Suitability of Machine Learning Models and their Performance for PM 2.5 Estimation using high-resolution satellite-driven datasets over Northwest India

Suitability of Machine Learning Models and their Performance for PM 2.5 Estimation using high-resolution satellite-driven datasets over Northwest India | 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 Suitability of Machine Learning Models and their Performance for PM 2.5 Estimation using high-resolution satellite-driven datasets over Northwest India Prity S. Pippal, Rajesh Kumar, Atar Singh, Ramesh Kumar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7959491/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 The estimation of PM 2.5 levels using high-resolution satellite-driven datasets and machine learning algorithms represented a potential advancement in air quality monitoring over Northwest India (NW). The traditional ground-based PM 2.5 measurements, while accurate, suffer from limited spatial coverage, prompting the need for satellite-based retrieval methods. The machine learning (ML) algorithms convert high-resolution satellite-derived Aerosol Optical Depth (AOD) into PM 2.5 , and enhance the accuracy of this conversion. Therefore, this study presented 1km resolution of satellite-driven PM 2.5 estimation framework using Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD and meteorology through ML algorithms over under-covered NW India. This study used XGBoost, random forest (RF), support vector machine (SVM), and AdaBoost ML models to integrating the MAIAC AOD with meteorological variables. The datasets have been pre-processed and optimized for better accuracy from 2022 to 2023 align with ground observations. RF and XGBoost (R² = 0.91 and 0.91, RMSE = 29.34 µg/m³ and 32.19 µg/m³, Bias = 0.30 µg/m³ and 0.48 µg/m³, respectively) outperform AdaBoost and SVM over northwest India. The estimated PM 2.5 values exceed National Ambient Air Quality Standards (NAAQS), with mean 24-hour and annual average concentrations of 74.05 µg/m³ and 70.53 µg/m³, underlining severe air pollution in the region. By leveraging high-resolution satellite data and advanced ML techniques, this study offers a novel and scalable solution for PM 2.5 estimation in data-scarce regions. These fusing approaches provided actionable insights for air quality monitoring and policymaking, enhanced the ability to capture the complexity of PM 2.5 variability, and facilitated predictive models that contribute to efficient air quality management. Aerosols Particulate matter Feature Importance MAIAC Air quality Full Text Additional Declarations No competing interests reported. Supplementary Files Supplementary31.10.2025.docx 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-7959491","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":559136640,"identity":"d7e2dfa5-8b4a-4908-b36c-641f477a5351","order_by":0,"name":"Prity S. Pippal","email":"","orcid":"","institution":"Central University of Rajasthan","correspondingAuthor":false,"prefix":"","firstName":"Prity","middleName":"S.","lastName":"Pippal","suffix":""},{"id":559136646,"identity":"2113d86b-544b-493b-b862-fd262d82b684","order_by":1,"name":"Rajesh Kumar","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABB0lEQVRIiWNgGAWjYHCCBAbGBgYDMPMDmDwAIiSI08I4g0gtDHAtzDzEuMq8/cDDhz93MBgbXDv87LNNzeF8/sYDjB9+MFjk4dIicyYh2Zj3DIOZwe0049k5xw5bzjhwgFmyh0GiGJcWCYaENGnGNgYbg9sJxsy5DYcNGA4cYJAGSiQ24NLC/yD950+wlvTPzJZALfJAW37j1SKRkMbA2wZyWI4xMyNQi8GBA2z4bZF4kCzN2yZhLHk7p5ix51i6geGBg22WPQb4HJaT+PFnm41h3+30zQw/aqwN5G4cPnzjR0UdTi0MDDwJDKgRJ3EQqNgAp3ogYD+AJsCP2/hRMApGwSgYmQAAuVNWn8rouwkAAAAASUVORK5CYII=","orcid":"","institution":"Central University of Rajasthan","correspondingAuthor":true,"prefix":"","firstName":"Rajesh","middleName":"","lastName":"Kumar","suffix":""},{"id":559136648,"identity":"f69dc49a-9a7c-437b-b5fe-1e61b01dd235","order_by":2,"name":"Atar Singh","email":"","orcid":"","institution":"National Institute of Hydrology","correspondingAuthor":false,"prefix":"","firstName":"Atar","middleName":"","lastName":"Singh","suffix":""},{"id":559136655,"identity":"5c0a4969-aeae-4682-a5e6-b2cb9e02bd66","order_by":3,"name":"Ramesh Kumar","email":"","orcid":"","institution":"Marwadi University Research Center, Marwadi University","correspondingAuthor":false,"prefix":"","firstName":"Ramesh","middleName":"","lastName":"Kumar","suffix":""}],"badges":[],"createdAt":"2025-10-27 