Machine Learning Approaches for Predicting Air Pollution Levels: A Transparent, Time-Aware Pipeline for Daily AQI in Indian Cities

Machine Learning Approaches for Predicting Air Pollution Levels: A Transparent, Time-Aware Pipeline for Daily AQI in Indian Cities | 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 Machine Learning Approaches for Predicting Air Pollution Levels: A Transparent, Time-Aware Pipeline for Daily AQI in Indian Cities Philipp Goetzinger, Sebastian Noy This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7730670/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 21 Feb, 2026 Read the published version in Modeling Earth Systems and Environment → Version 1 posted 9 You are reading this latest preprint version Abstract Accurate city-scale forecasts of the Air Quality Index (AQI) are essential for exposure advisories and short-term mitigation.We present a transparent, leakage-aware machine-learning pipeline for daily AQI prediction across Indian cities usingpublicly available regulatory measurements. The workflow standardizes types, de-duplicates City×Date records, andapplies within-city interpolation followed by median filling; it then constructs calendar variables, PM2.5/PM10 interactionfeatures, and city-specific time-aware history (lags at t−1,t−3,t−7; rolling mean/standard deviation over 3/7/14 dayscomputed on shifted series to prevent leakage). Under a strictly chronological split (last 20% of dates as a forward hold-out),we compare Linear Regression, Ridge, Random Forest, and Histogram-based Gradient Boosting using MAE, RMSE,R2, and MAPE. Random Forest attains the best test performance (MAE = 12.7742, RMSE = 24.8427, R2 = 0.9320,MAPE = 11.3123%). Feature importance indicates short-memory persistence (AQIt−1) as the dominant driver, withco-pollutants (CO, PM2.5, PM10) and recent variability providing incremental skill. The pipeline is fully reproducibleand deployment-ready, offering a strong operational baseline that agencies can extend with exogenous drivers (e.g.,meteorology) and to alternative targets (e.g., PM2.5 or hourly horizons). Air quality Air Quality Index (AQI) Machine learning Random Forest Gradient Boosting Time-series features India Environmental forecasting Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 21 Feb, 2026 Read the published version in Modeling Earth Systems and Environment → Version 1 posted Editorial decision: Revision requested 20 Dec, 2025 Reviews received at journal 03 Nov, 2025 Reviews received at journal 13 Oct, 2025 Reviewers agreed at journal 04 Oct, 2025 Reviewers agreed at journal 02 Oct, 2025 Reviewers invited by journal 30 Sep, 2025 Editor assigned by journal 30 Sep, 2025 Submission checks completed at journal 30 Sep, 2025 First submitted to journal 27 Sep, 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-7730670","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":527823453,"identity":"6aaf2bcb-1904-4ab2-ae29-48344ec8186c","order_by":0,"name":"Philipp Goetzinger","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABD0lEQVRIiWNgGAWjYPACCRDB+ADMZj4AZDYQ0HAAooXZgIEBiNgSiNICBmwSRGkx51988PGHPxZ58u69z6oLKv4w8LOxP37BuOMeTi2WM54lGxzgkSg2PHPc7PaMMwYMkm0MaRaMZ4pxajG4ccZM4oCEROLGGWlst3nbDBgM7jccM2BsS8CnxfzHAQOglvnP2Ip5/xkw2B9jbMOv5XyPGcOBBInE+RJsbMy8DUBb2JiZH+DTYjmDLVnizAGJxA08aczSPMeMeSSOsbExJOLRYs5/+OCHij91ifPbjzF+5qmRk+NvY3/84SM+h0lA5QwOQGgeBlAE4dYAVMkPVSrfgBBk/oBHxygYBaNgFIw8AABxAFM/4ZvGlAAAAABJRU5ErkJggg==","orcid":"","institution":"University of Zagreb","correspondingAuthor":true,"prefix":"","firstName":"Philipp","middleName":"","lastName":"Goetzinger","suffix":""},{"id":527823454,"identity":"fe9ec980-b7b6-4b16-8182-b5220f37897d","order_by":1,"name":"Sebastian Noy","email":"","orcid":"","institution":"Fontys University of Applied Sciences","correspondingAuthor":false,"prefix":"","firstName":"Sebastian","middleName":"","lastName":"Noy","suffix":""}],"badges":[],"createdAt":"2025-09-27 22:53:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7730670/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7730670/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s40808-026-02741-8","type":"published","date":"2026-02-21T15:57:39+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":93420174,"identity":"6c7d4707-9099-41e5-a091-766ddd39b50f","added_by":"auto","created_at":"2025-10-13 16:09:43","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4554,"visible":true,"origin":"","legend":"","description":"","filename":"f5e5f6686e654502a09a9d8dcebebff7.json","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/578a4b17c8e04ff538c4e59b.json"},{"id":93420083,"identity":"5fca3283-8871-46c8-970a-25103da13de3","added_by":"auto","created_at":"2025-10-13 16:09:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1068189,"visible":true,"origin":"","legend":"","description":"","filename":"Paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/e2d95406d2c7165bec53f5e2.pdf"},{"id":93420236,"identity":"2bdf279c-e9b3-4bd4-8f85-5db6eb8d530b","added_by":"auto","created_at":"2025-10-13 16:09:47","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":61581,"visible":true,"origin":"","legend":"","description":"","filename":"besttreetop20featureimportance.png","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/dd9640ceb3d4d5317738a5fd.png"},{"id":93420177,"identity":"27f9316a-93aa-4948-a7c4-3dbeda7486a3","added_by":"auto","created_at":"2025-10-13 16:09:43","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":190260,"visible":true,"origin":"","legend":"","description":"","filename":"compareabserroroverlay.png","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/f11fcaae5dfa463ca217d408.png"},{"id":93420089,"identity":"d660530f-a330-4248-8dda-ead9008eda21","added_by":"auto","created_at":"2025-10-13 16:09:35","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":79537,"visible":true,"origin":"","legend":"","description":"","filename":"comparermsebar.png","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/68638e8f2c802fb55d38c675.png"},{"id":93420123,"identity":"6257017d-978d-4d8e-927e-cc8f27ee7a32","added_by":"auto","created_at":"2025-10-13 