A Decomposition-Driven Hybrid Framework Based on STL for Accurate Traffic Flow Forecasting

A Decomposition-Driven Hybrid Framework Based on STL for Accurate Traffic Flow Forecasting | 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 Decomposition-Driven Hybrid Framework Based on STL for Accurate Traffic Flow Forecasting Fujiang Yuan, Yangrui Fan, Xiaohuan Bing, Zhen Tian, Chunhong Yuan, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7941600/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract Accurate traffic flow forecasting is crucial for intelligent transportation systems and urban traffic management. However, existing single-model approaches often struggle to capture the complex, nonlinear, and multi-scale temporal patterns inherent in traffic flow data. This study proposes a novel decomposition-driven hybrid framework that integrates Seasonal-Trend decomposition using Loess (STL) with three complementary predictive models to enhance forecasting accuracy and robustness. The STL method first decomposes the original traffic flow time series into three distinct components: trend, seasonal, and residual. Subsequently, a Long Short-Term Memory (LSTM) network is employed to model the trend component and capture long-range temporal dependencies, an Autoregressive Integrated Moving Average (ARIMA) model is applied to the seasonal component to exploit periodic patterns, and an Extreme Gradient Boosting (XGBoost) algorithm is utilized to predict the residual component and handle nonlinear irregularities. The final forecast is obtained through multiplicative integration of the three sub-model predictions. The proposed framework is validated using 998 traffic flow records collected from a New York City intersection between November and December 2015. Experimental results demonstrate that the LSTM-ARIMA-XGBoost hybrid model significantly outperforms individual baseline models including standalone LSTM, ARIMA, XGBoost, and their variants (xLSTM, sLSTM, mLSTM) across multiple evaluation metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R²). The decomposition strategy effectively isolates different temporal characteristics, enabling each specialized model to focus on its strength domain, thereby improving overall prediction accuracy, interpretability, and stability. This hybrid approach provides a reliable and efficient solution for real-time traffic flow forecasting in urban transportation systems. Physical sciences/Engineering Physical sciences/Mathematics and computing Traffic flow forecasting STL decomposition Hybrid model LSTM ARIMA XGBoost Intelligent transportation systems Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 15 Dec, 2025 Reviews received at journal 09 Dec, 2025 Reviewers agreed at journal 09 Dec, 2025 Reviews received at journal 05 Dec, 2025 Reviewers agreed at journal 01 Nov, 2025 Reviewers invited by journal 30 Oct, 2025 Editor assigned by journal 30 Oct, 2025 Editor invited by journal 30 Oct, 2025 Submission checks completed at journal 27 Oct, 2025 First submitted to journal 27 Oct, 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-7941600","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":542241074,"identity":"34af429c-c2fb-41b2-9fe2-4cc577722343","order_by":0,"name":"Fujiang Yuan","email":"","orcid":"","institution":"Taiyuan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Fujiang","middleName":"","lastName":"Yuan","suffix":""},{"id":542241075,"identity":"57576b53-823a-47c1-9df6-c1fbd334e545","order_by":1,"name":"Yangrui Fan","email":"","orcid":"","institution":"Taiyuan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Yangrui","middleName":"","lastName":"Fan","suffix":""},{"id":542241076,"identity":"48759ec9-dbe4-49e1-935a-98b9b8da2e45","order_by":2,"name":"Xiaohuan Bing","email":"data:image/png;base64,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","orcid":"","institution":"University of Göttingen","correspondingAuthor":true,"prefix":"","firstName":"Xiaohuan","middleName":"","lastName":"Bing","suffix":""},{"id":542241077,"identity":"be850e0f-d2aa-4bd4-8eef-4f956557f93e","order_by":3,"name":"Zhen Tian","email":"","orcid":"","institution":"University of Glasgow","correspondingAuthor":false,"prefix":"","firstName":"Zhen","middleName":"","lastName":"Tian","suffix":""},{"id":542241078,"identity":"141fc6c2-1133-464b-9beb-0787c77ceeac","order_by":4,"name":"Chunhong Yuan","email":"","orcid":"","institution":"College of Science and Technology, Ningbo