Mitigating Systematic Underestimation in Short-Term Wind Speed Forecasting via Quantile Loss

Mitigating Systematic Underestimation in Short-Term Wind Speed Forecasting via Quantile Loss | 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 Mitigating Systematic Underestimation in Short-Term Wind Speed Forecasting via Quantile Loss Ziyu Wang, Du Cheng, Zhijun Wang, Jun Wei, Guiting Song This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8685390/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Accurate short-term wind speed forecasting is pivotal for wind power integration. Deep learning models have shown promise but often suffer from distributional bias. Since wind speed follows a right-skewed Weibull distribution, the scarcity of high-wind-speed samples creates a data imbalance that predisposes deep learning models to systematic underestimation. To address this, we propose a lightweight strategy incorporating quantile loss to guide model training. By imposing asymmetric penalties, this method forces the model to better capture the tail of the distribution. We evaluate this approach using three representative spatiotemporal models (Conv3D, SimVP, and MFWPN). The results show that the proposed method not only effectively mitigates systematic negative bias but also significantly enhances the detection of extreme wind events. Specifically, the models exhibit improved Probability of Detection (POD) and Critical Success Index (CSI) scores, demonstrating that quantile loss is a robust and generalizable solution for high-impact wind speed forecasting. Deep learning Wind speed forecasting Weibull distribution Quantile Loss Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 24 Mar, 2026 Reviews received at journal 22 Mar, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviews received at journal 03 Mar, 2026 Reviewers agreed at journal 04 Feb, 2026 Reviewers invited by journal 04 Feb, 2026 Editor assigned by journal 29 Jan, 2026 Submission checks completed at journal 29 Jan, 2026 First submitted to journal 24 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-8685390","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":585492374,"identity":"21894e09-89a5-4162-aab9-8212379766d6","order_by":0,"name":"Ziyu Wang","email":"","orcid":"","institution":"Sun Yat-Sen University and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)","correspondingAuthor":false,"prefix":"","firstName":"Ziyu","middleName":"","lastName":"Wang","suffix":""},{"id":585492375,"identity":"36ac56b7-d32f-4720-a74c-da3e9134a90a","order_by":1,"name":"Du Cheng","email":"","orcid":"","institution":"Jilin University","correspondingAuthor":false,"prefix":"","firstName":"Du","middleName":"","lastName":"Cheng","suffix":""},{"id":585492376,"identity":"feee868d-0080-4a53-afc2-be148fb98979","order_by":2,"name":"Zhijun Wang","email":"","orcid":"","institution":"Zhuhai College of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhijun","middleName":"","lastName":"Wang","suffix":""},{"id":585492377,"identity":"eefd812c-fb68-4c98-b785-1d8968e979d3","order_by":3,"name":"Jun Wei","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIiWNgGAWjYFACxgYDBoZ/ckBG4wGYmAQRWg4YgxjEagGDA4kNIJIoLQbHmxuKeXfcSV/bfhhoy5/D9gYHmA/e5mGwy8Op5czBBmPeM89yt51JbDjA2HY4ccMBtmRrHobkYlxazG4kArW0MeduOwDS0nA4weAAj5k0D9SpWLXcfwjWkm52/iHMYfzf8Gu5wQjScjgBZN0BBrbDjBsO8LDh1WIP9ILh3LY0w203gLYktqUnzjzMZmw5xyAZpxbJ9uPPDN622cibnU9/+ODDH2t7vuPND2+8qbDDqQUI2AzgzASGZgYGZhDLAKdyEGB+gMSpw6t0FIyCUTAKRiYAAA02Yr2IWgm+AAAAAElFTkSuQmCC","orcid":"","institution":"Sun Yat-Sen University and Southern Marine Science and Engineering Guangdong Laboratory (Zhuhai)","correspondingAuthor":true,"prefix":"","firstName":"Jun","middleName":"","lastName":"Wei","suffix":""},{"id":585492378,"identity":"a2ea5893-0f71-466a-997c-c0ce5c7c8db0","order_by":4,"name":"Guiting Song","email":"","orcid":"","institution":"Sun Yat-Sen University","correspondingAuthor":false,"prefix":"","firstName":"Guiting","middleName":"","lastName":"Song","suffix":""}],"badges":[],"createdAt":"2026-01-24 09:23:31","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8685390/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8685390/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102295505,"identity":"0d0d9783-3827-4338-bb17-0ab197e6eadb","added_by":"auto","created_at":"2026-02-10 10:11:52","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":7031577,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8685390/v1_covered_f1651cea-913c-4f80-a2cc-d3fab18f85fc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Mitigating Systematic Underestimation in Short-Term Wind Speed Forecasting via Quantile Loss","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"geoscience-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gosl","sideBox":"Learn more about [Geoscience Letters](https://geoscienceletters.springeropen.com/)","snPcode":"40562","submissionUrl":"https://submission.springernature.com/new-submission/40562/3","title":"Geoscience Letters","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Deep learning, Wind speed forecasting, Weibull distribution, Quantile Loss","lastPublishedDoi":"10.21203/rs.3.rs-8685390/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8685390/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate short-term wind speed forecasting is pivotal for wind power integration. Deep learning models have shown promise but often suffer from distributional bias. Since wind speed follows a right-skewed Weibull distribution, the scarcity of high-wind-speed samples creates a data imbalance that predisposes deep learning models to systematic underestimation. To address this, we propose a lightweight strategy incorporating quantile loss to guide model training. By imposing asymmetric penalties, this method forces the model to better capture the tail of the distribution. We evaluate this approach using three representative spatiotemporal models (Conv3D, SimVP, and MFWPN). The results show that the proposed method not only effectively mitigates systematic negative bias but also significantly enhances the detection of extreme wind events. Specifically, the models exhibit improved Probability of Detection (POD) and Critical Success Index (CSI) scores, demonstrating that quantile loss is a robust and generalizable solution for high-impact wind speed forecasting.","manuscriptTitle":"Mitigating Systematic Underestimation in Short-Term Wind Speed Forecasting via Quantile Loss","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-06 09:59:52","doi":"10.21203/rs.3.rs-8685390/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-24T07:39:56+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-23T03:20:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"124111111804324938765240933808566081961","date":"2026-03-20T09:08:00+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-03T16:01:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"129258233741034268323352943972688387649","date":"2026-02-04T07:18:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-04T05:31:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-30T02:55:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-29T07:11:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"Geoscience Letters","date":"2026-01-24T09:18:48+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"geoscience-letters","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"gosl","sideBox":"Learn more about [Geoscience Letters](https://geoscienceletters.springeropen.com/)","snPcode":"40562","submissionUrl":"https://submission.springernature.com/new-submission/40562/3","title":"Geoscience Letters","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"34bf5439-f9a3-4da5-b590-3309c90c4ad4","owner":[],"postedDate":"February 6th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-03-24T07:57:40+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-06 09:59:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8685390","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8685390","identity":"rs-8685390","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}