Impact of Urbanization on Air Quality in Delhi: A Multi-Source Remote Sensing and Machine Learning Approach

Impact of Urbanization on Air Quality in Delhi: A Multi-Source Remote Sensing and Machine Learning Approach | 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 Impact of Urbanization on Air Quality in Delhi: A Multi-Source Remote Sensing and Machine Learning Approach Nusrat Hasani, Faiyaz Ahamad This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9666261/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 Delhi is experiencing chronic air quality deterioration driven by rapid urbanization. This study investigates the urbanization–air quality relationship using an integrated pipeline of multi-source satellite data and machine learning. Monthly measurements from 9 CPCB stations (2018–2025, 853 station-months, 27 features) were combined with TROPOMI atmospheric composition, MODIS aerosol optical depth, ERA5-Land meteorology, VIIRS nighttime lights, Sentinel-2 spectral indices, and a multi-product urban consensus map. XGBoost with autoregressive lagged features (XGBoost+Lag) and a hybrid CNN–LSTM were evaluated via 5-fold cross-validation and walk-forward temporal validation. XGBoost+Lag achieved R² = 0.966 (RMSE = 13.73 μg m⁻³) for PM₂.₅ and R² = 0.934 (RMSE = 27.15 μg m⁻³) for PM₁₀, while CNN-LSTM outperformed it for ozone (R² = 0.674 vs. 0.452). Walk-forward validation confirmed XGBoost+Lag generalizes better across year boundaries (R² = 0.900 for PM₂.₅). Feature importance analysis revealed that seasonality dominates particulate matter prediction (>84% MDI), whereas TROPOMI NO₂ column density, the urban consensus score, and nighttime radiance collectively explain over 50% of importance for NO₂. Partial dependence analysis identified a nonlinear urbanization threshold: predicted PM₂.₅ increases sharply once built-up fraction exceeds 50%. These findings demonstrate that combining multi-product urbanization indices with satellite atmospheric observations enables robust multi-pollutant prediction, providing actionable evidence for urban air quality management in rapidly growing South Asian cities. Particulate matter Gradient boosting Satellite observations Indo-Gangetic Plain Spatiotemporal prediction CPCB monitoring Full Text Additional Declarations No competing interests reported. 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-9666261","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":637489000,"identity":"4b98e755-78ed-4196-8548-323afd5c8e64","order_by":0,"name":"Nusrat Hasani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYDACCQgpx8/eAKQNLIjXYizZcwCkRYJoLQyJG24kIHHxAXPp5scffu6wSGy4+fzqhh8FEgz87d0JeLVYzjlmJtl7RsK4cXZO2c0eoMMkzpzdgFeLwY0EMwbeNgnZZumctBs8QC0GErmEtKR//vi3TYKxTfJM2s0/xGnJMZAG2qLYI8F+7DaRtuSUScu2SRhL8OSw3ZYxkOAhwi/pmz++bauTsz9+/NnNN39s5Pjbe/FrQQI8BmCSWOUgwP6AFNWjYBSMglEwggAAOCJHiDDHn7UAAAAASUVORK5CYII=","orcid":"","institution":"Integral University","correspondingAuthor":true,"prefix":"","firstName":"Nusrat","middleName":"","lastName":"Hasani","suffix":""},{"id":637489004,"identity":"45ecd78c-ff96-483f-894b-1b360ed08c3a","order_by":1,"name":"Faiyaz Ahamad","email":"","orcid":"","institution":"Integral University","correspondingAuthor":false,"prefix":"","firstName":"Faiyaz","middleName":"","lastName":"Ahamad","suffix":""}],"badges":[],"createdAt":"2026-05-09 20:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9666261/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9666261/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109068232,"identity":"aacf7632-30e0-4975-b005-ff7dc16d0bee","added_by":"auto","created_at":"2026-05-12 10:04:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":788291,"visible":true,"origin":"","legend":"","description":"","filename":"ImpactofUrbanizationEMAFormat.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9666261/v1_covered_1e207ef8-6702-4373-bffd-86b830e2ceef.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Impact of Urbanization on Air Quality in Delhi: A Multi-Source Remote Sensing and Machine Learning Approach","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Particulate matter, Gradient boosting, Satellite observations, Indo-Gangetic Plain, Spatiotemporal prediction, CPCB monitoring","lastPublishedDoi":"10.21203/rs.3.rs-9666261/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9666261/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eDelhi is experiencing chronic air quality deterioration driven by rapid urbanization. This study investigates the urbanization–air quality relationship using an integrated pipeline of multi-source satellite data and machine learning. Monthly measurements from 9 CPCB stations (2018–2025, 853 station-months, 27 features) were combined with TROPOMI atmospheric composition, MODIS aerosol optical depth, ERA5-Land meteorology, VIIRS nighttime lights, Sentinel-2 spectral indices, and a multi-product urban consensus map. XGBoost with autoregressive lagged features (XGBoost+Lag) and a hybrid CNN–LSTM were evaluated via 5-fold cross-validation and walk-forward temporal validation. XGBoost+Lag achieved R² = 0.966 (RMSE = 13.73 μg m⁻³) for PM₂.₅ and R² = 0.934 (RMSE = 27.15 μg m⁻³) for PM₁₀, while CNN-LSTM outperformed it for ozone (R² = 0.674 vs. 0.452). Walk-forward validation confirmed XGBoost+Lag generalizes better across year boundaries (R² = 0.900 for PM₂.₅). Feature importance analysis revealed that seasonality dominates particulate matter prediction (\u0026gt;84% MDI), whereas TROPOMI NO₂ column density, the urban consensus score, and nighttime radiance collectively explain over 50% of importance for NO₂. Partial dependence analysis identified a nonlinear urbanization threshold: predicted PM₂.₅ increases sharply once built-up fraction exceeds 50%. These findings demonstrate that combining multi-product urbanization indices with satellite atmospheric observations enables robust multi-pollutant prediction, providing actionable evidence for urban air quality management in rapidly growing South Asian cities.\u003c/p\u003e","manuscriptTitle":"Impact of Urbanization on Air Quality in Delhi: A Multi-Source Remote Sensing and Machine Learning Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-12 08:36:04","doi":"10.21203/rs.3.rs-9666261/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":"6aa1195b-24ef-4b7a-98fe-c57cbaefb230","owner":[],"postedDate":"May 12th, 2026","published":true,"recentEditorialEvents":[{"type":"submitted","content":"Environmental Monitoring and Assessment","date":"2026-05-09T20:23:09+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-12T08:36:04+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-12 08:36:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9666261","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9666261","identity":"rs-9666261","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}