From Land to Ocean: Bathymetric Terrain Reconstruction via Conditional Generative Adversarial Network

From Land to Ocean: Bathymetric Terrain Reconstruction via Conditional Generative Adversarial 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 From Land to Ocean: Bathymetric Terrain Reconstruction via Conditional Generative Adversarial Network Liwen Zhang, Jiabao Wen, Ziqiang Huo, Zhengjian Li, Meng Xi, Jiachen Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4127951/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 13 You are reading this latest preprint version Abstract Acquiring global ocean digital elevation model (DEM) is a forefront branch of marine geology and hydrographic survey that plays a crucial role in the study of the Earth's system and seafloor's structure. Due to limitations in technological capabilities and surveying costs, large-scale sampling of ocean depths is very coarse, making it challenging to directly create complete ocean DEM. Many traditional interpolation and deep learning methods have been applied to reconstruct ocean DEM images. However, the continuity and heterogeneity of ocean terrain data are too complex to be approximated effectively by traditional interpolation models. Meanwhile, due to the scarcity of available data, training an sufficient network directly with deep learning methods is difficult. In this work, we propose a conditional generative adversarial network (CGAN) based on transfer learning, which applies knowledge learned from land terrain to ocean terrain. We pre-train the model using land DEM data and fine-tune it using ocean DEM data. Specifically, we utilize randomly sampled ocean terrain data as network input, employ CGAN with U-Net architecture and residual blocks to capture terrain features of images through adversarial training, resulting in reconstructed bathymetric terrain images. The training process is constrained by the combined loss composed of adversarial loss, reconstruction loss, and perceptual loss. Experimental results demonstrate that our approach reduces the required amount of training data, and achieves better reconstruction accuracy compared to traditional methods. Conditional generative adversarial network transfer learning DEM reconstruction bathymetric data Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 15 May, 2024 Reviewers agreed at journal 14 May, 2024 Reviewers agreed at journal 08 May, 2024 Reviews received at journal 07 May, 2024 Reviewers agreed at journal 04 May, 2024 Reviewers agreed at journal 02 May, 2024 Reviews received at journal 19 Apr, 2024 Reviewers agreed at journal 02 Apr, 2024 Reviewers agreed at journal 01 Apr, 2024 Reviewers invited by journal 30 Mar, 2024 Editor assigned by journal 30 Mar, 2024 Submission checks completed at journal 21 Mar, 2024 First submitted to journal 19 Mar, 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-4127951","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":282200179,"identity":"2ca51654-d556-4f8c-9589-93294692d4e2","order_by":0,"name":"Liwen Zhang","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Liwen","middleName":"","lastName":"Zhang","suffix":""},{"id":282200180,"identity":"29e01e39-d1cf-4e6e-8bf2-ac720388355b","order_by":1,"name":"Jiabao Wen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8klEQVRIiWNgGAWjYBACgwNAosKAIYGBgfkAgwRI6AAxWiTAWtgSG0jQwgDSwmPYwECUluO9QPcU2OXxt/d8f2DZxiDHdyOB8XMBHi1mZ84lAB2WXCxx5uzGBsk2BmPJGwnM0jPwabmRYwDUwpzYcCMXrCVxw40ENmYefFruvwFpqU+cfyPnIUhLPUEt9jd4DBglDA4DDc9hBGlJMCCkxfJMjgHjBoPjxYZnjhnOkDgnYTjzzMNmaXxaDI6fMWB48Kc6T+5484PPEmU28nzHkw9+xqcFCNh/wFjMEuD4Z2zArwEZMH4gXu0oGAWjYBSMIAAAdCNPYjYP5JAAAAAASUVORK5CYII=","orcid":"","institution":"Tianjin University","correspondingAuthor":true,"prefix":"","firstName":"Jiabao","middleName":"","lastName":"Wen","suffix":""},{"id":282200181,"identity":"d714a099-9b9a-4ddd-9e3c-b88a327f02ac","order_by":2,"name":"Ziqiang Huo","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Ziqiang","middleName":"","lastName":"Huo","suffix":""},{"id":282200182,"identity":"e54742bd-c8a9-42eb-aa69-b71e8b380788","order_by":3,"name":"Zhengjian Li","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Zhengjian","middleName":"","lastName":"Li","suffix":""},{"id":282200183,"identity":"c635e898-0ddf-40d4-bab6-cac909676e1a","order_by":4,"name":"Meng Xi","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Meng","middleName":"","lastName":"Xi","suffix":""},{"id":282200184,"identity":"a5f087da-0c6a-45ef-bc95-508dba99cfde","order_by":5,"name":"Jiachen Yang","email":"","orcid":"","institution":"Tianjin University","correspondingAuthor":false,"prefix":"","firstName":"Jiachen","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2024-03-19 06:54:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4127951/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4127951/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":53359687,"identity":"b6949768-33fb-4bc1-8284-7505bb272050","added_by":"auto","created_at":"2024-03-25 