Bridging Sparse Air-Quality Monitoring: Machine-Learning Sharpens Daily PM2.5 in 12 Cities Across Two Regions

Bridging Sparse Air-Quality Monitoring: Machine-Learning Sharpens Daily PM2.5 in 12 Cities Across Two Regions | 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 Bridging Sparse Air-Quality Monitoring: Machine-Learning Sharpens Daily PM 2.5 in 12 Cities Across Two Regions Negin Rezaei Nokandeh, Parisa A. Ariya This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8690244/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 12 You are reading this latest preprint version Abstract Airborne particles smaller than 2.5 µm (PM 2.5 ) pose significant risks to human health and influence the climate. However, the accuracy of ground- and satellite-based estimates varies widely across regions. To evaluate the potential of machine learning (ML) to improve ground PM 2.5 concentration measurements, we analyzed ground-level PM 2.5 concentrations in 12 cities across the Greater Middle East (GME) and Canada. We deployed three ML models to enhance daily PM 2.5 estimations, using nearly a decade of combined ground-based observations and MODIS-MAIAC aerosol optical depth (AOD), along with a uniform predictor set comprising AOD and meteorological variables. To ensure comparability, each city was anchored to a single regulatory monitor in both Canada and the GME. Using ten-fold cross-validation, ML improved the AOD–PM 2.5 correlation from approximately 0.15 to a mean R of 0.59 in Canada and ~0.48 in the GME. A pooled regional model integrating all GME observations achieved high out-of-sample agreement (r ≈ 0.90), compared to an AOD-only fit (r ≈ 0.11). SHAP diagnostics revealed that PM 2.5 history (lags and rolling means), AOD, its interaction with physical processes (e.g., temperature and pressure), and boundary-layer height were the dominant drivers in the GME, with more stable influences observed in Canada. PM 2.5 levels in Canada rarely exceeded the WHO guideline, whereas exceedances were frequent across all GME cities. These findings demonstrate that ML, particularly when incorporating temporal context and regional pooling, can significantly enhance PM 2.5 inference in data-scarce environments. Nonetheless, we emphasize the ongoing need for denser ground monitoring to support high-resolution mapping. AOD Ground PM2.5 analysis Machine learning Dust Middle East Canada Full Text Additional Declarations No competing interests reported. Supplementary Files SupplementaryEnvirementalMonitorongandAssesmentNRNPAAJan24.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 20 Apr, 2026 Reviews received at journal 05 Apr, 2026 Reviews received at journal 01 Apr, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers agreed at journal 20 Mar, 2026 Reviewers agreed at journal 18 Mar, 2026 Reviews received at journal 18 Mar, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers invited by journal 17 Feb, 2026 Editor assigned by journal 10 Feb, 2026 Submission checks completed at journal 10 Feb, 2026 First submitted to journal 25 Jan, 2026 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-8690244","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":593584201,"identity":"0ce875ec-7848-4f9b-a28f-212ee1037f71","order_by":0,"name":"Negin Rezaei Nokandeh","email":"","orcid":"","institution":"McGill University","correspondingAuthor":false,"prefix":"","firstName":"Negin","middleName":"Rezaei","lastName":"Nokandeh","suffix":""},{"id":593584204,"identity":"9a70ed12-7da9-403e-9bb5-0592539f7f72","order_by":1,"name":"Parisa A. Ariya","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYJCCA2CSGYg/ADEbO3MD8VoYZ4C0MDMS1gIHzDxgkoAWc/azDw/+qGGQN2/nMfxsm2Nn1wfSAhTBCSx70g0O8xxjMJxzmMdYOndbcnIbUAtjzzHcWgwOpDEcZmADeoOZxwCo5UAyyC/MQBHcWs4/Yzj44x+DPVCL8W9LuJZ/eLTcSGM4wNvGkAjUYibNuO2AHVgLYxsev8x4xnCYt08ieQYzW5ll77bkBJCWg719uLWY86cxf/zxzcZ2Bv/hzTd+brOzl29vPvjgxzc8DoNQEkDMAWYnNjDAIhe/FhBgfwAi7fGpHgWjYBSMgpEJACW3SXXR4lX9AAAAAElFTkSuQmCC","orcid":"","institution":"McGill University","correspondingAuthor":true,"prefix":"","firstName":"Parisa","middleName":"A.","lastName":"Ariya","suffix":""}],"badges":[],"createdAt":"2026-01-25 05:08:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8690244/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8690244/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105903691,"identity":"bf8db0d2-a683-40bd-999e-0ee875731039","added_by":"auto","created_at":"2026-04-01 09:48:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1000110,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptEnvirementalMonitorongandAssesmentNRNPAAJan31.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8690244/v1_covered_3b4884cb-a216-4f7a-8ee9-bfde8aa6e4cc.pdf"},{"id":103241987,"identity":"294d360e-8057-42c6-99e7-a36c9db2f31f","added_by":"auto","created_at":"2026-02-23 14:21:04","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":5473123,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryEnvirementalMonitorongandAssesmentNRNPAAJan24.docx","url":"https://assets-eu.researchsquare.com/files/rs-8690244/v1/4c1e6d72dcd0e6c1035d1964.