Hybrid Neural Hierarchical Interpolation Time Series with STL Optimized by Multi-Agent HPO for Flow Forecasting in Hydroelectric Power Plants

Hybrid Neural Hierarchical Interpolation Time Series with STL Optimized by Multi-Agent HPO for Flow Forecasting in Hydroelectric Power Plants | 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 Hybrid Neural Hierarchical Interpolation Time Series with STL Optimized by Multi-Agent HPO for Flow Forecasting in Hydroelectric Power Plants Rafael Ninno Muniz, William Gouvêa Buratto, Gabriel Villarrubia Gonzalez, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7943519/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Accurate forecasting of reservoir levels in hydroelectric power plants is essential for efficient energy generation, operational safety, and sustainable water management. This study proposes a hybrid forecasting framework that integrates Seasonal-Trend Decomposition using Loess (STL) with the Neural Hierarchical Interpolation Time Series (NHITS) model optimized through Multi-Agent Hyperparameter Optimization (HPO). The STL filter is employed to remove high-frequency noise and preserve underlying signal trends, enhancing the quality of inputs for the predictive model. The NHITS architecture leverages hierarchical multi-scale processing and interpolation-based reconstruction to capture both short- and long-term temporal dependencies, while the Multi-Agent HPO framework ensures optimal hyperparameter configuration through cooperative agent-based exploration. The proposed method was evaluated using turbine flow data from the Santo Antônio Hydroelectric Power Plant in Brazil, achieving superior performance compared to state-of-the-art benchmarks, including transformer-based and recurrent models, across very short- and short-term forecasting horizons. The model demonstrated substantial reductions in RMSE, MAE, MAPE, and MSLE, while maintaining competitive inference times. The results confirm that the STL–NHITS architecture optimized via Multi-Agent HPO offers an efficient, robust, and interpretable solution for hydropower forecasting, providing a valuable tool for intelligent management of renewable energy systems. Time series forecasting Signal denoising Seasonal-Trend Decomposition using Loess Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted 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-7943519","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":534673204,"identity":"20bda3cb-383e-4ec5-a20b-d26d867e6fb2","order_by":0,"name":"Rafael Ninno Muniz","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie3OsQrCQAyA4ZTCdRFc46A+gXBFcBKf5YqripMIglYK59IH8GEEcwjtUpy7qQhOLm66eRUnkbZuDveTbPkgACbTn0Z6qwD28igYgBMQK0VqPlgBz0glEsUE3kQilCGt9VCpx6aH1dVSTo8T8EIG7DzNIZ10JAgvfcREyVTsX8Rxk1wy4MTJnkPqST3gbZs+028WEEELbB5OcpyR7LFiQrRDnlr6vhRJrlz5FKObeAGKPbZDZq3cXBIP2rc7zbAR79TtPunWQ2ZHpzzyGeq1fgEmk8lk+tYTu6ZSQipFDboAAAAASUVORK5CYII=","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Rafael","middleName":"Ninno","lastName":"Muniz","suffix":""},{"id":534673205,"identity":"f0cc2c2f-7041-4dcb-b192-cc6109c9d5f2","order_by":1,"name":"William Gouvêa Buratto","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"William","middleName":"Gouvêa","lastName":"Buratto","suffix":""},{"id":534673206,"identity":"811fe544-7897-4836-91ed-37587fc8a9f3","order_by":2,"name":"Gabriel Villarrubia Gonzalez","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Gabriel","middleName":"Villarrubia","lastName":"Gonzalez","suffix":""},{"id":534673207,"identity":"a4ae5f31-dafd-4b8f-aeac-af16b1be28b1","order_by":3,"name":"Laio Oriel Seman","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Laio","middleName":"Oriel","lastName":"Seman","suffix":""},{"id":534673208,"identity":"b4391ac9-fa0f-4be7-8b82-737194fe463a","order_by":4,"name":"Valdeci José Costa","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Valdeci","middleName":"José","lastName":"Costa","suffix":""},{"id":534673209,"identity":"4cdf97be-e617-42ca-94b3-f8bcb07b3655","order_by":5,"name":"Ademir Nied","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ademir","middleName":"","lastName":"Nied","suffix":""}],"badges":[],"createdAt":"2025-10-26 16:13:11","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-7943519/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7943519/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94612237,"identity":"31fefea0-5f2f-4df5-942b-cae26310f269","added_by":"auto","created_at":"2025-10-29 02:07:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":992475,"visible":true,"origin":"","legend":"","description":"","filename":"PaperSpringerRafaelSubmetidoSR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7943519/v1_covered_0e4937fc-ff28-4f3d-96ce-b6384f30de9d.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eHybrid Neural Hierarchical Interpolation Time Series with STL Optimized by Multi-Agent HPO for Flow Forecasting in Hydroelectric Power Plants\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Salamanca","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Time series forecasting, Signal denoising, Seasonal-Trend Decomposition using Loess","lastPublishedDoi":"10.21203/rs.3.rs-7943519/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7943519/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate forecasting of reservoir levels in hydroelectric power plants is essential for efficient energy generation, operational safety, and sustainable water management. This study proposes a hybrid forecasting framework that integrates Seasonal-Trend Decomposition using Loess (STL) with the Neural Hierarchical Interpolation Time Series (NHITS) model optimized through Multi-Agent Hyperparameter Optimization (HPO). The STL filter is employed to remove high-frequency noise and preserve underlying signal trends, enhancing the quality of inputs for the predictive model. The NHITS architecture leverages hierarchical multi-scale processing and interpolation-based reconstruction to capture both short- and long-term temporal dependencies, while the Multi-Agent HPO framework ensures optimal hyperparameter configuration through cooperative agent-based exploration. The proposed method was evaluated using turbine flow data from the Santo Antônio Hydroelectric Power Plant in Brazil, achieving superior performance compared to state-of-the-art benchmarks, including transformer-based and recurrent models, across very short- and short-term forecasting horizons. The model demonstrated substantial reductions in RMSE, MAE, MAPE, and MSLE, while maintaining competitive inference times. The results confirm that the STL–NHITS architecture optimized via Multi-Agent HPO offers an efficient, robust, and interpretable solution for hydropower forecasting, providing a valuable tool for intelligent management of renewable energy systems.\u003c/p\u003e","manuscriptTitle":"Hybrid Neural Hierarchical Interpolation Time Series with STL Optimized by Multi-Agent HPO for Flow Forecasting in Hydroelectric Power Plants","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-28 20:17:00","doi":"10.21203/rs.3.rs-7943519/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"583e1b95-8bb4-438a-8add-37c1d5319897","owner":[],"postedDate":"October 28th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-28T20:17:00+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-28 20:17:00","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7943519","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7943519","identity":"rs-7943519","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}