12:50:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7959491/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7959491/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98214861,"identity":"a763df07-fe5c-4773-8e24-05ce2f28a35f","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2958833,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript31.10.2025.docx","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/392426994da346d0c8928b5f.docx"},{"id":98214852,"identity":"f6b7d0ec-7269-48d1-8a63-91f8ec985bac","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6510,"visible":true,"origin":"","legend":"","description":"","filename":"a14480fa6ab241878bafccebdd6e5c8d.json","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/14d35d215f3682f9221be1a0.json"},{"id":98214853,"identity":"2bd3ecd3-4d4c-46a7-b9ff-e901017d5fa0","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":996370,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary31.10.2025.docx","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/4836c0f810141344f81fa8d6.docx"},{"id":98214856,"identity":"7ffb8035-42e5-41a1-a88f-dde36bd7e8a8","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":198471,"visible":true,"origin":"","legend":"","description":"","filename":"a14480fa6ab241878bafccebdd6e5c8d1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/c9d5813b50a4d75bf40668aa.xml"},{"id":98214857,"identity":"a1549222-3789-4af2-8485-b0927a7f3584","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":970223,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/6c777b00ab330534179e65cd.png"},{"id":98433310,"identity":"a4b8344e-5870-4ca7-a402-793a421688d8","added_by":"auto","created_at":"2025-12-17 16:50:35","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":206029,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/8333d23c9653dc848aada368.png"},{"id":98433627,"identity":"629c8923-e8b0-4422-ab56-32248a6a9589","added_by":"auto","created_at":"2025-12-17 16:50:57","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":271353,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/58f6f009c06d07319ea41778.png"},{"id":98214859,"identity":"3ecfd6d3-fc30-49d9-9eeb-a04593214f54","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":219785,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/7de8b411a9dc7e38551a4f51.png"},{"id":98431753,"identity":"ae1eb4d9-c277-44b6-b8cf-1f37268a71bb","added_by":"auto","created_at":"2025-12-17 16:48:17","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":54814,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/80f6f2402a7e4c713c874d8b.png"},{"id":98214864,"identity":"fa8264a5-7f12-4341-8e07-5394f8f4e0ae","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":172697,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/2cbaa5ee7cfe6fb9db8268f1.png"},{"id":98214883,"identity":"8a0489bd-363b-4945-9088-40c382f9b8b3","added_by":"auto","created_at":"2025-12-15 10:20:39","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":842263,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/acea77c26f789c2a67bde024.png"},{"id":98432383,"identity":"0de9245d-b5f1-4a9e-b3f1-ed9968f6c3f3","added_by":"auto","created_at":"2025-12-17 16:49:29","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109285,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/187ba91a3ab18d98c7c70c30.png"},{"id":98214872,"identity":"52cfeba0-dde6-4b3e-be2d-dca489614bae","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":171694,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/2fbd055637c330892e381e19.png"},{"id":98432402,"identity":"53c32eca-238a-4d49-8f56-037199999e11","added_by":"auto","created_at":"2025-12-17 16:49:31","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":48724,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/cf0518088f3dcf91b5aaa44b.png"},{"id":98433494,"identity":"4738c829-d6da-49b1-8b99-a1ff55d89609","added_by":"auto","created_at":"2025-12-17 16:50:51","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68616,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/c82413b105162b0c1a01eec7.png"},{"id":98432896,"identity":"dfe8fc43-3178-4125-b9eb-5c78b3965b97","added_by":"auto","created_at":"2025-12-17 16:50:05","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":57423,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/f0ed52989d23df34274463bb.png"},{"id":98214866,"identity":"ab630aa2-f589-4c43-b310-4812d12c5299","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15750,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/98c07fbbbf0fbf576ac3fa08.png"},{"id":98214868,"identity":"57a661ac-fc62-46cf-9adf-9c86cbcedfc7","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":51694,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/4cfc1af62ea2fbd4490ba494.png"},{"id":98214865,"identity":"4477d9bc-ae79-4775-bca6-0f8add11881d","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":118097,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/c56e296c1113d45ddbb0d386.png"},{"id":98214869,"identity":"7b8ded1b-75b3-48f9-be5a-6dc0dc8376c7","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24338,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/55fadbd28696e9af5c7ef358.png"},{"id":98214873,"identity":"e581c776-ffe0-4c99-b5ce-8062e366ffa3","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"xml","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":197321,"visible":true,"origin":"","legend":"","description":"","filename":"a14480fa6ab241878bafccebdd6e5c8d1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/5fcdd53c1f0bb3ba0169ef6c.xml"},{"id":98433515,"identity":"d14fda71-8fe8-40ff-83e4-ce161534eed5","added_by":"auto","created_at":"2025-12-17 