A Deep Learning-based Land-Atmosphere Coupled Model for Heatwave Prediction

A Deep Learning-based Land-Atmosphere Coupled Model for Heatwave Prediction | 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 A Deep Learning-based Land-Atmosphere Coupled Model for Heatwave Prediction Dongjin Cho, Yoo-Geun Ham, Suyeon Jeong, Seon-Yu Kang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7484832/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 02 Feb, 2026 Read the published version in npj Climate and Atmospheric Science → Version 1 posted 10 You are reading this latest preprint version Abstract Extreme heat events are intensifying under climate change, yet their prediction remains limited by the inadequate representation of land–atmosphere (L–A) interactions. Most deep learning–based weather models have focused solely on atmospheric variables, overlooking the role of land surface conditions in driving heat extremes. In this study, we present an L–A coupled prediction framework to enhance heatwave forecasting, focusing on Northern Hemisphere summer conditions. The model integrates soil moisture and temperature across multiple vertical layers into the atmospheric forecasting process and is trained to reflect their dynamic influence. We found that training the model with a multi-step loss function significantly improved its ability to capture L–A interactions on a sub-seasonal time scale by sustaining their strength and structure across longer lead times. Using multi-step loss, the L–A coupled model achieved a 5.9–11.2% improvement in heatwave forecast accuracy relative to the atmosphere-only model across 1–7 day lead times, as measured by root mean squared error, whereas the improvement was only 1.9–4.3% with single-step loss. The coupled model’s forecast skill gain is strongest at short leads (~ 3 day) when both SM and circulation predictability were high, and sustained at longer leads (up to 7 day) mainly by L–A coupling through SM predictability. Case studies of recent WesternEuropean and East Asian heatwaves further demonstrated its ability to capture land surface drying and associated temperature extremes. These findings underscore the importance of incorporating L–A coupling with multi-step optimization in advancing data-driven heatwave forecasting systems. Earth and environmental sciences/Climate sciences Earth and environmental sciences/Environmental sciences Heatwave Prediction Land–Atmosphere Coupling Deep Learning Multi-step Loss Autoregressive Forecasting ERA5 Reanalysis Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryFigures.docx Cite Share Download PDF Status: Published Journal Publication published 02 Feb, 2026 Read the published version in npj Climate and Atmospheric Science → Version 1 posted Editorial decision: Revision requested 27 Oct, 2025 Reviews received at journal 27 Oct, 2025 Reviewers agreed at journal 16 Oct, 2025 Reviews received at journal 26 Sep, 2025 Reviewers agreed at journal 11 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviewers invited by journal 09 Sep, 2025 Editor assigned by journal 05 Sep, 2025 Submission checks completed at journal 05 Sep, 2025 First submitted to journal 29 Aug, 2025 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-7484832","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":514630243,"identity":"3a885186-b1e1-4c34-ba4a-699137f56f9d","order_by":0,"name":"Dongjin Cho","email":"","orcid":"","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Dongjin","middleName":"","lastName":"Cho","suffix":""},{"id":514630244,"identity":"3579b91c-68ab-4f90-aa9f-54712bad7b00","order_by":1,"name":"Yoo-Geun Ham","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAx0lEQVRIiWNgGAWjYBADORjDgGgtxqRrSWwgWovB8ebDLz623UmfPyP3AMOPGgZj8wZCWs4cS7Oc2fYsd8ONvATGnmMMZjIHCGm5kWNmzNt2OHeDRI4BA28Dg40EQYeBtPxtO5wuPyPHgPEvkVqMHzO2HU5guJFjwAy0xYygFkmgXxh7zh023HDmjcFhmWMSxgS18AFD7MOPssPy8u05hg/f1NgYziCkReEAAxvc3AMMDATtYGCQb2Bg/kBY2SgYBaNgFIxoAAA+UkBgvayW6AAAAABJRU5ErkJggg==","orcid":"","institution":"Seoul National University","correspondingAuthor":true,"prefix":"","firstName":"Yoo-Geun","middleName":"","lastName":"Ham","suffix":""},{"id":514630245,"identity":"0904e41e-733c-4d8b-965e-ddee8ecb8625","order_by":2,"name":"Suyeon Jeong","email":"","orcid":"","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Suyeon","middleName":"","lastName":"Jeong","suffix":""},{"id":514630246,"identity":"892dc93f-747d-45c8-841f-386559839f0e","order_by":3,"name":"Seon-Yu Kang","email":"","orcid":"","institution":"Seoul National University","correspondingAuthor":false,"prefix":"","firstName":"Seon-Yu","middleName":"","lastName":"Kang","suffix":""}],"badges":[],"createdAt":"2025-08-29 04:38:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7484832/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7484832/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41612-025-01311-6","type":"published","date":"2026-02-02T15:57:27+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":102233989,"identity":"350f431c-fc00-48a3-b135-a9ae304e4713","added_by":"auto","created_at":"2026-02-09 16:02:12","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1677387,"visible":true,"origin":"","legend":"","description":"","filename":"MSLAcouplingHeatwave.