A new strong convective precipitation forecasting method based on attention mechanism and spatio-temporal reasoning

A new strong convective precipitation forecasting method based on attention mechanism and spatio-temporal reasoning | 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 new strong convective precipitation forecasting method based on attention mechanism and spatio-temporal reasoning Guoyu Zhao, Zhangu Wang, Ziliang Zhao, Jun Zhao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4002513/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Aug, 2024 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract Radar observation variables reflect the precipitation amount of strong convective precipitation processes, which accurate forecast is an important difficulty in weather forecasting. Current forecasting methods are mostly based on radar echo extrapolation, which has the insufficiency of input information and the ineffectiveness of model architecture. This paper presents a Bidirectional Long Short-Term Memory forecasting method for strong convective precipitation based on the attention mechanism and residual neural network (ResNet-Attention-BiLSTM). First, this paper uses ResNet to effectively extract the key information of extreme weather and solves the problem of regression to the mean of the prediction model by learning the residuals of the radar observation data. Second, this paper uses the attention mechanism to adaptively weight the fusion of the features to enhance the extraction of the important features of the precipitation image data. On this basis, this paper presents a novel spatio-temporal reasoning method for radar observations and establishes a precipitation forecasting model, which captures the past and future time-order relationship of the sequence data. Finally, this paper conducts experiments based on the real collected data of a strong convective precipitation process and compares its performance with the existing models, the mean absolute percentage error of this model was reduced by 15.94% (1km), 18.72% (3km), and 14.91% (7km), and the prediction accuracy (R2) was increased by 10.89% (1km), 9.61% (3km), and 9.29% (7km), which proves the state of the art and effectiveness of this forecasting model. Earth and environmental sciences/Climate sciences/Atmospheric science Physical sciences/Physics/Techniques and instrumentation Physical sciences/Mathematics and computing/Computer science Strong convective precipitation forecasting BiLSTM ResNet deep learning attention mechanism Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 16 Aug, 2024 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 30 May, 2024 Reviews received at journal 28 May, 2024 Reviewers agreed at journal 22 May, 2024 Reviews received at journal 23 Mar, 2024 Reviewers agreed at journal 15 Mar, 2024 Reviewers invited by journal 13 Mar, 2024 Editor assigned by journal 08 Mar, 2024 Editor invited by journal 08 Mar, 2024 Submission checks completed at journal 08 Mar, 2024 First submitted to journal 01 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-4002513","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":278096507,"identity":"ca131fdf-bb19-4850-8890-8319a2d11ae0","order_by":0,"name":"Guoyu Zhao","email":"","orcid":"","institution":"China University of Geosciences","correspondingAuthor":false,"prefix":"","firstName":"Guoyu","middleName":"","lastName":"Zhao","suffix":""},{"id":278096508,"identity":"1744de63-cd2e-4ff4-98bc-1f149b93f554","order_by":1,"name":"Zhangu Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYLACxgYw2fggoaKGJC3MzQYPzhwjSQt7m+TDFmbCqg2Onz388ucOuzz5iMS2isQGNgb+9u4E/FrO5KVZSJ5JLja8kdh2I3GHDIPEmbMb8GoxO5BjZmDYxpy4cQZIyxk2BgOJXAJazr8xM0hsqwdrKUhsYyZCy40c4wcH2w4nzpdIbGMgSov9jTdmjI1txxM38Dxslkg4c4yHoF8k+3OMP/5sq06c357+8OOPiho5/vZe/FqAgE0CRBocgPB4CCkHAeYPIFK+gRi1o2AUjIJRMCIBAHInUYwCsLObAAAAAElFTkSuQmCC","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Zhangu","middleName":"","lastName":"Wang","suffix":""},{"id":278096509,"identity":"f36a27d8-3cc6-4f63-9d58-bab541415b43","order_by":2,"name":"Ziliang Zhao","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ziliang","middleName":"","lastName":"Zhao","suffix":""},{"id":278096510,"identity":"d316b56f-817e-4c6a-ad4a-95462b4ee8d7","order_by":3,"name":"Jun Zhao","email":"","orcid":"","institution":"Shandong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jun","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2024-03-01 08:04:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4002513/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4002513/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-024-68951-1","type":"published","date":"2024-08-16T15:56:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":63070815,"identity":"91eeaa3f-c70c-4018-a234-74dbcc82c91b","added_by":"auto","created_at":"2024-08-22 19:54:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8284033,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4002513/v1_covered_8c937635-8ffb-4aad-8713-8d289530a882.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A new strong convective precipitation forecasting method based on attention mechanism and spatio-temporal reasoning","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Strong convective precipitation forecasting, BiLSTM, ResNet, deep learning, attention mechanism","lastPublishedDoi":"10.21203/rs.3.rs-4002513/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4002513/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Radar observation variables reflect the precipitation amount of strong convective precipitation processes, which accurate forecast is an important difficulty in weather forecasting. Current forecasting methods are mostly based on radar echo extrapolation, which has the insufficiency of input information and the ineffectiveness of model architecture. This paper presents a Bidirectional Long Short-Term Memory forecasting method for strong convective precipitation based on the attention mechanism and residual neural network (ResNet-Attention-BiLSTM). First, this paper uses ResNet to effectively extract the key information of extreme weather and solves the problem of regression to the mean of the prediction model by learning the residuals of the radar observation data. Second, this paper uses the attention mechanism to adaptively weight the fusion of the features to enhance the extraction of the important features of the precipitation image data. On this basis, this paper presents a novel spatio-temporal reasoning method for radar observations and establishes a precipitation forecasting model, which captures the past and future time-order relationship of the sequence data. Finally, this paper conducts experiments based on the real collected data of a strong convective precipitation process and compares its performance with the existing models, the mean absolute percentage error of this model was reduced by 15.94% (1km), 18.72% (3km), and 14.91% (7km), and the prediction accuracy (R2) was increased by 10.89% (1km), 9.61% (3km), and 9.29% (7km), which proves the state of the art and effectiveness of this forecasting model.","manuscriptTitle":"A new strong convective precipitation forecasting method based on attention mechanism and spatio-temporal reasoning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-12 06:21:23","doi":"10.21203/rs.3.rs-4002513/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-05-30T05:25:02+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-05-28T23:03:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"299776083741899199271427371433985000089","date":"2024-05-22T15:43:30+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-03-23T14:23:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"561c1deb-58e1-435e-8926-656533efb9eb_SNPRID","date":"2024-03-15T12:58:24+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-03-13T17:44:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-03-08T16:40:05+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-03-08T11:42:47+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-03-08T11:36:35+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2024-03-01T07:25:08+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"584c2ecd-7aab-4d68-8f67-437f956a7435","owner":[],"postedDate":"March 12th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":29291118,"name":"Earth and environmental sciences/Climate sciences/Atmospheric science"},{"id":29291119,"name":"Physical sciences/Physics/Techniques and instrumentation"},{"id":29291120,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-08-22T19:26:26+00:00","versionOfRecord":{"articleIdentity":"rs-4002513","link":"https://doi.org/10.1038/s41598-024-68951-1","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2024-08-16 15:56:52","publishedOnDateReadable":"August 16th, 2024"},"versionCreatedAt":"2024-03-12 06:21:23","video":"","vorDoi":"10.1038/s41598-024-68951-1","vorDoiUrl":"https://doi.org/10.1038/s41598-024-68951-1","workflowStages":[]},"version":"v1","identity":"rs-4002513","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4002513","identity":"rs-4002513","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}