Comparative Analysis of Machine Learning Models for Multi-Horizon PM2.5 Forecasting

Comparative Analysis of Machine Learning Models for Multi-Horizon PM2.5 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 Research Article Comparative Analysis of Machine Learning Models for Multi-Horizon PM2.5 Forecasting Shengqi Shao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8724199/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 particulate matter (PM2.5) concentrations is critical for public health management and environmental policy-making. This study presents a comprehensive comparison of six machine learning models—Linear Regression, Support Vector Regression (SVR), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Multi-Layer Perceptron (MLP), and Long Short-Term Memory (LSTM)—for multi-horizon PM2.5 prediction. Using hourly air quality data from 11 cities in Zhejiang Province, China (January-February 2024), we evaluate model performance across three forecast horizons: 1-hour, 6-hour, and 24-hour ahead predictions. Our results demonstrate that model performance varies significantly with forecast horizon. For short-term (1-hour) predictions, Linear Regression achieves the best performance (RMSE=10.682, R²=0.901), suggesting near-linear temporal dynamics. For longer horizons (24-hour), ensemble tree-based models outperform others, with GBDT achieving RMSE=24.264 and R²=0.467. Surprisingly, deep learning approaches (LSTM) underperform traditional machine learning methods, particularly for long-term forecasting. Feature importance analysis reveals that the most recent PM2.5 value (lag-1) accounts for 47.8% of predictive power, while Air Quality Index contributes 42.3%, highlighting the dominance of temporal autocorrelation in PM2.5 dynamics. Artificial Intelligence and Machine Learning PM2.5 forecasting air quality prediction machine learning comparison time series analysis LSTM gradient boosting 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-8724199","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":581985631,"identity":"ce52c13d-a55b-48be-8d39-1b8debeb36a9","order_by":0,"name":"Shengqi Shao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/klEQVRIie3QMWsCMRTA8XcE4vIk6zso7Vd44FJQuK8SEeri4OgoFOzi4erglxBBOkYC7XIfQOhiF6cOV5yc2pd26nDnjQXzn0LIj+QFIBb7h5k775zlHmqlHNA47Nl6ki5135WThxvT0haIGxDeY2e3LHwvXaCcb0Lgbcq+PVPIHj/Le/ZgWiOG83O1SFbOCtFC2hsiIen8g5O8qCYKrBOCgWwhEN6PWCWzaqKhPxVC4WHHH5JdIkgDkPEZ00fUv7fQBUL4AvLJFo3SHZlliFQcx7u8hmSvi1Np+SvTxr+faNK9NU+D9eFcQ/6kSF4aFq4hkB8vGx+NxWKxa+obdWlOurvWa5YAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0009-6546-378X","institution":"China Jiliang University","correspondingAuthor":true,"prefix":"","firstName":"Shengqi","middleName":"","lastName":"Shao","suffix":""}],"badges":[],"createdAt":"2026-01-28 17:54:36","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-8724199/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8724199/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101398829,"identity":"9724564b-7423-4079-9b72-7473ebbee24b","added_by":"auto","created_at":"2026-01-29 09:48:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1858583,"visible":true,"origin":"","legend":"","description":"","filename":"output.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8724199/v1_covered_53f1bafd-1c08-4f1a-a3c9-5cbfd7373062.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eComparative Analysis of Machine Learning Models for Multi-Horizon PM2.5 Forecasting\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"China Jiliang University","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":"PM2.5 forecasting, air quality prediction, machine learning comparison, time series analysis, LSTM, gradient boosting","lastPublishedDoi":"10.21203/rs.3.rs-8724199/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8724199/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate forecasting of particulate matter (PM2.5) concentrations is critical for public health management and environmental policy-making. This study presents a comprehensive comparison of six machine learning models—Linear Regression, Support Vector Regression (SVR), Random Forest (RF), Gradient Boosting Decision Trees (GBDT), Multi-Layer Perceptron (MLP), and Long Short-Term Memory (LSTM)—for multi-horizon PM2.5 prediction. Using hourly air quality data from 11 cities in Zhejiang Province, China (January-February 2024), we evaluate model performance across three forecast horizons: 1-hour, 6-hour, and 24-hour ahead predictions.\u003c/p\u003e\n\u003cp\u003eOur results demonstrate that model performance varies significantly with forecast horizon. For short-term (1-hour) predictions, Linear Regression achieves the best performance (RMSE=10.682, R²=0.901), suggesting near-linear temporal dynamics. For longer horizons (24-hour), ensemble tree-based models outperform others, with GBDT achieving RMSE=24.264 and R²=0.467. Surprisingly, deep learning approaches (LSTM) underperform traditional machine learning methods, particularly for long-term forecasting. Feature importance analysis reveals that the most recent PM2.5 value (lag-1) accounts for 47.8% of predictive power, while Air Quality Index contributes 42.3%, highlighting the dominance of temporal autocorrelation in PM2.5 dynamics.\u003c/p\u003e","manuscriptTitle":"Comparative Analysis of Machine Learning Models for Multi-Horizon PM2.5 Forecasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-29 09:02:59","doi":"10.21203/rs.3.rs-8724199/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":"0aa11653-945d-4657-bacc-47e46bc667df","owner":[],"postedDate":"January 29th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":61920347,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2026-01-29T09:02:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-29 09:02:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8724199","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8724199","identity":"rs-8724199","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}