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7484832/v1_covered_e88790f2-1bca-42a5-915e-e27b91d28b3a.pdf"},{"id":91558937,"identity":"41e33114-5f89-4481-9455-5d7f56bdc4b6","added_by":"auto","created_at":"2025-09-17 18:12:17","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":3176133,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryFigures.docx","url":"https://assets-eu.researchsquare.com/files/rs-7484832/v1/357fbc91d26cb7b8ce4eb872.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Deep Learning-based Land-Atmosphere Coupled Model for Heatwave Prediction","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-climate-and-atmospheric-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjclimatsci","sideBox":"Learn more about [npj Climate and Atmospheric Science](http://www.nature.com/npjclimatsci/)","snPcode":"41612","submissionUrl":"https://submission.springernature.com/new-submission/41612/3","title":"npj Climate and Atmospheric Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Heatwave Prediction, Land–Atmosphere Coupling, Deep Learning, Multi-step Loss, Autoregressive Forecasting, ERA5 Reanalysis","lastPublishedDoi":"10.21203/rs.3.rs-7484832/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7484832/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eExtreme heat events are intensifying under climate change, yet their prediction remains limited by the inadequate representation of land–atmosphere (L–A) interactions. Most deep learning–based weather models have focused solely on atmospheric variables, overlooking the role of land surface conditions in driving heat extremes. In this study, we present an L–A coupled prediction framework to enhance heatwave forecasting, focusing on Northern Hemisphere summer conditions. The model integrates soil moisture and temperature across multiple vertical layers into the atmospheric forecasting process and is trained to reflect their dynamic influence. We found that training the model with a multi-step loss function significantly improved its ability to capture L–A interactions on a sub-seasonal time scale by sustaining their strength and structure across longer lead times. Using multi-step loss, the L–A coupled model achieved a 5.9–11.2% improvement in heatwave forecast accuracy relative to the atmosphere-only model across 1–7 day lead times, as measured by root mean squared error, whereas the improvement was only 1.9–4.3% with single-step loss. The coupled model’s forecast skill gain is strongest at short leads (~ 3 day) when both SM and circulation predictability were high, and sustained at longer leads (up to 7 day) mainly by L–A coupling through SM predictability. Case studies of recent WesternEuropean and East Asian heatwaves further demonstrated its ability to capture land surface drying and associated temperature extremes. These findings underscore the importance of incorporating L–A coupling with multi-step optimization in advancing data-driven heatwave forecasting systems.\u003c/p\u003e","manuscriptTitle":"A Deep Learning-based Land-Atmosphere Coupled Model for Heatwave Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 18:12:12","doi":"10.21203/rs.3.rs-7484832/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-27T23:34:37+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-27T16:29:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"161933000031279957195799778750852482306","date":"2025-10-16T07:53:51+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-26T11:23:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"282615376274974091818311573669782773497","date":"2025-09-12T02:26:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"65084905521934111421194128000091333357","date":"2025-09-10T18:49:33+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-10T00:33:18+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-05T07:45:21+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-05T07:41:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Climate and Atmospheric Science","date":"2025-08-29T04:35:47+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-climate-and-atmospheric-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"npjclimatsci","sideBox":"Learn more about [npj Climate and Atmospheric Science](http://www.nature.com/npjclimatsci/)","snPcode":"41612","submissionUrl":"https://submission.springernature.com/new-submission/41612/3","title":"npj Climate and Atmospheric Science","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"NPJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d958b227-3b53-44d4-be64-8d33031942c7","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54671493,"name":"Earth and environmental sciences/Climate sciences"},{"id":54671494,"name":"Earth and environmental sciences/Environmental sciences"}],"tags":[],"updatedAt":"2026-02-09T16:00:39+00:00","versionOfRecord":{"articleIdentity":"rs-7484832","link":"https://doi.org/10.1038/s41612-025-01311-6","journal":{"identity":"npj-climate-and-atmospheric-science","isVorOnly":false,"title":"npj Climate and Atmospheric Science"},"publishedOn":"2026-02-02 15:57:27","publishedOnDateReadable":"February 2nd, 2026"},"versionCreatedAt":"2025-09-17 18:12:12","video":"","vorDoi":"10.1038/s41612-025-01311-6","vorDoiUrl":"https://doi.org/10.1038/s41612-025-01311-6","workflowStages":[]},"version":"v1","identity":"rs-7484832","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7484832","identity":"rs-7484832","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}