A multi-scale deep learning framework for medium-long-term streamflow forecasting based on EMD-TCN-GRU

A multi-scale deep learning framework for medium-long-term streamflow forecasting based on EMD-TCN-GRU | 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 A multi-scale deep learning framework for medium-long-term streamflow forecasting based on EMD-TCN-GRU Tiantian Li, Jihua Chen, Yingping Huang, Jingcheng Han, Biao Xiong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7444917/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 22 Dec, 2025 Read the published version in Natural Hazards → Version 1 posted 4 You are reading this latest preprint version Abstract Accurate medium-long-term streamflow forecasting underpins flood mitigation and water-resource management across the Yangtze River Basin. Single deep-learning approaches remain challenged by non-stationarity, intricate long-range dependencies, and extreme-event sparsity. We propose an EMD-TCN-GRU framework: empirical mode decomposition (EMD) decomposes daily discharge into quasi-stationary modes and a residual, temporal convolutional networks (TCN) extract multi-scale temporal features in parallel, and gated recurrent units (GRU) generate multi-step forecasts for each component prior to linear recombination. When the forecast horizon is set at 3 days, the model—trained on 2013-2022 Wuhan observations—records an R2 of 0.9951 and a MAPE of 2.87%. Extending to 7 days, the R2 is 0.9925 and the MAPE is 3.22%. At 15 days, the R2 remains at 0.9922 while the MAPE is 3.25%. Compared to a standard GRU, the MAE is reduced by 63%, 51%, and 58%, respectively, and performance decay over time is negligible. Systematic ablation studies corroborate that the decomposition-convolution-gating pipeline is the primary factor in the observed increase in accuracy. The elimination of EMD serves to amplify residual noise, while the removal of TCN results in the severing of long-range information pathways. Furthermore, the substitution of multi-step GRU forecasting with single-step GRU forecasting triggers rapid error accumulation. The framework provides a robust, transferable solution for real-time flood warning and medium-long-term water allocation in the Yangtze River and analogous complex networks. Flow prediction EMD TCN GRU Yangtze River Full Text Cite Share Download PDF Status: Published Journal Publication published 22 Dec, 2025 Read the published version in Natural Hazards → Version 1 posted Reviewers invited by journal 16 Sep, 2025 Editor assigned by journal 15 Sep, 2025 First submitted to journal 14 Sep, 2025 Editorial decision: Minor revisions 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-7444917","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":516134712,"identity":"fc20c09e-6754-47a8-8aae-7476fdedf563","order_by":0,"name":"Tiantian Li","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Tiantian","middleName":"","lastName":"Li","suffix":""},{"id":516134713,"identity":"27dfca09-848f-43c0-9fae-c8f15bd1aa65","order_by":1,"name":"Jihua Chen","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Jihua","middleName":"","lastName":"Chen","suffix":""},{"id":516134714,"identity":"8c89275b-42a7-443d-9420-32d9c078595d","order_by":2,"name":"Yingping Huang","email":"","orcid":"","institution":"China Three Gorges University","correspondingAuthor":false,"prefix":"","firstName":"Yingping","middleName":"","lastName":"Huang","suffix":""},{"id":516134715,"identity":"1afb9832-2942-40bb-b148-345d7d60521e","order_by":3,"name":"Jingcheng Han","email":"","orcid":"","institution":"Shenzhen University","correspondingAuthor":false,"prefix":"","firstName":"Jingcheng","middleName":"","lastName":"Han","suffix":""},{"id":516134716,"identity":"f9a63fc8-d42b-44b0-a208-cb7cc6e67cde","order_by":4,"name":"Biao Xiong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyklEQVRIiWNgGAWjYBACNmb+zw8S/9jI8bM3HyBOCx87g5nBx4Y0Y8meYwnEaZHjZzCQnNlwOHHDDB8DYh3GkGDMu4PZ2ECC5+ONNwx2croNhLUceMx7hk3OXLp3s+UchmRjswMEtTA2GPOw8Rhbzjm7TZqH4UDiNsJamBmkedgkEjfcyHlGrBY2BsmZbQYgLWzEauFhM/hwJgEUyEDHGRDhF/n+M8wPEir+g6Ly4Y03FXZyBLWgAAkeIqMGWQupOkbBKBgFo2BEAADGfj2h7emcQQAAAABJRU5ErkJggg==","orcid":"","institution":"China Three Gorges University","correspondingAuthor":true,"prefix":"","firstName":"Biao","middleName":"","lastName":"Xiong","suffix":""}],"badges":[],"createdAt":"2025-08-24 08:23:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7444917/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7444917/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11069-025-07734-x","type":"published","date":"2025-12-22T15:58:33+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92252861,"identity":"0bc121bc-4cf7-4e0e-b2b4-a1c810bfb1ac","added_by":"auto","created_at":"2025-09-26 10:57:04","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":10339,"visible":true,"origin":"","legend":"","description":"","filename":"nhazNHAZD2502831.xml","url":"https://assets-eu.researchsquare.com/files/rs-7444917/v1/4a0f1d52af059d43aab0a2a2.xml"},{"id":92252097,"identity":"44c2d142-98ff-44e0-a1a9-33c93b7a4fb8","added_by":"auto","created_at":"2025-09-26 