PM 2.5 Concentration 7-days Prediction in the Beijing-Tianjin-Hebei Region Using a Novel Stacking Framework

PM 2.5 Concentration 7-days Prediction in the Beijing-Tianjin-Hebei Region Using a Novel Stacking Framework | 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 PM 2.5 Concentration 7-days Prediction in the Beijing-Tianjin-Hebei Region Using a Novel Stacking Framework Xintong Gao, Xiaohong Wang, Fuping Li, Wenhao Jiang, Meng Zhe, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6007740/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 01 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted 12 You are reading this latest preprint version Abstract High-precision prediction of near-surface PM 2.5 concentration is an significant theoretical prerequisite for effective monitoring and prevention of air pollution, and also provides guiding suggestions for PM 2.5 health risk prevention and control. In view of the fact that the control variables of existing PM 2.5 prediction models are mostly dependent on the influencing factors at the near-surface, and it is often difficult to fully explore the continuous spatio-temporal characteristics in PM 2.5 . In this study, MODIS remote sensing-derived Aerosol Optical Depth (AOD) daily data, atmospheric environment ground monitoring station data and meteorological factors are introduced to identify strong correlation factors. A highly robust seven-day prediction model for PM 2.5 concentration is constructed based on the Stacking algorithm combined with various machine learning methods to improve the generalisation ability of the model; the estimation ability of the integrated model is compared and analyzed with LSTM, RF and KNN models. The results demonstrated that the PM 2.5 prediction results on the basis of this integrated RF-LSTM-Stacking model exhibited a better fit, with R², RMSE, and MAE values of 0.95, 7.74 µg/m³, and 6.08 µg/m³, respectively. This approach improved the prediction accuracy by approximately 17% compared to a single machine learning model. Based on this study, it was evident that the LSTM-RF model, integrated with the fusion-based Stacking algorithm, significantly enhanced the PM 2.5 prediction accuracy and provided an effective reference for PM 2.5 predicting and early warning monitoring. Earth and environmental sciences/Environmental sciences Earth and environmental sciences/Environmental social sciences PM2.5 concentration prediction Long short-term memory neural networks Random forest stacking Beijing-Tianjin-Hebei region Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 01 Jul, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 24 Apr, 2025 Reviews received at journal 22 Apr, 2025 Reviewers agreed at journal 17 Apr, 2025 Reviewers agreed at journal 16 Apr, 2025 Reviews received at journal 02 Mar, 2025 Reviewers agreed at journal 20 Feb, 2025 Reviewers agreed at journal 20 Feb, 2025 Reviewers invited by journal 20 Feb, 2025 Editor assigned by journal 20 Feb, 2025 Editor invited by journal 14 Feb, 2025 Submission checks completed at journal 13 Feb, 2025 First submitted to journal 11 Feb, 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-6007740","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":415709534,"identity":"01647d58-5119-4e78-9e4d-61532f3dfb0a","order_by":0,"name":"Xintong Gao","email":"","orcid":"","institution":"North China University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xintong","middleName":"","lastName":"Gao","suffix":""},{"id":415709535,"identity":"b67cae28-335b-4b9b-b742-02bc947dd028","order_by":1,"name":"Xiaohong Wang","email":"","orcid":"","institution":"North China University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xiaohong","middleName":"","lastName":"Wang","suffix":""},{"id":415709536,"identity":"32f08415-dc68-4ca9-a6e8-354f38e7e0f2","order_by":2,"name":"Fuping Li","email":"","orcid":"","institution":"North China University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Fuping","middleName":"","lastName":"Li","suffix":""},{"id":415709537,"identity":"1c8f9c6e-5521-4598-b67c-6f23a6809b82","order_by":3,"name":"Wenhao Jiang","email":"","orcid":"","institution":"Hebei Vocational College of Rail Transportation","correspondingAuthor":false,"prefix":"","firstName":"Wenhao","middleName":"","lastName":"Jiang","suffix":""},{"id":415709538,"identity":"e4e5e77a-c633-4eda-ae20-b35ed2d6fd34","order_by":4,"name":"Meng Zhe","email":"","orcid":"","institution":"Tianjin Normal University","correspondingAuthor":false,"prefix":"","firstName":"Meng","middleName":"","lastName":"Zhe","suffix":""},{"id":415709539,"identity":"f7f5daa3-ec83-46df-bf18-3cd427708cb2","order_by":5,"name":"Jiaxing Sun","email":"","orcid":"","institution":"Shandong Province Pengbo Safety and Environmental Protection Service Co","correspondingAuthor":false,"prefix":"","firstName":"Jiaxing","middleName":"","lastName":"Sun","suffix":""},{"id":415709540,"identity":"5117a408-7d6b-4e5b-99bf-c0445e2ef926","order_by":6,"name":"Ao Zhang","email":"","orcid":"","institution":"North China University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Ao","middleName":"","lastName":"Zhang","suffix":""},{"id":415709541,"identity":"62f07849-20d6-4221-9606-adf4a469735b","order_by":7,"name":"Linlin Jiao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYBACxmYg8cCAQYaNgbHxwYcKGx5+/gYitCQYMPCwMTA3G844kyYjOeMAEVYlMDDwMDCwt0nzth22MWhIwK+auZ354YOEgjs8fNKNbZIzzpznMWA4wPjhYw4+h7EZGyQYPONhkznYbPGh4jaPOXMDs+TMbXj9YiaRYHCYh00isfHmjDO3eSwbDrAx8+LVwv4NpqUB6JdzPAYHEghp4YHb0gTUcoAoLcUGUC2gQE7mkZxxsBmvXwz7j2988OHPYTn5GekPgVFpZ8/P33zww0d8Whqw2IxFDAnI45UdBaNgFIyCUQACAIWOUY8asOktAAAAAElFTkSuQmCC","orcid":"","institution":"North