segmenting ancient cemetery under forests using synthesized LiDAR-derived data and deep convolutional neural network

Segmenting ancient cemetery under forests using synthesized LiDAR-derived data and deep convolutional neural network | 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 Segmenting ancient cemetery under forests using synthesized LiDAR-derived data and deep convolutional neural network Hong Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5290268/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 03 Jun, 2025 Read the published version in npj Heritage Science → Version 1 posted 11 You are reading this latest preprint version Abstract The investigation and identification of spatial distribution of archaeological remains is full of challenges in forested areas, deep learning (DL) methods and light-detection and ranging (LiDAR) make it possible to quickly and automatically identify remains under vegetation cover. This study applied a semantic segmentation model based on convolutional neural networks and LiDAR-derived data to segment an ancient cemetery in a forested area in Baling Mountain and Jishan Mountain in Jingzhou City, Hubei Province, China. We proposed to synthesize multiple LiDAR-derived data into three-channel and five-channel data and perform data augmentation. Moreover, the channel attention (CA) mechanism was used to improve the U-Net and TransUNet models. Finally, segmentation of cemeteries in two regions was implemented and model migration was applied to new geographic regions. The results indicated that it has higher precision using five-channel raster data synthesized with elevation (DEM), slope, hillshade, roughness, and curvature than one or three derived data synthesized raster data in the test dataset. For the U-Net model, the intersection over union (IoU), precision, and recall reached 0.885, 0.921, and 0.924, respectively, for the TransUNet model, the IoU, precision, and recall reached 0.901, 0.921, and 0.944, respectively, successfully segmenting the unknown region cemetery. In addition, the migration of the model also indicated that the model trained by synthesizing data has better portability. In conclusion, our results contribute to the current discussion on techniques for automatically extracting historical terrain features using the DL method and LiDAR-derived data, and can also provide useful guidance for identifying archaeological remains in vegetation covered areas. archaeology deep learning convolutional neural networks (CNN) ancient cemetery Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 03 Jun, 2025 Read the published version in npj Heritage Science → Version 1 posted Editorial decision: Revision requested 27 Dec, 2024 Reviews received at journal 27 Dec, 2024 Reviews received at journal 15 Dec, 2024 Reviewers agreed at journal 03 Dec, 2024 Reviewers agreed at journal 02 Dec, 2024 Reviewers agreed at journal 01 Dec, 2024 Reviewers agreed at journal 28 Nov, 2024 Reviewers invited by journal 04 Nov, 2024 Editor assigned by journal 26 Oct, 2024 Submission checks completed at journal 26 Oct, 2024 First submitted to journal 18 Oct, 2024 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-5290268","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":374072161,"identity":"f81f82b8-0bcd-403a-be00-693cf86af63e","order_by":0,"name":"Hong Yang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6klEQVRIie3QuwrCMBSA4ZRAXI66poiXRwgE6mDxWRQhU72MbhYEJ3FW9CE6uRoI2EVxrZsguNhBEBy9dHOKdRPMvx04HxwOQibTj4ZRn5byGZ8kg+WnIxuX22P5DbFGohlEjZSEhVt17hFl+fvYOQJyi4HEp4OWbDqiNgWFrblX5YAEDySpMi2RnsOBKoIL7WUBkGoGEgjVkl38IkwBsbcJeaQgkceP0BAUaDYh8jOxo9jBIF1GoXuzF6zFZ4o4WpLbefyavdPBKlwLGvfrxUk4PGlJRaL3M5JXYd3+q7KP8OXDjslkMv17Tzj+SDaNJWaWAAAAAElFTkSuQmCC","orcid":"","institution":"Wuhan University","correspondingAuthor":true,"prefix":"","firstName":"Hong","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2024-10-18 14:53:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5290268/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5290268/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s40494-025-01798-5","type":"published","date":"2025-06-03T15:57:29+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":84242569,"identity":"f396e561-c3c1-41cd-8489-6bf2c3419c2e","added_by":"auto","created_at":"2025-06-09 16:09:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1558677,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5290268/v1_covered_3940b339-66d5-479f-9b22-d0ee94523433.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Segmenting ancient cemetery under forests using synthesized LiDAR-derived data and deep convolutional neural network","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"archaeology, deep learning, convolutional neural networks (CNN), ancient cemetery","lastPublishedDoi":"10.21203/rs.3.rs-5290268/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5290268/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe investigation and identification of spatial distribution of archaeological remains is full of challenges in forested areas, deep learning (DL) methods and light-detection and ranging (LiDAR) make it possible to quickly and automatically identify remains under vegetation cover. This study applied a semantic segmentation model based on convolutional neural networks and LiDAR-derived data to segment an ancient cemetery in a forested area in Baling Mountain and Jishan Mountain in Jingzhou City, Hubei Province, China. We proposed to synthesize multiple LiDAR-derived data into three-channel and five-channel data and perform data augmentation. Moreover, the channel attention (CA) mechanism was used to improve the U-Net and TransUNet models. Finally, segmentation of cemeteries in two regions was implemented and model migration was applied to new geographic regions. The results indicated that it has higher precision using five-channel raster data synthesized with elevation (DEM), slope, hillshade, roughness, and curvature than one or three derived data synthesized raster data in the test dataset. For the U-Net model, the intersection over union (IoU), precision, and recall reached 0.885, 0.921, and 0.924, respectively, for the TransUNet model, the IoU, precision, and recall reached 0.901, 0.921, and 0.944, respectively, successfully segmenting the unknown region cemetery. In addition, the migration of the model also indicated that the model trained by synthesizing data has better portability. In conclusion, our results contribute to the current discussion on techniques for automatically extracting historical terrain features using the DL method and LiDAR-derived data, and can also provide useful guidance for identifying archaeological remains in vegetation covered areas.\u003c/p\u003e","manuscriptTitle":"Segmenting ancient cemetery under forests using synthesized LiDAR-derived data and deep convolutional neural network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-06 18:04:49","doi":"10.21203/rs.3.rs-5290268/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-12-27T22:35:44+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-27T19:35:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-12-16T02:25:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"117371565386927591804152418759187276365","date":"2024-12-03T07:38:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"141742834238866378965206314192316786664","date":"2024-12-02T17:34:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"171813860583286478005019860664462612020","date":"2024-12-02T00:41:55+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"287190425669097270370782043898129124321","date":"2024-11-28T05:27:10+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-11-04T22:23:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-10-26T07:09:44+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-10-26T07:08:20+00:00","index":"","fulltext":""},{"type":"submitted","content":"Heritage Science","date":"2024-10-18T14:42:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"4710a228-da3f-458b-888e-f2c80a26626b","owner":[],"postedDate":"November 6th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-09T16:02:08+00:00","versionOfRecord":{"articleIdentity":"rs-5290268","link":"https://doi.org/10.1038/s40494-025-01798-5","journal":{"identity":"npj-heritage-science","isVorOnly":false,"title":"npj Heritage Science"},"publishedOn":"2025-06-03 15:57:29","publishedOnDateReadable":"June 3rd, 2025"},"versionCreatedAt":"2024-11-06 18:04:49","video":"","vorDoi":"10.1038/s40494-025-01798-5","vorDoiUrl":"https://doi.org/10.1038/s40494-025-01798-5","workflowStages":[]},"version":"v1","identity":"rs-5290268","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5290268","identity":"rs-5290268","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}