University","correspondingAuthor":false,"prefix":"","firstName":"Chunhong","middleName":"","lastName":"Yuan","suffix":""},{"id":542241079,"identity":"af735980-46b2-4721-afdc-f4222086d9a8","order_by":5,"name":"Yankang Li","email":"","orcid":"","institution":"Taiyuan Normal University","correspondingAuthor":false,"prefix":"","firstName":"Yankang","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-10-25 14:35:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7941600/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7941600/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95517784,"identity":"cc8eb6ef-0ba7-442d-a1b8-9f79c84f3343","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":8530,"visible":true,"origin":"","legend":"","description":"","filename":"d56f4f7552d04b339204f1c3b70b13d0.json","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/f46ee476015df630ded8ddda.json"},{"id":95517787,"identity":"3145eddb-faf6-411b-91cd-f4d45d28f002","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94813,"visible":true,"origin":"","legend":"","description":"","filename":"d56f4f7552d04b339204f1c3b70b13d01enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/1f56045a7bfcdca44c601c3b.xml"},{"id":95517785,"identity":"091f7f7a-2460-4538-9350-7905139fb56c","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42225,"visible":true,"origin":"","legend":"","description":"","filename":"APF.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/675eb6951980615f288d6789.png"},{"id":95517792,"identity":"f6e9b597-3f2c-4a45-8fec-f69ea9421599","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155147,"visible":true,"origin":"","legend":"","description":"","filename":"ARIMA.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/72fdcda09574e773383051fe.png"},{"id":95517795,"identity":"466d4272-aa93-42a5-8498-9e1be9a83f2e","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"pdf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2821747,"visible":true,"origin":"","legend":"","description":"","filename":"ADecompositionDrivenHybridFrameworkBasedonSTLforAccurateTrafficFlowForecasting2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/05a9859bd2f8f4e5daf09a33.pdf"},{"id":95529739,"identity":"b618d4fc-5f7c-4147-9756-60efa683532d","added_by":"auto","created_at":"2025-11-10 10:17:27","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":353404,"visible":true,"origin":"","legend":"","description":"","filename":"ArimaSeasonal.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/2e498e7b055cf1cc48e7ea53.png"},{"id":95529520,"identity":"bf45413c-1dd9-492c-98b3-e729809b0404","added_by":"auto","created_at":"2025-11-10 10:17:12","extension":"doc","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16384,"visible":true,"origin":"","legend":"","description":"","filename":"CoverLetterSR.doc","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/24bad034eeed61b9bf8e48b3.doc"},{"id":95517789,"identity":"66218f46-1e6f-4833-ba7a-2b6804d4d3de","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":70817,"visible":true,"origin":"","legend":"","description":"","filename":"LSTM.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/f3b0d722b15cf5ae8bc6e5a3.png"},{"id":95529202,"identity":"1bb740cc-33c7-4ecc-b81c-5220d3e3d1e8","added_by":"auto","created_at":"2025-11-10 10:16:53","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":338194,"visible":true,"origin":"","legend":"","description":"","filename":"LSTMARIMAXGBoost.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/de7ac86727a4c2791ceb8ced.png"},{"id":95517786,"identity":"8daaee1b-011a-4601-baa9-1a1b0e94d5c3","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36922,"visible":true,"origin":"","legend":"","description":"","filename":"Revise.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/ea8373cc0e7e3b3db658bd05.pdf"},{"id":95517794,"identity":"ce2258c2-eadc-4c95-915c-2cd49faa3c56","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":223527,"visible":true,"origin":"","legend":"","description":"","filename":"STL.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/cf65f11fc58c7bafcdfc5329.png"},{"id":95529776,"identity":"98105023-4faf-4bc4-9780-652f42645f88","added_by":"auto","created_at":"2025-11-10 10:17:31","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":209642,"visible":true,"origin":"","legend":"","description":"","filename":"STLresult.