Comparative Streamflow Forecasting Using LSTM, GRU, and 1D-CNN Models with PSO-Based Hyperparameter Optimization and MANOVA Analysis

Comparative Streamflow Forecasting Using LSTM, GRU, and 1D-CNN Models with PSO-Based Hyperparameter Optimization and MANOVA Analysis | 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 Comparative Streamflow Forecasting Using LSTM, GRU, and 1D-CNN Models with PSO-Based Hyperparameter Optimization and MANOVA Analysis Huseyin Yildirim Dalkilic, İsmail AKGÜL, Sefa Nur Yeşilyurt, Mehmet Kürşat Öksüz, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7288736/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 5 You are reading this latest preprint version Abstract Daily flow estimation is very important for situations such as sudden floods, low flows, and drought estimation. Therefore, daily flow estimation should be performed for the planning and protection of water resources. The existence of numerous methods that can be used for daily flow estimation makes it necessary to find the best method. In this study, three deep learning methods (Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and one-dimensional Convolutional Neural Network (1D-CNN)) were compared using 31 years of observation data for daily flow estimation. These configurations were found using a complete factorial design. Performance was evaluated using standard hydrological metrics, and the influence of hyperparameters and model types was statistically examined through multivariate analysis of variance (MANOVA). The results show that PSO-based hyperparameter tuning significantly improves prediction accuracy across all models, with the number of hidden units proving to be the most influential parameter. Notably, models with 64 hidden units consistently outperformed those with 32, while further increases to 128 units yielded no additional benefit. All models achieved comparable performance when optimised, emphasising the critical role of rigorous hyperparameter selection over architectural preference. Thus, the success of the methods could be statistically evaluated. The study provides compelling evidence for integrating deep learning and metaheuristic optimization in streamflow prediction, along with valuable insights for future hydrological modelling efforts. Streamflow Prediction Deep Learning LSTM GRU 1D-CNN Hyperparameter Optimization PSO Full Text Supplementary Files HighlightDalkilicetal01.08.25.docx graphicalabstract.png Cite Share Download PDF Status: Under Review Version 1 posted Editor invited by journal 12 Mar, 2026 Reviewers agreed at journal 05 Sep, 2025 Reviewers invited by journal 05 Sep, 2025 Editor assigned by journal 05 Aug, 2025 First submitted to journal 05 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-7288736","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":510662340,"identity":"7a913441-2d1a-4111-ac2a-b406e638e6a2","order_by":0,"name":"Huseyin Yildirim Dalkilic","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABEklEQVRIiWNgGAWjYBACAxB6cEBCho2B+QCQLwEVZyOgJeGABA8bA1sCqhYe/FpA8jwGSOJ4tJhLJG/8kHDGgoeP/czHxxV/LPL4288eYPhQdpjBXvoAVi2WM9KKJRJuAB3Gk7vZ8AyPRLHEmbwExhnnDjPw8CVgd9iNHAOJhA9ALRK82yQbJCQSNzDkGDDztgG14HAZUIvxD4gWnuc/GwyAWvjfGDD/xa/FDOIwIGJsSABqkQDawohPy5lnZRYJZ0B+STOWbDggkTjjxhuDgz3n0nl4zuDQcjx5840Px+rk5NsPP/zY8Kcusb8/x/DBjzJrOfYe7FoYBLAFywEG3NHCwMB/AKfUKBgFo2AUjAIIAADFLFhpCI3M3QAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-4405-9341","institution":"Erzincan Binali Yildirim University: Erzincan Binali Yildirim Universitesi","correspondingAuthor":true,"prefix":"","firstName":"Huseyin","middleName":"Yildirim","lastName":"Dalkilic","suffix":""},{"id":510662341,"identity":"6e6dcc4f-28aa-4d5a-b365-d0e545410dc0","order_by":1,"name":"İsmail AKGÜL","email":"","orcid":"","institution":"Erzincan Üniversitesi: Erzincan Binali Yildirim Universitesi","correspondingAuthor":false,"prefix":"","firstName":"İsmail","middleName":"","lastName":"AKGÜL","suffix":""},{"id":510662342,"identity":"92d9d2ba-f1a5-4d45-8a97-efd750588efe","order_by":2,"name":"Sefa Nur Yeşilyurt","email":"","orcid":"","institution":"Dokuz Eylul University: Dokuz Eylul Universitesi","correspondingAuthor":false,"prefix":"","firstName":"Sefa","middleName":"Nur","lastName":"Yeşilyurt","suffix":""},{"id":510662343,"identity":"a87ee68b-8c07-4354-986a-8202b29a905a","order_by":3,"name":"Mehmet Kürşat Öksüz","email":"","orcid":"","institution":"Erzincan Üniversitesi: Erzincan Binali Yildirim Universitesi","correspondingAuthor":false,"prefix":"","firstName":"Mehmet","middleName":"Kürşat","lastName":"Öksüz","suffix":""},{"id":510662344,"identity":"2fb6c719-0f28-403b-bc94-550d89828017","order_by":4,"name":"Funda AKAR","email":"","orcid":"","institution":"Erzincan Üniversitesi: Erzincan Binali Yildirim Universitesi","correspondingAuthor":false,"prefix":"","firstName":"Funda","middleName":"","lastName":"AKAR","suffix":""},{"id":510662345,"identity":"f590c9c7-da6b-4c0a-b030-76d963965593","order_by":5,"name":"Barış YILMAZ","email":"","orcid":"","institution":"International Vision University","correspondingAuthor":false,"prefix":"","firstName":"Barış","middleName":"","lastName":"YILMAZ","suffix":""}],"badges":[],"createdAt":"2025-08-04 08:28:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7288736/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7288736/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91071012,"identity":"cef1e0ce-b8d2-4f9f-b0cc-985a8f9cb2a0","added_by":"auto","created_at":"2025-09-11 10:48:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1433659,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptDalkilicetal05.08.25.