10:49:04","extension":"xml","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1009,"visible":true,"origin":"","legend":"","description":"","filename":"NHAZD250283153730.go.xml","url":"https://assets-eu.researchsquare.com/files/rs-7444917/v1/d745e96bc01ad9f0a43171af.xml"},{"id":92252099,"identity":"4b751a27-2679-40c6-a27d-f86b115eeb02","added_by":"auto","created_at":"2025-09-26 10:49:05","extension":"xml","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":859,"visible":true,"origin":"","legend":"","description":"","filename":"NHAZD2502831Import.xml","url":"https://assets-eu.researchsquare.com/files/rs-7444917/v1/a2d04c23d393ee982764a6d8.xml"},{"id":99172840,"identity":"82275bce-e009-4407-961c-18be1fb08539","added_by":"auto","created_at":"2025-12-29 16:11:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1548249,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7444917/v1_covered_f5bf2cb8-5af7-446a-b7fe-0386853d8f5f.pdf"}],"financialInterests":"","formattedTitle":"A multi-scale deep learning framework for medium-long-term streamflow forecasting based on EMD-TCN-GRU","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":"natural-hazards","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nhaz","sideBox":"Learn more about [Natural Hazards](https://www.springer.com/journal/11069)","snPcode":"11069","submissionUrl":"https://submission.nature.com/new-submission/11069/3","title":"Natural Hazards","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Flow prediction, EMD, TCN, GRU, Yangtze River","lastPublishedDoi":"10.21203/rs.3.rs-7444917/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7444917/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate medium-long-term streamflow forecasting underpins flood mitigation and water-resource management across the Yangtze River Basin. Single deep-learning approaches remain challenged by non-stationarity, intricate long-range dependencies, and extreme-event sparsity. We propose an EMD-TCN-GRU framework: empirical mode decomposition (EMD) decomposes daily discharge into quasi-stationary modes and a residual, temporal convolutional networks (TCN) extract multi-scale temporal features in parallel, and gated recurrent units (GRU) generate multi-step forecasts for each component prior to linear recombination. When the forecast horizon is set at 3 days, the model—trained on 2013-2022 Wuhan observations—records an R2 of 0.9951 and a MAPE of 2.87%. Extending to 7 days, the R2 is 0.9925 and the MAPE is 3.22%. At 15 days, the R2 remains at 0.9922 while the MAPE is 3.25%. Compared to a standard GRU, the MAE is reduced by 63%, 51%, and 58%, respectively, and performance decay over time is negligible. Systematic ablation studies corroborate that the decomposition-convolution-gating pipeline is the primary factor in the observed increase in accuracy. The elimination of EMD serves to amplify residual noise, while the removal of TCN results in the severing of long-range information pathways. Furthermore, the substitution of multi-step GRU forecasting with single-step GRU forecasting triggers rapid error accumulation. The framework provides a robust, transferable solution for real-time flood warning and medium-long-term water allocation in the Yangtze River and analogous complex networks.","manuscriptTitle":"A multi-scale deep learning framework for medium-long-term streamflow forecasting based on EMD-TCN-GRU","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-26 10:49:00","doi":"10.21203/rs.3.rs-7444917/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewersInvited","content":"","date":"2025-09-16T20:08:50+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-15T11:32:46+00:00","index":"","fulltext":""},{"type":"submitted","content":"Natural Hazards","date":"2025-09-14T08:39:52+00:00","index":"","fulltext":""},{"type":"decision","content":"Minor revisions","date":"2025-08-29T15:45:05+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"natural-hazards","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"nhaz","sideBox":"Learn more about [Natural Hazards](https://www.springer.com/journal/11069)","snPcode":"11069","submissionUrl":"https://submission.nature.com/new-submission/11069/3","title":"Natural Hazards","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"3ed11082-a379-4375-934d-66a6978b5048","owner":[],"postedDate":"September 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-12-29T16:09:23+00:00","versionOfRecord":{"articleIdentity":"rs-7444917","link":"https://doi.org/10.1007/s11069-025-07734-x","journal":{"identity":"natural-hazards","isVorOnly":false,"title":"Natural Hazards"},"publishedOn":"2025-12-22 15:58:33","publishedOnDateReadable":"December 22nd, 2025"},"versionCreatedAt":"2025-09-26 10:49:00","video":"","vorDoi":"10.1007/s11069-025-07734-x","vorDoiUrl":"https://doi.org/10.1007/s11069-025-07734-x","workflowStages":[]},"version":"v1","identity":"rs-7444917","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7444917","identity":"rs-7444917","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}