16:50:51","extension":"html","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":205694,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/251260b95d8149241028ed4b.html"},{"id":98444888,"identity":"75085cc9-cb7a-4ff0-a992-3af84c5a9645","added_by":"auto","created_at":"2025-12-17 17:18:02","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1454476,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript31.10.2025.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1_covered_3a9e63ea-6a0f-4119-a1d3-cc115698125c.pdf"},{"id":98214854,"identity":"6d3f4a76-54b1-41f4-b4d1-9afe9eafbd7c","added_by":"auto","created_at":"2025-12-15 10:19:42","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":996370,"visible":true,"origin":"","legend":"","description":"","filename":"Supplementary31.10.2025.docx","url":"https://assets-eu.researchsquare.com/files/rs-7959491/v1/93350d9a616266044a16b93d.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Suitability of Machine Learning Models and their Performance for PM 2.5 Estimation using high-resolution satellite-driven datasets over Northwest India","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Aerosols, Particulate matter, Feature Importance, MAIAC, Air quality","lastPublishedDoi":"10.21203/rs.3.rs-7959491/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7959491/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe estimation of PM\u003csub\u003e2.5\u003c/sub\u003e levels using high-resolution satellite-driven datasets and machine learning algorithms represented a potential advancement in air quality monitoring over Northwest India (NW). The traditional ground-based PM\u003csub\u003e2.5\u003c/sub\u003e measurements, while accurate, suffer from limited spatial coverage, prompting the need for satellite-based retrieval methods. The machine learning (ML) algorithms convert high-resolution satellite-derived Aerosol Optical Depth (AOD) into PM\u003csub\u003e2.5\u003c/sub\u003e, and enhance the accuracy of this conversion. Therefore, this study presented 1km resolution of satellite-driven PM\u003csub\u003e2.5\u003c/sub\u003e estimation framework using Multi-Angle Implementation of Atmospheric Correction (MAIAC) AOD and meteorology through ML algorithms over under-covered NW India. This study used XGBoost, random forest (RF), support vector machine (SVM), and AdaBoost ML models to integrating the MAIAC AOD with meteorological variables. The datasets have been pre-processed and optimized for better accuracy from 2022 to 2023 align with ground observations. RF and XGBoost (R\u0026sup2; = 0.91 and 0.91, RMSE\u0026thinsp;=\u0026thinsp;29.34 \u0026micro;g/m\u0026sup3; and 32.19 \u0026micro;g/m\u0026sup3;, Bias\u0026thinsp;=\u0026thinsp;0.30 \u0026micro;g/m\u0026sup3; and 0.48 \u0026micro;g/m\u0026sup3;, respectively) outperform AdaBoost and SVM over northwest India. The estimated PM\u003csub\u003e2.5\u003c/sub\u003e values exceed National Ambient Air Quality Standards (NAAQS), with mean 24-hour and annual average concentrations of 74.05 \u0026micro;g/m\u0026sup3; and 70.53 \u0026micro;g/m\u0026sup3;, underlining severe air pollution in the region. By leveraging high-resolution satellite data and advanced ML techniques, this study offers a novel and scalable solution for PM\u003csub\u003e2.5\u003c/sub\u003e estimation in data-scarce regions. These fusing approaches provided actionable insights for air quality monitoring and policymaking, enhanced the ability to capture the complexity of PM\u003csub\u003e2.5\u003c/sub\u003e variability, and facilitated predictive models that contribute to efficient air quality management.\u003c/p\u003e","manuscriptTitle":"Suitability of Machine Learning Models and their Performance for PM 2.5 Estimation using high-resolution satellite-driven datasets over Northwest India","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-15 10:19:37","doi":"10.21203/rs.3.rs-7959491/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":"f5e228f2-dd50-43d3-9da7-6745e1d1721f","owner":[],"postedDate":"December 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-09T12:38:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-15 10:19:37","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7959491","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7959491","identity":"rs-7959491","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}