Transformer-based Surrogate Downscaling Model for Nested Numerical Weather Prediction Grids

Transformer-based Surrogate Downscaling Model for Nested Numerical Weather Prediction Grids | 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 Transformer-based Surrogate Downscaling Model for Nested Numerical Weather Prediction Grids Luan Vieira, Laura Bahiense, Luiz Paulo de Freitas Assad, Alexandre Gonçalves Evsukoff This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8545679/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 11 You are reading this latest preprint version Abstract High-resolution numerical weather prediction remains computationally expensive. We develop a Transformer-based surrogatedownscaling model for the WRF model, trained on a publicly available multiresolution WRF dataset with three nested domains(9 km, 3 km, and 1 km) over the southwestern Atlantic. The surrogate targets 10 m wind speed and follows an encoder-Transformer-decoder architecture to replace the inner nests (D02 and D03) with a learned mapping from the coarse outerdomain and surface fields to high-resolution winds. We evaluate three downscaling pairs (D01→D02, D02→D03, D01→D03)under 5-fold cross-validation and two input configurations: single-channel input (wind speed) and three-channel input (windspeed, near-surface air temperature, and surface pressure). Results are compared against bicubic interpolation with meanabsolute error and a Sobel gradient metrics over the full-grid, land, and sea. Across all domain pairs, regions, and input settings,the surrogate outperforms bicubic interpolation in at least 82.7% of timesteps. The D01→D02 pair, with higher target land ratio,exhibits the strongest gains: all timesteps improve on land and in the full-grid for Sobel, and land MAE improves in all timestepsfor the three-variable configuration and in all but one timestep for the single-variable model. Improvements are still consistentsfor predominantly oceanic targets and for the more challenging 9 km→1 km mapping. These results indicate that the surrogatecan effectively emulate high-resolution WRF nests for near-surface wind. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 23 Apr, 2026 Reviews received at journal 23 Apr, 2026 Reviewers agreed at journal 01 Apr, 2026 Reviews received at journal 09 Mar, 2026 Reviews received at journal 05 Feb, 2026 Reviewers agreed at journal 23 Jan, 2026 Reviewers agreed at journal 20 Jan, 2026 Reviewers invited by journal 20 Jan, 2026 Editor assigned by journal 09 Jan, 2026 Submission checks completed at journal 09 Jan, 2026 First submitted to journal 07 Jan, 2026 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-8545679","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":572866818,"identity":"0af17361-600e-4852-88fd-413775a0015b","order_by":0,"name":"Luan Vieira","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuUlEQVRIiWNgGAWjYBACPhDxAcxkfMAgwXCAsBY2kNoZYCazAfFamHlgWhiI0iKR/OyxTY2NPYNEMtsHC4Y7+URoSTM3zjmWltggkcw8Q4LhmWUDYS0JZtK5DYcTGCTyDwP9ctiACFvSv0lbNhwGOYyZWC05ZtKMDYcZG4jXwvOmTLIH6Jc2nsdALQbPCGvhZ0/fJvEDGGL87MnMzBIVdwhrQVgHxMwSJGiAAMYPpOoYBaNgFIyCEQEAce0tWfwnAuMAAAAASUVORK5CYII=","orcid":"","institution":"Federal University of Rio de Janeiro","correspondingAuthor":true,"prefix":"","firstName":"Luan","middleName":"","lastName":"Vieira","suffix":""},{"id":572866819,"identity":"17bd8143-1198-4a42-9f12-38123cbf12b4","order_by":1,"name":"Laura Bahiense","email":"","orcid":"","institution":"Federal University of Rio de Janeiro","correspondingAuthor":false,"prefix":"","firstName":"Laura","middleName":"","lastName":"Bahiense","suffix":""},{"id":572866820,"identity":"d225d344-faf3-4ddc-9597-19453cea4342","order_by":2,"name":"Luiz Paulo de Freitas Assad","email":"","orcid":"","institution":"Federal University of Rio de Janeiro","correspondingAuthor":false,"prefix":"","firstName":"Luiz","middleName":"Paulo de Freitas","lastName":"Assad","suffix":""},{"id":572866821,"identity":"b1d66948-4391-4370-ad68-7474fa6bbaa5","order_by":3,"name":"Alexandre Gonçalves Evsukoff","email":"","orcid":"","institution":"Federal University of Rio de Janeiro","correspondingAuthor":false,"prefix":"","firstName":"Alexandre","middleName":"Gonçalves","lastName":"Evsukoff","suffix":""}],"badges":[],"createdAt":"2026-01-08 00:38:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8545679/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8545679/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100193783,"identity":"9441460d-cfc3-4be0-b3a9-c2591b4ecaf0","added_by":"auto","created_at":"2026-01-14 02:41:40","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5827,"visible":true,"origin":"","legend":"","description":"","filename":"e1ef836ce5b14977af5bd21e7dd75ed8.json","url":"https://assets-eu.researchsquare.com/files/rs-8545679/v1/cfa3c6c1be4ad1736185db8a.json"},{"id":100369973,"identity":"3aa6dd98-4475-4741-a2d6-09ebad746521","added_by":"auto","created_at":"2026-01-16 07:59:43","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4163959,"visible":true,"origin":"","legend":"","description":"","filename":"TransformerbasedSurrogateDownscalingModelforNestedNumericalWeatherPredictionGrids.