China University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Linlin","middleName":"","lastName":"Jiao","suffix":""}],"badges":[],"createdAt":"2025-02-11 13:23:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6007740/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6007740/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-07719-7","type":"published","date":"2025-07-01T15:57:10+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":86179830,"identity":"ee24f8a3-086a-4b70-9c19-0fb6d082972c","added_by":"auto","created_at":"2025-07-07 16:19:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":746125,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6007740/v1_covered_d71a9e63-af3a-4d9a-8618-3343909c1dbb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"PM 2.5 Concentration 7-days Prediction in the Beijing-Tianjin-Hebei Region Using a Novel Stacking Framework","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"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":"PM2.5 concentration prediction, Long short-term memory neural networks, Random forest, stacking, Beijing-Tianjin-Hebei region","lastPublishedDoi":"10.21203/rs.3.rs-6007740/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6007740/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHigh-precision prediction of near-surface PM\u003csub\u003e2.5\u003c/sub\u003e concentration is an significant theoretical prerequisite for effective monitoring and prevention of air pollution, and also provides guiding suggestions for PM\u003csub\u003e2.5\u003c/sub\u003e health risk prevention and control. In view of the fact that the control variables of existing PM\u003csub\u003e2.5\u003c/sub\u003e prediction models are mostly dependent on the influencing factors at the near-surface, and it is often difficult to fully explore the continuous spatio-temporal characteristics in PM\u003csub\u003e2.5\u003c/sub\u003e. In this study, MODIS remote sensing-derived Aerosol Optical Depth (AOD) daily data, atmospheric environment ground monitoring station data and meteorological factors are introduced to identify strong correlation factors. A highly robust seven-day prediction model for PM\u003csub\u003e2.5\u003c/sub\u003e concentration is constructed based on the Stacking algorithm combined with various machine learning methods to improve the generalisation ability of the model; the estimation ability of the integrated model is compared and analyzed with LSTM, RF and KNN models. The results demonstrated that the PM\u003csub\u003e2.5\u003c/sub\u003e prediction results on the basis of this integrated RF-LSTM-Stacking model exhibited a better fit, with R\u0026sup2;, RMSE, and MAE values of 0.95, 7.74 \u0026micro;g/m\u0026sup3;, and 6.08 \u0026micro;g/m\u0026sup3;, respectively. This approach improved the prediction accuracy by approximately 17% compared to a single machine learning model. Based on this study, it was evident that the LSTM-RF model, integrated with the fusion-based Stacking algorithm, significantly enhanced the PM\u003csub\u003e2.5\u003c/sub\u003e prediction accuracy and provided an effective reference for PM\u003csub\u003e2.5\u003c/sub\u003e predicting and early warning monitoring.\u003c/p\u003e","manuscriptTitle":"PM 2.5 Concentration 7-days Prediction in the Beijing-Tianjin-Hebei Region Using a Novel Stacking Framework","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-17 17:45:31","doi":"10.21203/rs.3.rs-6007740/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-04-24T07:04:03+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-04-22T10:54:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45946191392098312489244015670487227386","date":"2025-04-17T04:39:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"107002266875232555761921373333855575726","date":"2025-04-17T02:17:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-03-03T03:44:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"203197847677214173133404993844398077909","date":"2025-02-20T16:26:56+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"153812590482492150026345714762958494145","date":"2025-02-20T07:24:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-02-20T06:25:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-02-20T06:23:10+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-02-14T08:26:56+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-02-13T07:42:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-02-11T13:09:29+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":"bf2c0640-e11d-4d4c-adce-37db6227d98a","owner":[],"postedDate":"February 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":44329760,"name":"Earth and environmental sciences/Environmental sciences"},{"id":44329761,"name":"Earth and environmental sciences/Environmental social sciences"}],"tags":[],"updatedAt":"2025-07-07T16:11:11+00:00","versionOfRecord":{"articleIdentity":"rs-6007740","link":"https://doi.org/10.1038/s41598-025-07719-7","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-07-01 15:57:10","publishedOnDateReadable":"July 1st, 2025"},"versionCreatedAt":"2025-02-17 17:45:31","video":"","vorDoi":"10.1038/s41598-025-07719-7","vorDoiUrl":"https://doi.org/10.1038/s41598-025-07719-7","workflowStages":[]},"version":"v1","identity":"rs-6007740","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6007740","identity":"rs-6007740","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}