Deep Learning Approach to predict PM10 pollutant by using other Air Pollutants and Meteorological Factors

Deep Learning Approach to predict PM10 pollutant by using other Air Pollutants and Meteorological Factors | 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 Deep Learning Approach to predict PM10 pollutant by using other Air Pollutants and Meteorological Factors Ishaan Sunita Pandita, Gaurav Bhanot, A.V. Shanmukh Reddy This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3360409/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 6 You are reading this latest preprint version Abstract Particulate matter in particular poses a serious risk to both human health and the environment. For efficient pollution management and the deployment of appropriate mitigation techniques, accurate air quality forecasting is essential. The objective of the proposed work is to forecast the concentration of PM10 (particulate matter with a diameter of 10 micrometres or less) using a variety of air pollutants as predictors, such as PM2.5, NO2, CO, and other pertinent chemical species. Proposed system makes use of a sizable dataset that includes historical measurements of PM10, PM2.5, NO2, CO, and numerous other air contaminants. It is common knowledge that these pollutants are significant sources of air pollution, and metropolitan areas regularly monitor these pollutants' concentrations. The accuracy of PM10 prediction is increased by using numerous air pollutants as predictors because the intricate interactions and synergistic effects among various pollutants can be captured. This study proposes the development of a system, inspired by existing machine learning and deep learning techniques, capable of forecasting the concentration of PM10 in the atmosphere, using data about other pollutants, as mentioned previously, in the air in the region of prediction, along with meteorological factors defining the weather in the region of prediction, including but not limited to relative humidity, wind speed, wind direction, average temperature and barometric pressure. Before using data from trusted sources (elicited in the references) to build machine learning and deep learning models, the relationships of various features within the dataset were studied in comparison with the target variable – concentration of PM10. In the work done, it has been observed that the Machine Learning model based on Decision-Tree architecture, Extra Trees Regressor, delivered a 93% R2 score, with an RMSE of less than 20 parts per million with respect to PM10 concentration in the air. With this proposed system, multiple advantageous technologies emerging in the domain of air pollution control and mitigation can be built, such as early warning systems for administrative and meteorological departments; and improvement of this system to expand the forecast horizon and integrate the forecasting framework are some valuable future improvements which can be added to this work. Particulate Matter PM10 Respirable Suspended Particulate Matter Forecasting Air Pollution Machine Learning Deep Learning Meteorological Factors Full Text Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Major revisions 24 Jul, 2024 Reviewers agreed at journal 13 Mar, 2024 Reviewers invited by journal 11 Mar, 2024 Editor invited by journal 11 Mar, 2024 Editor assigned by journal 20 Oct, 2023 First submitted to journal 18 Oct, 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-3360409","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":278493562,"identity":"618f253b-20a3-4d5f-bd97-b9c7b21fcbad","order_by":0,"name":"Ishaan Sunita Pandita","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAElEQVRIiWNgGAWjYHADHiA2YJADMQ88IEoHG0SLMVhLAvFaGBgSG0AkPi38YmcPPq6ouCdvPr/3mHRFweH0+WGHHwJtsZPTbcCuRXJ2XrLhmTPFhnOO8aVJnjFIy914O80AqCXZ2OwAdi0Gt3PMJBvbEhhnsPGYSTYY2ORunJ0A0nIgcRsOLfa3c8x/ArXYQ7VIpBvOTv+AV4uBdI4ZI1BLIsyWBHnpHPy2SNzOS5ZsOJOQPIMtx9iywSDNcIN0TsGBBAPcfuGfnXvwY0NFgu0M5jOGNxv+HJaXn52++cOHCjs5XFogkY7iVLBKA1zKsWmRb8CnehSMglEwCkYiAACrUVujUXDKFgAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0006-1868-7244","institution":"Amity University Amity School of Engineering and Technology Mumbai","correspondingAuthor":true,"prefix":"","firstName":"Ishaan","middleName":"Sunita","lastName":"Pandita","suffix":""},{"id":278493563,"identity":"1166e0c9-e4b3-4f3e-9452-99dc21c94d4b","order_by":1,"name":"Gaurav Bhanot","email":"","orcid":"","institution":"Amity University Amity School of Engineering and Technology Mumbai","correspondingAuthor":false,"prefix":"","firstName":"Gaurav","middleName":"","lastName":"Bhanot","suffix":""},{"id":278493564,"identity":"6c169a6b-b233-4010-94eb-be9bfe9c8f89","order_by":2,"name":"A.V. Shanmukh Reddy","email":"","orcid":"","institution":"Amity University Amity School of Engineering and Technology Mumbai","correspondingAuthor":false,"prefix":"","firstName":"A.V.","middleName":"Shanmukh","lastName":"Reddy","suffix":""}],"badges":[],"createdAt":"2023-09-16 05:21:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3360409/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3360409/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":52628551,"identity":"28be7091-cdbb-4b6d-a32e-55da91e0e60b","added_by":"auto","created_at":"2024-03-13 