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/860aca5410f40e9381c71b54.png"},{"id":95529401,"identity":"bbc65534-a68d-4d51-b525-17bf0d0c41e0","added_by":"auto","created_at":"2025-11-10 10:17:04","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":483873,"visible":true,"origin":"","legend":"","description":"","filename":"XGBoost.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/475e209e3dc1af2a42e69d94.png"},{"id":95517797,"identity":"17468999-43c8-4561-9818-38a295e40414","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"eps","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/69cc67b41166d32a3da59cf4.eps"},{"id":95529183,"identity":"c3886063-3a50-4f09-b136-3d47ec955f4e","added_by":"auto","created_at":"2025-11-10 10:16:52","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":187619,"visible":true,"origin":"","legend":"","description":"","filename":"lstmtrend.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/13d0a0ba99a41ae99937a0d7.png"},{"id":95517808,"identity":"8e5b520e-43bb-481a-bfbd-d21f5a259450","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/425c176d7480de67b2c0ef7c.bst"},{"id":95517806,"identity":"54f4b726-3ebd-4ffc-ad87-32123651b3b3","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/329410c4dc2974b1ef05baa5.bst"},{"id":95517801,"identity":"b7e866e5-9331-4ee2-b51b-a02dbaf324ba","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/9d6e4cc34ea203bc6b0fecb3.bst"},{"id":95529316,"identity":"c8dee1c1-038a-4181-81ff-6c199c88c175","added_by":"auto","created_at":"2025-11-10 10:16:58","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/25cd7106cbf972ccde96ee6b.bst"},{"id":95529244,"identity":"86e28bc8-c75f-4e2f-b434-ce60146ce9e9","added_by":"auto","created_at":"2025-11-10 10:16:55","extension":"cls","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/cda274ea69064a8e11c0388b.cls"},{"id":95529913,"identity":"c744c9c3-2377-4079-83ed-2860ed7e343d","added_by":"auto","created_at":"2025-11-10 10:17:41","extension":"bst","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/2e0ff580b8270de2c0743a38.bst"},{"id":95517799,"identity":"f2b8424a-6288-4cb5-a0ba-dc1be78bb4fe","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"bst","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/fb0869c87fcc1540965ed637.bst"},{"id":95517807,"identity":"26ee0666-e024-4597-9df6-be192db24f4c","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/a0f08afe1ec2a2256ea52ef9.bst"},{"id":95517809,"identity":"3e0d4669-59c2-43f5-9cde-14efbba8f621","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"bst","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/b6c49306850b97438fd0c8bc.bst"},{"id":95517813,"identity":"beb7da1f-2e08-44eb-889b-25bb07176272","added_by":"auto","created_at":"2025-11-10 08:48:09","extension":"bst","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/1bc3d7652be0dc80b83fa454.bst"},{"id":95517803,"identity":"10f898ae-1985-45b1-9070-8aa5356257d0","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":283279,"visible":true,"origin":"","legend":"","description":"","filename":"total.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/be43fd9c0ad50d8bb137a78e.png"},{"id":95529743,"identity":"696944e0-b4f9-42eb-86b8-a33f02a6d8e9","added_by":"auto","created_at":"2025-11-10 10:17:27","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29481,"visible":true,"origin":"","legend":"","description":"","filename":"traffic.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/78722cc1dd1a777fbf65ca16.png"},{"id":95529190,"identity":"dbbc21e8-26cd-4132-8716-c0caf2692a79","added_by":"auto","created_at":"2025-11-10 10:16:52","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":283698,"visible":true,"origin":"","legend":"","description":"","filename":"xgboostresid.png","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/b8a9f48bea0d987f4c16442b.png"},{"id":95517810,"identity":"4a00d66e-4af0-47a4-9d80-2676d6d6514f","added_by":"auto","created_at":"2025-11-10 08:48:08","extension":"xml","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103734,"visible":true,"origin":"","legend":"","description":"","filename":"d56f4f7552d04b339204f1c3b70b13d01structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/0bc65140e54e0f6d19eb20f6.xml"},{"id":95517811,"identity":"6c6a8390-7dfe-42af-a70e-77d83713d452","added_by":"auto","created_at":"2025-11-10 08:48:09","extension":"html","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":117326,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1/d5919fda983e57e7eb829ccc.html"},{"id":95653995,"identity":"a05d41af-1f3f-49b2-8e2e-1920aa1eda08","added_by":"auto","created_at":"2025-11-11 