An ensemble deep learning approach for air quality estimation in Delhi, India

An ensemble deep learning approach for air quality estimation in Delhi, 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 An ensemble deep learning approach for air quality estimation in Delhi, India Anju S Mohan, Lizy Abraham This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3610320/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 19 Jan, 2024 Read the published version in Earth Science Informatics → Version 1 posted 7 You are reading this latest preprint version Abstract South Asian megacities are significant contributors to the degrading air quality. In highly populated northern India, Delhi is a major hotspot for air pollutants that influence health and climate. Effective mitigation of air pollution is impeded by inadequate estimation which emphasizes the need for cost-effective alternatives. This paper proposes an ensemble model based on transformer and Convolutional Neural Network (CNN) models to estimate air quality from images and weather parameters in Delhi. A Data Efficient Image transformer (DeiT) is fine-tuned with outdoor images, and parallelly dark-channel prior extracted from images are fed to a CNN model. Additionally, a 1-dimensional CNN is trained with meteorological features to improve accuracy. The predictions from these three parallel branches are then fused with ensemble learning to classify images into six Air Quality Index (AQI) classes and estimate the AQI value. To train and validate the proposed model, an image dataset is collected from Delhi, India termed ‘ AirSetDelhi’ and properly labeled with ground-truth AQI values. Experiments conducted on the dataset demonstrate that the proposed model outperforms other deep learning networks in the literature. The model achieved an overall accuracy of 89.28% and a Cohen Kappa score of 0.856 for AQI classification, while it obtained an RMSE of 47.36 and an R 2 value of 0.861 for AQI estimation, demonstrating efficacy in both tasks. As a regional estimation model based on images and weather features, the proposed model offers an alternative feasible approach for air quality estimation. Air pollution estimation Air quality index AQI classification CNN DeiT Ensemble learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 19 Jan, 2024 Read the published version in Earth Science Informatics → Version 1 posted Editorial decision: Revision requested 08 Dec, 2023 Reviews received at journal 29 Nov, 2023 Reviewers agreed at journal 22 Nov, 2023 Reviewers invited by journal 22 Nov, 2023 Editor assigned by journal 22 Nov, 2023 Submission checks completed at journal 21 Nov, 2023 First submitted to journal 14 Nov, 2023 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-3610320","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":251612014,"identity":"1c4aee1d-f57f-4e60-b6ae-b0ce60a22b1f","order_by":0,"name":"Anju S Mohan","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+klEQVRIie3RsWrDMBCA4SsGZ5HxeiaQvIJKIBTih5EJeHKDIXvwFC99gRJoX8FevEbh5uwqeGgIZPZUMHioDG6HgkzGDvoHDRIfxyEAm+1/JobDOREADpf8LuKKnuA95McxrsnvGHP+IbsFbRJu/MNLQ2n3tOPSuTSQ1kaCtYynXhVvsT4X9LpH5NJdIPCbeYwS8fShoihTzwV5GeJSwlLvQkYx1yRoNXlXySexrieTr1HCNUFPk0IlQMztCRuf8qjEeqV3iUoV836X4Ehsi2KEzFQSfbRVGL2p9eWadjs/yPOyaToz0d8h/lw4MHyvsYkcfbbZbDYbfAMTLFnuBOyqJgAAAABJRU5ErkJggg==","orcid":"","institution":"LBS Institute of Technology for Women","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Anju","middleName":"S","lastName":"Mohan","suffix":""},{"id":251612015,"identity":"fd35807c-7b50-45c9-9364-da2dbdede82a","order_by":1,"name":"Lizy Abraham","email":"","orcid":"","institution":"LBS Institute of Technology for Women","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Lizy","middleName":"","lastName":"Abraham","suffix":""}],"badges":[],"createdAt":"2023-11-14 12:44:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3610320/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3610320/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s12145-023-01210-5","type":"published","date":"2024-01-19T15:01:50+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":49978950,"identity":"c5726a2b-936d-425a-a146-ce3e0a4ae79d","added_by":"auto","created_at":"2024-01-22 15:10:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":718219,"visible":true,"origin":"","legend":"","description":"","filename":"ESINmanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3610320/v1_covered_56e095f4-c0fe-461d-9d8c-12e1fbc88e16.