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8545679/v1_covered_6b39f1c0-fcb8-4f20-875b-8e9e9e592e2d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Transformer-based Surrogate Downscaling Model for Nested Numerical Weather Prediction Grids","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":false,"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":"theoretical-and-applied-climatology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"taac","sideBox":"Learn more about [Theoretical and Applied Climatology](https://www.springer.com/journal/704)","snPcode":"704","submissionUrl":"https://submission.nature.com/new-submission/704/3","title":"Theoretical and Applied Climatology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8545679/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8545679/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"High-resolution numerical weather prediction remains computationally expensive. We develop a Transformer-based surrogatedownscaling model for the WRF model, trained on a publicly available multiresolution WRF dataset with three nested domains(9 km, 3 km, and 1 km) over the southwestern Atlantic. The surrogate targets 10 m wind speed and follows an encoder-Transformer-decoder architecture to replace the inner nests (D02 and D03) with a learned mapping from the coarse outerdomain and surface fields to high-resolution winds. We evaluate three downscaling pairs (D01→D02, D02→D03, D01→D03)under 5-fold cross-validation and two input configurations: single-channel input (wind speed) and three-channel input (windspeed, near-surface air temperature, and surface pressure). Results are compared against bicubic interpolation with meanabsolute error and a Sobel gradient metrics over the full-grid, land, and sea. Across all domain pairs, regions, and input settings,the surrogate outperforms bicubic interpolation in at least 82.7% of timesteps. The D01→D02 pair, with higher target land ratio,exhibits the strongest gains: all timesteps improve on land and in the full-grid for Sobel, and land MAE improves in all timestepsfor the three-variable configuration and in all but one timestep for the single-variable model. Improvements are still consistentsfor predominantly oceanic targets and for the more challenging 9 km→1 km mapping. These results indicate that the surrogatecan effectively emulate high-resolution WRF nests for near-surface wind.","manuscriptTitle":"Transformer-based Surrogate Downscaling Model for Nested Numerical Weather Prediction Grids","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-14 02:41:34","doi":"10.21203/rs.3.rs-8545679/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-23T09:52:45+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-23T09:09:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"174205718319945631882793176561969889899","date":"2026-04-02T03:57:57+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-09T07:24:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-05T18:37:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"159049676936380424069629808877539365639","date":"2026-01-23T09:07:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"23254907403902271116828134630463536989","date":"2026-01-20T16:30:15+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-20T11:45:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-10T01:50:14+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-10T01:49:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"Theoretical and Applied Climatology","date":"2026-01-08T00:26:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"theoretical-and-applied-climatology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"taac","sideBox":"Learn more about [Theoretical and Applied Climatology](https://www.springer.com/journal/704)","snPcode":"704","submissionUrl":"https://submission.nature.com/new-submission/704/3","title":"Theoretical and Applied Climatology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"16f939e5-d41d-49fc-8cb7-1b1b50322593","owner":[],"postedDate":"January 14th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-23T10:08:32+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-14 02:41:34","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8545679","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8545679","identity":"rs-8545679","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}