16:07:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2221592,"visible":true,"origin":"","legend":"","description":"","filename":"ADecompositionDrivenHybridFrameworkBasedonSTLforAccurateTrafficFlowForecasting2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7941600/v1_covered_9dda59e1-599e-42f2-8c0c-d7a223046e5a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Decomposition-Driven Hybrid Framework Based on STL for Accurate Traffic Flow Forecasting","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":"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":"Traffic flow forecasting, STL decomposition, Hybrid model, LSTM, ARIMA, XGBoost, Intelligent transportation systems","lastPublishedDoi":"10.21203/rs.3.rs-7941600/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7941600/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate traffic flow forecasting is crucial for intelligent transportation systems and urban traffic management. However, existing single-model approaches often struggle to capture the complex, nonlinear, and multi-scale temporal patterns inherent in traffic flow data. This study proposes a novel decomposition-driven hybrid framework that integrates Seasonal-Trend decomposition using Loess (STL) with three complementary predictive models to enhance forecasting accuracy and robustness. The STL method first decomposes the original traffic flow time series into three distinct components: trend, seasonal, and residual. Subsequently, a Long Short-Term Memory (LSTM) network is employed to model the trend component and capture long-range temporal dependencies, an Autoregressive Integrated Moving Average (ARIMA) model is applied to the seasonal component to exploit periodic patterns, and an Extreme Gradient Boosting (XGBoost) algorithm is utilized to predict the residual component and handle nonlinear irregularities. The final forecast is obtained through multiplicative integration of the three sub-model predictions. The proposed framework is validated using 998 traffic flow records collected from a New York City intersection between November and December 2015. Experimental results demonstrate that the LSTM-ARIMA-XGBoost hybrid model significantly outperforms individual baseline models including standalone LSTM, ARIMA, XGBoost, and their variants (xLSTM, sLSTM, mLSTM) across multiple evaluation metrics, including Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and coefficient of determination (R\u0026sup2;). The decomposition strategy effectively isolates different temporal characteristics, enabling each specialized model to focus on its strength domain, thereby improving overall prediction accuracy, interpretability, and stability. This hybrid approach provides a reliable and efficient solution for real-time traffic flow forecasting in urban transportation systems.\u003c/p\u003e","manuscriptTitle":"A Decomposition-Driven Hybrid Framework Based on STL for Accurate Traffic Flow Forecasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-10 08:48:03","doi":"10.21203/rs.3.rs-7941600/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-15T11:49:24+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-10T03:38:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"20682278290078155305899338292024590209","date":"2025-12-09T12:29:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-05T17:38:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"28620207423120778643028348636619240399","date":"2025-11-01T23:03:14+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-30T17:21:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-30T17:19:35+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-10-30T16:41:26+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-10-27T12:50:40+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-10-27T12:48:16+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":"ff0df47c-2284-4d06-a79b-2e729d6e0547","owner":[],"postedDate":"November 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":57682689,"name":"Physical sciences/Engineering"},{"id":57682690,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-02-05T16:39:17+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-10 08:48:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7941600","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7941600","identity":"rs-7941600","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}