04:26:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7167856,"visible":true,"origin":"","legend":"","description":"","filename":"ESIManuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4127951/v1_covered_86836a81-835a-4454-b48c-5eed0cbf5d4c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"From Land to Ocean: Bathymetric Terrain Reconstruction via Conditional Generative Adversarial 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":"earth-science-informatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esin","sideBox":"Learn more about [Earth Science Informatics](http://link.springer.com/journal/12145)","snPcode":"12145","submissionUrl":"https://submission.nature.com/new-submission/12145/3","title":"Earth Science Informatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Conditional generative adversarial network, transfer learning, DEM reconstruction, bathymetric data","lastPublishedDoi":"10.21203/rs.3.rs-4127951/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4127951/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Acquiring global ocean digital elevation model (DEM) is a forefront branch of marine geology and hydrographic survey that plays a crucial role in the study of the Earth's system and seafloor's structure. Due to limitations in technological capabilities and surveying costs, large-scale sampling of ocean depths is very coarse, making it challenging to directly create complete ocean DEM. Many traditional interpolation and deep learning methods have been applied to reconstruct ocean DEM images. However, the continuity and heterogeneity of ocean terrain data are too complex to be approximated effectively by traditional interpolation models. Meanwhile, due to the scarcity of available data, training an sufficient network directly with deep learning methods is difficult. In this work, we propose a conditional generative adversarial network (CGAN) based on transfer learning, which applies knowledge learned from land terrain to ocean terrain. We pre-train the model using land DEM data and fine-tune it using ocean DEM data. Specifically, we utilize randomly sampled ocean terrain data as network input, employ CGAN with U-Net architecture and residual blocks to capture terrain features of images through adversarial training, resulting in reconstructed bathymetric terrain images. The training process is constrained by the combined loss composed of adversarial loss, reconstruction loss, and perceptual loss. Experimental results demonstrate that our approach reduces the required amount of training data, and achieves better reconstruction accuracy compared to traditional methods.","manuscriptTitle":"From Land to Ocean: Bathymetric Terrain Reconstruction via Conditional Generative Adversarial Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-25 04:09:40","doi":"10.21203/rs.3.rs-4127951/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-05-15T19:32:23+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"34261744129789502074685632379130176532","date":"2024-05-15T01:46:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"135845821178065917586941152625048870001","date":"2024-05-08T07:43:32+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-08T01:07:10+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"28545266116866450647309801056548251634","date":"2024-05-04T23:14:46+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"218078883657438623824994033022445714400","date":"2024-05-02T22:08:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-04-19T13:36:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"9d001ca9-2bb0-496a-849d-4221f6a47e5b","date":"2024-04-02T08:57:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"8b1493fd-a7de-4bda-adcd-6afe00a2439d","date":"2024-04-01T20:41:04+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-03-30T20:03:21+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-03-30T20:01:38+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-21T10:10:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"Earth Science Informatics","date":"2024-03-19T06:53:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"earth-science-informatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esin","sideBox":"Learn more about [Earth Science Informatics](http://link.springer.com/journal/12145)","snPcode":"12145","submissionUrl":"https://submission.nature.com/new-submission/12145/3","title":"Earth Science Informatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3fd7f01d-fbf8-4211-90d4-7f4151802d95","owner":[],"postedDate":"March 25th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-06-16T17:53:12+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-25 04:09:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4127951","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4127951","identity":"rs-4127951","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}