Using Artificial Neural Network for Forecasting PM2.5 Levels in a Prominent Industrial and Historically Significant Urban Center in Iran: Evaluating Health Implications

Using Artificial Neural Network for Forecasting PM2.5 Levels in a Prominent Industrial and Historically Significant Urban Center in Iran: Evaluating Health Implications | 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 Using Artificial Neural Network for Forecasting PM 2.5 Levels in a Prominent Industrial and Historically Significant Urban Center in Iran: Evaluating Health Implications ali mohammadi bardshahi, Neemat Jaafarzadeh, Tayebeh Tabatabaie, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3283577/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 5 You are reading this latest preprint version Abstract There has been a scarcity of comprehensive studies that aim to predict both the levels of PM 2.5 particles and their corresponding impacts on human health. To fill this gap, we developed an artificial neural network model and AirQ+ software to predict PM 2.5 concentrations and assess their associated health effects. The ANN model utilized five distinct input parameters, specifically wind velocity, wind orientation, atmospheric temperature, relative moisture content, and PM 2.5 levels, observed within the time frame of 2018 to 2019. The concealed stratum comprised a total of ten neurons, in addition to the presence of an output layer. The MLP neural network demonstrated strong correlations at each stage: 0.908 (training), 0.910 (validation), 0.914 (testing), and 0.907 overall. The RMSE was determined as 6.52 µg/m 3 when evaluating the neural network, thus indicating the notable predictive precision exhibited by the multilayer perceptron (MLP) neural network when forecasting the concentration of PM 2.5 particles. The AirQ+ software, created by the World Health Organization (WHO), was employed to assess the magnitude and consequences of PM 2.5 concentrations. The average concentration of PM 2.5 particles throughout the duration of the study was recorded as 26.5 μg/m 3 , which exceeds the recommended limit provided by the WHO by a factor of 5.3. The study estimated the proportions and numbers of deaths attributed to various conditions. Specifically, chronic obstructive pulmonary disease (COPD), ischemic heart disease (IHD), lung cancer (LC), stroke, and all-cause mortality accounted for approximately 11.67%, 15.02%, 13.25%, 15.225%, and 9.45% respectively. The estimated number of deaths were 19,195 for all causes, 10,063 for COPD, 564 for IHD, and 1,063 for lung cancer. The findings of this investigation demonstrate a high degree of reliability in the methodologies utilized. Through the utilization of these approaches, individuals in positions of authority and responsibility can aptly evaluate the cost-benefit analysis, leading to a reduction in human casualties and mitigating the economic burdens on society. PM2.5 Prediction Artificial Neural Network Iran Health Effects Full Text Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Major Revision 08 Jul, 2024 Reviewers agreed at journal 02 Dec, 2023 Reviewers invited by journal 09 Oct, 2023 Editor assigned by journal 27 Sep, 2023 First submitted to journal 20 Sep, 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-3283577","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":238806418,"identity":"7e640b5b-8832-438b-89a4-486bce4a9258","order_by":0,"name":"ali mohammadi bardshahi","email":"data:image/png;base64,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","orcid":"","institution":"Azad University: Islamic Azad University","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"ali","middleName":"mohammadi","lastName":"bardshahi","suffix":""},{"id":238806419,"identity":"a28c141a-a38f-4127-85fa-ae4890a7675d","order_by":1,"name":"Neemat Jaafarzadeh","email":"","orcid":"","institution":"Ahvaz Jondishapour University of Medical Sciences","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Neemat","middleName":"","lastName":"Jaafarzadeh","suffix":""},{"id":238806420,"identity":"ed365724-f9c0-495a-aed6-91516b7c96f9","order_by":2,"name":"Tayebeh Tabatabaie","email":"","orcid":"","institution":"Islamic Azad University Bushehr Branch","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tayebeh","middleName":"","lastName":"Tabatabaie","suffix":""},{"id":238806421,"identity":"d2019a1c-7456-4890-be38-e1080a12ba23","order_by":3,"name":"Fazel Amiri","email":"","orcid":"","institution":"Islamic Azad University Bushehr Branch","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Fazel","middleName":"","lastName":"Amiri","suffix":""}],"badges":[],"createdAt":"2023-08-21 20:19:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3283577/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3283577/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":44531613,"identity":"2bf28d9e-4a70-4ad4-933e-11e3b198f752","added_by":"auto","created_at":"2023-10-12 17:43:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1107481,"visible":true,"origin":"","legend":"","description":"","filename":"MANUSCRIPT.