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An ensemble deep learning approach for air quality estimation in Delhi, India","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":"earth-science-informatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esin","sideBox":"Learn more about [Earth Science Informatics](http://link.springer.com/journal/12145)","snPcode":"12145","submissionUrl":"https://submission.nature.com/new-submission/12145/3","title":"Earth Science Informatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Air pollution estimation, Air quality index, AQI classification, CNN, DeiT, Ensemble learning","lastPublishedDoi":"10.21203/rs.3.rs-3610320/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3610320/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eSouth Asian megacities are significant contributors to the degrading air quality. In highly populated northern India, Delhi is a major hotspot for air pollutants that influence health and climate. Effective mitigation of air pollution is impeded by inadequate estimation which emphasizes the need for cost-effective alternatives. This paper proposes an ensemble model based on transformer and Convolutional Neural Network (CNN) models to estimate air quality from images and weather parameters in Delhi. A Data Efficient Image transformer (DeiT) is fine-tuned with outdoor images, and parallelly dark-channel prior extracted from images are fed to a CNN model. Additionally, a 1-dimensional CNN is trained with meteorological features to improve accuracy. The predictions from these three parallel branches are then fused with ensemble learning to classify images into six Air Quality Index (AQI) classes and estimate the AQI value. To train and validate the proposed model, an image dataset is collected from Delhi, India termed \u0026lsquo;\u003cem\u003eAirSetDelhi\u0026rsquo;\u003c/em\u003e and properly labeled with ground-truth AQI values. Experiments conducted on the dataset demonstrate that the proposed model outperforms other deep learning networks in the literature. The model achieved an overall accuracy of 89.28% and a Cohen Kappa score of 0.856 for AQI classification, while it obtained an RMSE of 47.36 and an R\u003csup\u003e2\u003c/sup\u003e value of 0.861 for AQI estimation, demonstrating efficacy in both tasks. As a regional estimation model based on images and weather features, the proposed model offers an alternative feasible approach for air quality estimation.\u003c/p\u003e","manuscriptTitle":"An ensemble deep learning approach for air quality estimation in Delhi, India","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-11-22 20:03:10","doi":"10.21203/rs.3.rs-3610320/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2023-12-08T21:05:11+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2023-11-29T10:58:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"11e730ff-71cb-4f61-a508-71428920bdeb","date":"2023-11-23T03:46:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-11-22T17:50:54+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-11-22T17:49:43+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2023-11-21T08:08:49+00:00","index":"","fulltext":""},{"type":"submitted","content":"Earth Science Informatics","date":"2023-11-14T12:42:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"earth-science-informatics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"esin","sideBox":"Learn more about [Earth Science Informatics](http://link.springer.com/journal/12145)","snPcode":"12145","submissionUrl":"https://submission.nature.com/new-submission/12145/3","title":"Earth Science Informatics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"770452de-6ba6-49ee-bb26-7bd0e96e733d","owner":[],"postedDate":"November 22nd, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-01-22T15:07:30+00:00","versionOfRecord":{"articleIdentity":"rs-3610320","link":"https://doi.org/10.1007/s12145-023-01210-5","journal":{"identity":"earth-science-informatics","isVorOnly":false,"title":"Earth Science Informatics"},"publishedOn":"2024-01-19 15:01:50","publishedOnDateReadable":"January 19th, 2024"},"versionCreatedAt":"2023-11-22 20:03:10","video":"","vorDoi":"10.1007/s12145-023-01210-5","vorDoiUrl":"https://doi.org/10.1007/s12145-023-01210-5","workflowStages":[]},"version":"v1","identity":"rs-3610320","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3610320","identity":"rs-3610320","version":["v1"]},"buildId":"rHA-KDH7Qsr4HCuvH75dn","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}