Multiscale Spatio-Temporal Aware Graph Recurrent Neural Network for Traffic Prediction

Multiscale Spatio-Temporal Aware Graph Recurrent Neural Network for Traffic Prediction | 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 Multiscale Spatio-Temporal Aware Graph Recurrent Neural Network for Traffic Prediction Lei Chang, Wenxi Yang, Kaiyuan Qi, Tao Cui, Lianfei Yu, Zhijian Qu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5257185/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 The main problem within most existing traffic prediction methods is that they capture sequence features using a single scale, such as the time continuity or the direct adjacency relationship. It makes the relevant traffic prediction models still insufficient in capturing the dynamic patterns and spatio-temporal correlations. To fully mine the spatio-temporal correlation of traffic sequence, a multiscale spatio-temporal aware graph recurrent neural network (MSSTA-GRN) is proposed in the paper. Firstly, to capture the internal temporal correlation of traffic sequences at different scales, we decompose the hidden states of GRU into different scales and then update the corresponding hidden states according to different frequencies, the speed changes at different frequencies can be better captured. Secondly, to capture the multiscale spatial correlation of the traffic network more comprehensively, a multiscale spatial feature capture module is constructed by cascading multiple GCNs, the multiscale GCN can better deal with the interaction between different regions. Finally, MSSTA-GRN is designed to fuse multiscale spatio-temporal features, and experimental results indicate that the proposed perception method can improve the accuracy and robustness of traffic prediction. Physical sciences/Mathematics and computing/Computational science Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Statistics traffic prediction spatial dependence temporal dependence graph convolutional Full Text Additional Declarations No competing interests reported. Supplementary Files data.zip 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-5257185","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":378848240,"identity":"ef877bf4-4323-43e4-97c2-d9ba36e4ff47","order_by":0,"name":"Lei Chang","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Lei","middleName":"","lastName":"Chang","suffix":""},{"id":378848241,"identity":"e59dfd3b-ba1f-4508-b423-9168f0ce6f6a","order_by":1,"name":"Wenxi Yang","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Wenxi","middleName":"","lastName":"Yang","suffix":""},{"id":378848242,"identity":"ed7fd3d5-39ab-4749-8f8e-bb2372906a64","order_by":2,"name":"Kaiyuan Qi","email":"","orcid":"","institution":"Inspur (Jinan) Data Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Kaiyuan","middleName":"","lastName":"Qi","suffix":""},{"id":378848243,"identity":"b926ede3-1203-475e-8d45-8e14f6d8e3ce","order_by":3,"name":"Tao Cui","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Cui","suffix":""},{"id":378848244,"identity":"94480b08-f755-4ba4-94b8-d9f15016abcd","order_by":4,"name":"Lianfei Yu","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Lianfei","middleName":"","lastName":"Yu","suffix":""},{"id":378848245,"identity":"a3e57036-3835-4d6b-ba68-03c85e79457b","order_by":5,"name":"Zhijian Qu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYDACCcYGgwQQg72BQQIscoBoLTwHgFoSiNICZyQQqUV+dnNDwYOaO7Ibbj5/eJv3B4Mc340Exs8FeLQwzjkIdNixZ8YbbucYW/MkMBhL3khglp6BRwuzRCJQC9vhRKAWNmmglsQNNxLYmHnwaGEDa/kH1HLz+DOQlnqCWnhAWhLbgFpuMJiBtCQYENIiAdbSd9h45pkcY8s5aRKGM888bJbGp0V+Rvozwx/fDsv2HT/+8MYbGxt5vuPJBz/j0wLyjgGQYGyA2orExg2YHxClbBSMglEwCkYuAADVbk/atRPauAAAAABJRU5ErkJggg==","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Zhijian","middleName":"","lastName":"Qu","suffix":""},{"id":378848246,"identity":"fb42814d-cdc8-473b-99b5-3d55b5ec5fc8","order_by":6,"name":"Chongguang Ren","email":"","orcid":"","institution":"Shandong University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Chongguang","middleName":"","lastName":"Ren","suffix":""}],"badges":[],"createdAt":"2024-10-14 01:08:17","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5257185/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5257185/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72798476,"identity":"aa124ebe-579e-42cc-8bd0-577653817afe","added_by":"auto","created_at":"2025-01-02 09:09:47","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1457067,"visible":true,"origin":"","legend":"","description":"","filename":"MultiscaleSpatioTemporalAwareGraphRecurrentNeuralNetworkforTrafficPrediction.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5257185/v1_covered_fd10ba4a-fb43-49e3-bb1a-11a4fc468d97.pdf"},{"id":69214104,"identity":"9596838e-263b-442c-8cfd-a752e5aabf07","added_by":"auto","created_at":"2024-11-18 06:05:09","extension":"zip","order_by":23,"title":"","display":"","copyAsset":false,"role":"supplement","size":3222315,"visible":true,"origin":"","legend":"","description":"","filename":"data.zip","url":"https://assets-eu.researchsquare.com/files/rs-5257185/v1/67b25b0662741963e7c6c37c.zip"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multiscale Spatio-Temporal Aware Graph Recurrent Neural Network for Traffic Prediction","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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":"traffic prediction, spatial dependence, temporal dependence, graph convolutional","lastPublishedDoi":"10.21203/rs.3.rs-5257185/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5257185/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe main problem within most existing traffic prediction methods is that they capture sequence features using a single scale, such as the time continuity or the direct adjacency relationship. It makes the relevant traffic prediction models still insufficient in capturing the dynamic patterns and spatio-temporal correlations. To fully mine the spatio-temporal correlation of traffic sequence, a multiscale spatio-temporal aware graph recurrent neural network (MSSTA-GRN) is proposed in the paper. Firstly, to capture the internal temporal correlation of traffic sequences at different scales, we decompose the hidden states of GRU into different scales and then update the corresponding hidden states according to different frequencies, the speed changes at different frequencies can be better captured. Secondly, to capture the multiscale spatial correlation of the traffic network more comprehensively, a multiscale spatial feature capture module is constructed by cascading multiple GCNs, the multiscale GCN can better deal with the interaction between different regions. Finally, MSSTA-GRN is designed to fuse multiscale spatio-temporal features, and experimental results indicate that the proposed perception method can improve the accuracy and robustness of traffic prediction.\u003c/p\u003e","manuscriptTitle":"Multiscale Spatio-Temporal Aware Graph Recurrent Neural Network for Traffic Prediction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-18 06:05:01","doi":"10.21203/rs.3.rs-5257185/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":"f111899c-4a4c-429f-be30-2cf4c20b73e2","owner":[],"postedDate":"November 18th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":40345925,"name":"Physical sciences/Mathematics and computing/Computational science"},{"id":40345926,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":40345927,"name":"Physical sciences/Mathematics and computing/Statistics"}],"tags":[],"updatedAt":"2025-01-02T09:09:13+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-18 06:05:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5257185","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5257185","identity":"rs-5257185","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}