AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal ecosystems

AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal ecosystems | 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 Article AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal ecosystems Jianping Gan, Fan Zhang, Hiusuet Kung, Fa Zhang, Can Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6065794/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted You are reading this latest preprint version Abstract Predicting spatiotemporal Chlorophyll-a (Chl_a) distributions is essential for diagnosing and analyzing productivity and ecosystem health of coastal oceans. Yet, current tools remain inadequate for diagnosing and prognosing marine ecosystems, particularly in the dynamic coastal ocean. Coupled physics-biogeochemical models struggle to resolve complex trophic interactions, while data-driven approaches are limited by incomplete satellite observations. We developed an advanced AI-powered spatiotemporal imputation and prediction (STIMP) model for predicting Chl_a in coastal ocean. STIMP adopts a novel paradigm that first imputes and subsequently predicts Chl_a across a broad spatiotemporal scale, resolving difficulties arising from incompletion, nonstationary temporal variations, and spatial heterogeneity of data through integrating specially designed modules. We demonstrated the STIMP’s robust imputation and prediction of Chl_a in four representative global coastal oceans. STIMP reduced the imputation mean absolute error (MAE) by 68.31%–95.28% compared with the data interpolating empirical orthogonal function method in geoscience and by 8.92%–43.04% against leading AI methods. With accurate imputation, STIMP demonstrated superior predictive accuracy, achieving MAE reductions of 58.99% over biogeophysical models and 6.54%–13.68% over AI benchmarks. STIMP offers a new approach for predicting oceans that typically have spatiotemporally limited data. Earth and environmental sciences/Ocean sciences/Marine biology Earth and environmental sciences/Natural hazards Earth and environmental sciences/Ocean sciences/Marine chemistry Full Text Additional Declarations There is NO Competing Interest. Supplementary Files Supplemetary.pdf Extended Figures Cite Share Download PDF Status: Under Review 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-6065794","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":428130957,"identity":"af529cad-159d-4070-a4ca-e5761f98c579","order_by":0,"name":"Jianping Gan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAnklEQVRIiWNgGAWjYNCCChDBw0yKljNADaRpYWwjRYtu+/GLnwvnHba3Z+A9bECUFrMzOcXSM7cdTuxh4EtOIE7LgZwEad5thxOADjM+QJyW82+Sf/POOWxPgpYb6cekeRsOM/YAtRDpsBtv2Kx5jqUn9hzmMSbS++fTH9/mqbG2Z2/vMZYgSgswQqBmkxCR7A+IVzsKRsEoGAUjEwAABMcqW3b8RhEAAAAASUVORK5CYII=","orcid":"https://orcid.org/0000-0001-9827-7929","institution":"Department of Mathematics and Department of Ocean Science, The Hong Kong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Jianping","middleName":"","lastName":"Gan","suffix":""},{"id":428130958,"identity":"407d979c-9f97-423a-813b-79e40fb7c071","order_by":1,"name":"Fan Zhang","email":"","orcid":"https://orcid.org/0000-0001-5894-3237","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Fan","middleName":"","lastName":"Zhang","suffix":""},{"id":428130959,"identity":"35d5ec25-ff7c-4d15-821a-fb3a5ae66384","order_by":2,"name":"Hiusuet Kung","email":"","orcid":"","institution":"Department of Ocean Science and Department of Mathematics, The Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Hiusuet","middleName":"","lastName":"Kung","suffix":""},{"id":428130960,"identity":"64bb8520-9bec-481a-ba46-311cfaa3750b","order_by":3,"name":"Fa Zhang","email":"","orcid":"","institution":"Department of Mathematics, The Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Fa","middleName":"","lastName":"Zhang","suffix":""},{"id":428130961,"identity":"af08cad6-06d4-4416-bc26-79a952fc03f9","order_by":4,"name":"Can Yang","email":"","orcid":"https://orcid.org/0000-0002-4407-3055","institution":"The Hong Kong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Can","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2025-02-19 16:20:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6065794/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6065794/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78494832,"identity":"9acaff52-0cc7-49e5-bedd-fb56af8959d4","added_by":"auto","created_at":"2025-03-14 03:50:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4441788,"visible":true,"origin":"","legend":"Article File","description":"","filename":"STIMP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6065794/v1_covered_325b7cf5-13a9-4369-b4d6-55da84f37211.pdf"},{"id":78494371,"identity":"08564670-b926-4684-ae53-719cc9b1dde0","added_by":"auto","created_at":"2025-03-14 03:42:17","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":3918694,"visible":true,"origin":"","legend":"Extended Figures","description":"","filename":"Supplemetary.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6065794/v1/bedeb2309b1a57b8dbd1de90.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal ecosystems","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"nature-portfolio","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"","title":"Nature Portfolio","twitterHandle":"","acdcEnabled":false,"dfaEnabled":false,"editorialSystem":"ejp","reportingPortfolio":"","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6065794/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6065794/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Predicting spatiotemporal Chlorophyll-a (Chl_a) distributions is essential for diagnosing and analyzing productivity and ecosystem health of coastal oceans. Yet, current tools remain inadequate for diagnosing and prognosing marine ecosystems, particularly in the dynamic coastal ocean. Coupled physics-biogeochemical models struggle to resolve complex trophic interactions, while data-driven approaches are limited by incomplete satellite observations. We developed an advanced AI-powered spatiotemporal imputation and prediction (STIMP) model for predicting Chl_a in coastal ocean. STIMP adopts a novel paradigm that first imputes and subsequently predicts Chl_a across a broad spatiotemporal scale, resolving difficulties arising from incompletion, nonstationary temporal variations, and spatial heterogeneity of data through integrating specially designed modules. We demonstrated the STIMP’s robust imputation and prediction of Chl_a in four representative global coastal oceans. STIMP reduced the imputation mean absolute error (MAE) by 68.31%–95.28% compared with the data interpolating empirical orthogonal function method in geoscience and by 8.92%–43.04% against leading AI methods. With accurate imputation, STIMP demonstrated superior predictive accuracy, achieving MAE reductions of 58.99% over biogeophysical models and 6.54%–13.68% over AI benchmarks. STIMP offers a new approach for predicting oceans that typically have spatiotemporally limited data.","manuscriptTitle":"AI-powered spatiotemporal imputation and prediction of chlorophyll-a concentration in coastal ecosystems","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-14 03:26:12","doi":"10.21203/rs.3.rs-6065794/v1","editorialEvents":[],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"nature-communications","isNatureJournal":true,"hasQc":false,"allowDirectSubmit":false,"externalIdentity":"NCOMMS","sideBox":"Learn more about [Nature Communications](http://www.nature.com/ncomms/)","snPcode":"","submissionUrl":"https://mts-ncomms.nature.com/","title":"Nature Communications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"ejp","reportingPortfolio":"Nature Communications","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"e5ac0216-4119-4dd9-a446-3bbc5236185a","owner":[],"postedDate":"March 14th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":45613655,"name":"Earth and environmental sciences/Ocean sciences/Marine biology"},{"id":45613656,"name":"Earth and environmental sciences/Natural hazards"},{"id":45613657,"name":"Earth and environmental sciences/Ocean sciences/Marine chemistry"}],"tags":[],"updatedAt":"2025-08-04T08:30:43+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-14 03:26:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6065794","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6065794","identity":"rs-6065794","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}