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3283577/v1_covered_542b9984-56ce-47e2-ad07-6c9e0d8a5a52.pdf"}],"financialInterests":"","formattedTitle":"\u003cp\u003eUsing Artificial Neural Network for Forecasting PM\u003csub\u003e2.5\u003c/sub\u003e Levels in a Prominent Industrial and Historically Significant Urban Center in Iran: Evaluating Health Implications\u003c/p\u003e","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":"environmental-science-and-pollution-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"espr","sideBox":"Learn more about [Environmental Science and Pollution Research](https://www.springer.com/journal/11356)","snPcode":"11356","submissionUrl":"https://submission.nature.com/new-submission/11356/3","title":"Environmental Science and Pollution Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"PM2.5, Prediction, Artificial Neural Network, Iran, Health Effects","lastPublishedDoi":"10.21203/rs.3.rs-3283577/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3283577/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThere has been a scarcity of comprehensive studies that aim to predict both the levels of PM\u003csub\u003e2.5\u003c/sub\u003e particles and their corresponding impacts on human health. To fill this gap, we developed an artificial neural network model and AirQ+ software to predict PM\u003csub\u003e2.5 \u003c/sub\u003econcentrations and assess their associated health effects. The ANN model utilized five distinct input parameters, specifically wind velocity, wind orientation, atmospheric temperature, relative moisture content, and PM\u003csub\u003e2.5 \u003c/sub\u003elevels, observed within the time frame of 2018 to 2019. The concealed stratum comprised a total of ten neurons, in addition to the presence of an output layer. The MLP neural network demonstrated strong correlations at each stage: 0.908 (training), 0.910 (validation), 0.914 (testing), and 0.907 overall. The RMSE was determined as 6.52 µg/m\u003csup\u003e3\u003c/sup\u003e when evaluating the neural network, thus indicating the notable predictive precision exhibited by the multilayer perceptron (MLP) neural network when forecasting the concentration of PM\u003csub\u003e2.5 \u003c/sub\u003eparticles. The AirQ+ software, created by the World Health Organization (WHO), was employed to assess the magnitude and consequences of PM\u003csub\u003e2.5 \u003c/sub\u003econcentrations. The average concentration of PM\u003csub\u003e2.5 \u003c/sub\u003eparticles throughout the duration of the study was recorded as 26.5 μg/m\u003csup\u003e3\u003c/sup\u003e, which exceeds the recommended limit provided by the WHO by a factor of 5.3. The study estimated the proportions and numbers of deaths attributed to various conditions. Specifically, chronic obstructive pulmonary disease (COPD), ischemic heart disease (IHD), lung cancer (LC), stroke, and all-cause mortality accounted for approximately 11.67%, 15.02%, 13.25%, 15.225%, and 9.45% respectively. The estimated number of deaths were 19,195 for all causes, 10,063 for COPD, 564 for IHD, and 1,063 for lung cancer. The findings of this investigation demonstrate a high degree of reliability in the methodologies utilized. Through the utilization of these approaches, individuals in positions of authority and responsibility can aptly evaluate the cost-benefit analysis, leading to a reduction in human casualties and mitigating the economic burdens on society.\u003c/p\u003e","manuscriptTitle":"Using Artificial Neural Network for Forecasting PM2.5 Levels in a Prominent Industrial and Historically Significant Urban Center in Iran: Evaluating Health Implications","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2023-10-12 17:35:15","doi":"10.21203/rs.3.rs-3283577/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Major Revision","date":"2024-07-08T18:03:33+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2023-12-03T02:44:34+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2023-10-09T11:50:07+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2023-09-27T05:09:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"Environmental Science and Pollution Research","date":"2023-09-20T14:17:07+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"environmental-science-and-pollution-research","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"espr","sideBox":"Learn more about [Environmental Science and Pollution Research](https://www.springer.com/journal/11356)","snPcode":"11356","submissionUrl":"https://submission.nature.com/new-submission/11356/3","title":"Environmental Science and Pollution Research","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"9eddbb4b-c831-411d-a931-4c0c78f1789a","owner":[],"postedDate":"October 12th, 2023","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2024-07-08T22:03:47+00:00","versionOfRecord":[],"versionCreatedAt":"2023-10-12 17:35:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3283577","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3283577","identity":"rs-3283577","version":["v1"]},"buildId":"rHA-KDH7Qsr4HCuvH75dn","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}