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7288736/v1_covered_46730fb9-4b5c-48ae-8179-e840753f8e27.pdf"},{"id":91068210,"identity":"7161e300-0fd5-4dad-8ff4-39579dff681c","added_by":"auto","created_at":"2025-09-11 10:16:03","extension":"docx","order_by":6,"title":"","display":"","copyAsset":false,"role":"supplement","size":22680,"visible":true,"origin":"","legend":"","description":"","filename":"HighlightDalkilicetal01.08.25.docx","url":"https://assets-eu.researchsquare.com/files/rs-7288736/v1/95b077cea2a6ec9720ef14ed.docx"},{"id":91068211,"identity":"f0ee4948-3d6c-48d0-9e1b-1de1c332d641","added_by":"auto","created_at":"2025-09-11 10:16:03","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"supplement","size":70869,"visible":true,"origin":"","legend":"","description":"","filename":"graphicalabstract.png","url":"https://assets-eu.researchsquare.com/files/rs-7288736/v1/17d03124c66e52f816327329.png"}],"financialInterests":"","formattedTitle":"Comparative Streamflow Forecasting Using LSTM, GRU, and 1D-CNN Models with PSO-Based Hyperparameter Optimization and MANOVA Analysis","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":"water-resources-management","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"warm","sideBox":"Learn more about [Water Resources Management](https://www.springer.com/journal/11269)","snPcode":"11269","submissionUrl":"https://submission.nature.com/new-submission/11269/3","title":"Water Resources Management","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Streamflow Prediction, Deep Learning, LSTM, GRU, 1D-CNN, Hyperparameter Optimization, PSO","lastPublishedDoi":"10.21203/rs.3.rs-7288736/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7288736/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDaily flow estimation is very important for situations such as sudden floods, low flows, and drought estimation. Therefore, daily flow estimation should be performed for the planning and protection of water resources. The existence of numerous methods that can be used for daily flow estimation makes it necessary to find the best method. In this study, three deep learning methods (Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and one-dimensional Convolutional Neural Network (1D-CNN)) were compared using 31 years of observation data for daily flow estimation. These configurations were found using a complete factorial design. Performance was evaluated using standard hydrological metrics, and the influence of hyperparameters and model types was statistically examined through multivariate analysis of variance (MANOVA). The results show that PSO-based hyperparameter tuning significantly improves prediction accuracy across all models, with the number of hidden units proving to be the most influential parameter. Notably, models with 64 hidden units consistently outperformed those with 32, while further increases to 128 units yielded no additional benefit. All models achieved comparable performance when optimised, emphasising the critical role of rigorous hyperparameter selection over architectural preference. Thus, the success of the methods could be statistically evaluated. The study provides compelling evidence for integrating deep learning and metaheuristic optimization in streamflow prediction, along with valuable insights for future hydrological modelling efforts.\u003c/p\u003e","manuscriptTitle":"Comparative Streamflow Forecasting Using LSTM, GRU, and 1D-CNN Models with PSO-Based Hyperparameter Optimization and MANOVA Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-11 10:15:58","doi":"10.21203/rs.3.rs-7288736/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvited","content":"Water Resources Management","date":"2026-03-12T13:06:52+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2025-09-05T13:38:00+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-05T08:45:29+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-05T11:42:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Water Resources Management","date":"2025-08-05T04:10:00+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"water-resources-management","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"warm","sideBox":"Learn more about [Water Resources Management](https://www.springer.com/journal/11269)","snPcode":"11269","submissionUrl":"https://submission.nature.com/new-submission/11269/3","title":"Water Resources Management","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1dfe84e4-9c01-438f-94f1-811ff938a5c8","owner":[],"postedDate":"September 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-09-11T10:15:58+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-11 10:15:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7288736","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7288736","identity":"rs-7288736","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}