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eBridging Sparse Air-Quality Monitoring: Machine-Learning Sharpens Daily PM\u003csub\u003e2.5\u003c/sub\u003e in 12 Cities Across Two Regions\u003c/p\u003e","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":"environmental-monitoring-and-assessment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"emas","sideBox":"Learn more about [Environmental Monitoring and Assessment](http://link.springer.com/journal/10661)","snPcode":"10661","submissionUrl":"https://submission.nature.com/new-submission/10661/3","title":"Environmental Monitoring and Assessment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"AOD, Ground PM2.5 analysis, Machine learning, Dust, Middle East, Canada","lastPublishedDoi":"10.21203/rs.3.rs-8690244/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8690244/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAirborne particles smaller than 2.5 µm (PM\u003csub\u003e2.5\u003c/sub\u003e) pose significant risks to human health and influence the climate. However, the accuracy of ground- and satellite-based estimates varies widely across regions.\u003cbr\u003e\nTo evaluate the potential of machine learning (ML) to improve ground PM\u003csub\u003e2.5\u003c/sub\u003e concentration measurements, we analyzed ground-level PM\u003csub\u003e2.5\u003c/sub\u003e concentrations in 12 cities across the Greater Middle East (GME) and Canada. We deployed three ML models to enhance daily PM\u003csub\u003e2.5\u003c/sub\u003e estimations, using nearly a decade of combined ground-based observations and MODIS-MAIAC aerosol optical depth (AOD), along with a uniform predictor set comprising AOD and meteorological variables. To ensure comparability, each city was anchored to a single regulatory monitor in both Canada and the GME. Using ten-fold cross-validation, ML improved the AOD–PM\u003csub\u003e2.5\u003c/sub\u003e correlation from approximately 0.15 to a mean R of 0.59 in Canada and ~0.48 in the GME. A pooled regional model integrating all GME observations achieved high out-of-sample agreement (r ≈ 0.90), compared to an AOD-only fit (r ≈ 0.11). SHAP diagnostics revealed that PM\u003csub\u003e2.5\u003c/sub\u003e history (lags and rolling means), AOD, its interaction with physical processes (e.g., temperature and pressure), and boundary-layer height were the dominant drivers in the GME, with more stable influences observed in Canada. PM\u003csub\u003e2.5\u003c/sub\u003e levels in Canada rarely exceeded the WHO guideline, whereas exceedances were frequent across all GME cities. These findings demonstrate that ML, particularly when incorporating temporal context and regional pooling, can significantly enhance PM\u003csub\u003e2.5\u003c/sub\u003e inference in data-scarce environments. Nonetheless, we emphasize the ongoing need for denser ground monitoring to support high-resolution mapping.\u003c/p\u003e","manuscriptTitle":"Bridging Sparse Air-Quality Monitoring: Machine-Learning Sharpens Daily PM2.5 in 12 Cities Across Two Regions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-23 14:20:58","doi":"10.21203/rs.3.rs-8690244/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-20T13:07:51+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-06T03:14:01+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-01T06:49:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"119645027737198631879620844513938893329","date":"2026-03-21T02:03:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"139163687761975955541989359701160545300","date":"2026-03-20T12:45:33+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"293033463834117545690053997726915488233","date":"2026-03-18T13:57:54+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-18T06:36:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"206577495019100104446332083632854389693","date":"2026-03-17T08:58:36+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-17T12:59:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-11T04:41:10+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-02-11T04:37:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Environmental Monitoring and Assessment","date":"2026-01-25T05:00:05+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"environmental-monitoring-and-assessment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"emas","sideBox":"Learn more about [Environmental Monitoring and Assessment](http://link.springer.com/journal/10661)","snPcode":"10661","submissionUrl":"https://submission.nature.com/new-submission/10661/3","title":"Environmental Monitoring and Assessment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"ac31e397-5363-4b81-beb5-bd5ca82f0f9a","owner":[],"postedDate":"February 23rd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-07T12:53:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-23 14:20:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8690244","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8690244","identity":"rs-8690244","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}