18:31:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":840566,"visible":true,"origin":"","legend":"","description":"","filename":"DLPM10APMFDECS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3360409/v1_covered_f5e59c2d-71d5-48d8-9b5c-1e322c132a1e.pdf"}],"financialInterests":"","formattedTitle":"Deep Learning Approach to predict PM10 pollutant by using other Air Pollutants and Meteorological Factors","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":"international-journal-of-system-assurance-engineering-and-management","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijsa","sideBox":"Learn more about [International Journal of System Assurance Engineering and Management](http://link.springer.com/journal/13198)","snPcode":"13198","submissionUrl":"https://www.editorialmanager.com/ijsa/default2.aspx","title":"International Journal of System Assurance Engineering and Management","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Particulate Matter, PM10, Respirable Suspended Particulate Matter, Forecasting, Air Pollution, Machine Learning, Deep Learning, Meteorological Factors","lastPublishedDoi":"10.21203/rs.3.rs-3360409/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3360409/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Particulate matter in particular poses a serious risk to both human health and the environment. For efficient pollution management and the deployment of appropriate mitigation techniques, accurate air quality forecasting is essential. The objective of the proposed work is to forecast the concentration of PM10 (particulate matter with a diameter of 10 micrometres or less) using a variety of air pollutants as predictors, such as PM2.5, NO2, CO, and other pertinent chemical species. Proposed system makes use of a sizable dataset that includes historical measurements of PM10, PM2.5, NO2, CO, and numerous other air contaminants. It is common knowledge that these pollutants are significant sources of air pollution, and metropolitan areas regularly monitor these pollutants' concentrations. The accuracy of PM10 prediction is increased by using numerous air pollutants as predictors because the intricate interactions and synergistic effects among various pollutants can be captured. This study proposes the development of a system, inspired by existing machine learning and deep learning techniques, capable of forecasting the concentration of PM10 in the atmosphere, using data about other pollutants, as mentioned previously, in the air in the region of prediction, along with meteorological factors defining the weather in the region of prediction, including but not limited to relative humidity, wind speed, wind direction, average temperature and barometric pressure. Before using data from trusted sources (elicited in the references) to build machine learning and deep learning models, the relationships of various features within the dataset were studied in comparison with the target variable – concentration of PM10. In the work done, it has been observed that the Machine Learning model based on Decision-Tree architecture, Extra Trees Regressor, delivered a 93% R2 score, with an RMSE of less than 20 parts per million with respect to PM10 concentration in the air. With this proposed system, multiple advantageous technologies emerging in the domain of air pollution control and mitigation can be built, such as early warning systems for administrative and meteorological departments; and improvement of this system to expand the forecast horizon and integrate the forecasting framework are some valuable future improvements which can be added to this work.","manuscriptTitle":"Deep Learning Approach to predict PM10 pollutant by using other Air Pollutants and Meteorological Factors","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-13 18:23:06","doi":"10.21203/rs.3.rs-3360409/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major revisions","date":"2024-07-24T09:32:30+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2024-03-13T09:09:35+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-03-11T23:50:40+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"International Journal of System Assurance Engineering and Management","date":"2024-03-11T19:47:36+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-10-20T07:50:25+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of System Assurance Engineering and Management","date":"2023-10-18T13:10:33+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-system-assurance-engineering-and-management","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijsa","sideBox":"Learn more about [International Journal of System Assurance Engineering and Management](http://link.springer.com/journal/13198)","snPcode":"13198","submissionUrl":"https://www.editorialmanager.com/ijsa/default2.aspx","title":"International Journal of System Assurance Engineering and Management","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"2b41b278-0df2-4881-b142-8071383f4015","owner":[],"postedDate":"March 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2024-10-07T01:32:40+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-13 18:23:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3360409","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3360409","identity":"rs-3360409","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}