16:09:40","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":227408,"visible":true,"origin":"","legend":"","description":"","filename":"comparetimeseriesoverlay.png","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/7696613104fc981a9bac9f7e.png"},{"id":93420344,"identity":"5984fd68-04de-4929-a704-35fc2aabe725","added_by":"auto","created_at":"2025-10-13 16:09:53","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49197,"visible":true,"origin":"","legend":"","description":"","filename":"residualhistRandomForest.png","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/9336e2e1dbef19cef428abca.png"},{"id":93420121,"identity":"1058f2c9-c205-41dc-9191-cc288ee38169","added_by":"auto","created_at":"2025-10-13 16:09:40","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":75457,"visible":true,"origin":"","legend":"","description":"","filename":"scatterpredvsactualRandomForest.png","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/2e61d2d4e43500300b74e1eb.png"},{"id":93420132,"identity":"29cdc179-3548-4e07-851c-697e9de9be18","added_by":"auto","created_at":"2025-10-13 16:09:41","extension":"xml","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":59195,"visible":true,"origin":"","legend":"","description":"","filename":"f5e5f6686e654502a09a9d8dcebebff71structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1/a30c41c649e0d033ca494a7c.xml"},{"id":103251271,"identity":"75c2cc4f-3c27-470e-ad5b-cbc20f1bc893","added_by":"auto","created_at":"2026-02-23 16:07:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1054827,"visible":true,"origin":"","legend":"","description":"","filename":"Paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7730670/v1_covered_157f350f-b8db-4dd4-b3d6-9269433823df.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine Learning Approaches for Predicting Air Pollution Levels: A Transparent, Time-Aware Pipeline for Daily AQI in Indian Cities","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":"modeling-earth-systems-and-environment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mese","sideBox":"Learn more about [Modeling Earth Systems and Environment](http://link.springer.com/journal/40808)","snPcode":"40808","submissionUrl":"https://submission.springernature.com/new-submission/40808/3","title":"Modeling Earth Systems and Environment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Air quality, Air Quality Index (AQI), Machine learning, Random Forest, Gradient Boosting, Time-series features, India, Environmental forecasting","lastPublishedDoi":"10.21203/rs.3.rs-7730670/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7730670/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Accurate city-scale forecasts of the Air Quality Index (AQI) are essential for exposure advisories and short-term mitigation.We present a transparent, leakage-aware machine-learning pipeline for daily AQI prediction across Indian cities usingpublicly available regulatory measurements. The workflow standardizes types, de-duplicates City×Date records, andapplies within-city interpolation followed by median filling; it then constructs calendar variables, PM2.5/PM10 interactionfeatures, and city-specific time-aware history (lags at t−1,t−3,t−7; rolling mean/standard deviation over 3/7/14 dayscomputed on shifted series to prevent leakage). Under a strictly chronological split (last 20% of dates as a forward hold-out),we compare Linear Regression, Ridge, Random Forest, and Histogram-based Gradient Boosting using MAE, RMSE,R2, and MAPE. Random Forest attains the best test performance (MAE = 12.7742, RMSE = 24.8427, R2 = 0.9320,MAPE = 11.3123%). Feature importance indicates short-memory persistence (AQIt−1) as the dominant driver, withco-pollutants (CO, PM2.5, PM10) and recent variability providing incremental skill. The pipeline is fully reproducibleand deployment-ready, offering a strong operational baseline that agencies can extend with exogenous drivers (e.g.,meteorology) and to alternative targets (e.g., PM2.5 or hourly horizons).","manuscriptTitle":"Machine Learning Approaches for Predicting Air Pollution Levels: A Transparent, Time-Aware Pipeline for Daily AQI in Indian Cities","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-13 16:03:58","doi":"10.21203/rs.3.rs-7730670/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-20T18:33:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-03T16:17:32+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-13T10:55:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"89821070149464972582290801821271450591","date":"2025-10-04T10:36:53+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"161230849663472751934958872331061739231","date":"2025-10-02T18:09:14+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-30T17:48:43+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-30T06:18:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-30T06:16:33+00:00","index":"","fulltext":""},{"type":"submitted","content":"Modeling Earth Systems and Environment","date":"2025-09-27T22:43:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"modeling-earth-systems-and-environment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mese","sideBox":"Learn more about [Modeling Earth Systems and Environment](http://link.springer.com/journal/40808)","snPcode":"40808","submissionUrl":"https://submission.springernature.com/new-submission/40808/3","title":"Modeling Earth Systems and Environment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"2c61b174-bb7d-4571-846d-13547d066c87","owner":[],"postedDate":"October 13th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-02-23T16:03:55+00:00","versionOfRecord":{"articleIdentity":"rs-7730670","link":"https://doi.org/10.1007/s40808-026-02741-8","journal":{"identity":"modeling-earth-systems-and-environment","isVorOnly":false,"title":"Modeling Earth Systems and Environment"},"publishedOn":"2026-02-21 15:57:39","publishedOnDateReadable":"February 21st, 2026"},"versionCreatedAt":"2025-10-13 16:03:58","video":"","vorDoi":"10.1007/s40808-026-02741-8","vorDoiUrl":"https://doi.org/10.1007/s40808-026-02741-8","workflowStages":[]},"version":"v1","identity":"rs-7730670","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7730670","identity":"rs-7730670","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}