Explainable AI for Accurate Ozone Prediction Based on Remote Sensing and Spatio-Temporal Data: An Empirical Study with the GLA Model

Explainable AI for Accurate Ozone Prediction Based on Remote Sensing and Spatio-Temporal Data: An Empirical Study with the GLA Model | 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 Explainable AI for Accurate Ozone Prediction Based on Remote Sensing and Spatio-Temporal Data: An Empirical Study with the GLA Model Yonghe Feng, Guie Li, Qingwu Yan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9217650/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 Ozone (O₃) exhibits strong spatiotemporal heterogeneity, posing challenges to environmental monitoring and pollution control. Current observation and forecasting approaches fail to effectively integrate remote sensing data and spatiotemporal feature learning, limiting high-resolution daily O₃ prediction and precise pollution management. This study proposes a hybrid machine learning model, GCN-LSTM-Attention, combining Graph Convolutional Networks, Long Short-Term Memory networks, and an attention mechanism with uncertainty quantification. The model captures spatial dependencies via GCN, extracts long-term temporal patterns through LSTM, and enhances interpretability and uncertainty estimation using attention. Applied to spatiotemporal O₃ forecasting in Tianjin with multi-source data (satellite remote sensing, ground observations, meteorology, air pollutants, and land use), results demonstrate high accuracy (R²=0.847, uncertainty = 12.807), strong long-term stability and robustness. Attention analysis identifies dew point temperature as the dominant driver. Control experiments verify the value of multi-source data. The GCN-LSTM-Attention model provides reliable O₃ early warning, supports mechanistic analysis, and offers technical support for targeted pollution control, making it suitable for environmental remote sensing applications. explainable AI ozone prediction spatiotemporal forecasting 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-9217650","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":633448883,"identity":"77fae44c-a6d2-4fa3-a962-7c75e28b38a5","order_by":0,"name":"Yonghe Feng","email":"","orcid":"","institution":"China University of Mining and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yonghe","middleName":"","lastName":"Feng","suffix":""},{"id":633448885,"identity":"e5316d78-a4ea-45b8-8dd0-8afc169c1423","order_by":1,"name":"Guie Li","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtklEQVRIiWNgGAWjYFAC5oYDH6BMCSK1MDYcnAGkeEjSwsxDkhZ598bGwzY1h6PtGZgP3uZhsMsjqMXwzMGGwznHDuf2MLAlW/MwJBcT1jIjseFwbgNIC4+ZNA/DgcQGglrmP2w4bAnWwv+NOC3yEowNhxkhtrARp8WAJ7HhYM+x9Nyew2zGlnMMkomwpf3w4Q8/aqxz29ubH954U2FHhC0HYCxmMJeQepAtBA0dBaNgFIyCUQAAB/s8jo1KjDcAAAAASUVORK5CYII=","orcid":"","institution":"China University of Mining and Technology","correspondingAuthor":true,"prefix":"","firstName":"Guie","middleName":"","lastName":"Li","suffix":""},{"id":633448887,"identity":"91138386-5a9b-4d30-b224-50b3d34e9480","order_by":2,"name":"Qingwu Yan","email":"","orcid":"","institution":"China University of Mining and Technology","correspondingAuthor":false,"prefix":"","firstName":"Qingwu","middleName":"","lastName":"Yan","suffix":""}],"badges":[],"createdAt":"2026-03-25 03:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9217650/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9217650/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109020438,"identity":"e1e3dbc4-6cb1-49a0-95a2-bed9b5381575","added_by":"auto","created_at":"2026-05-11 18:56:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1328067,"visible":true,"origin":"","legend":"","description":"","filename":"manus.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9217650/v1_covered_77465909-c27f-44fc-83a1-f85e4729be45.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eExplainable AI for Accurate Ozone Prediction Based on Remote Sensing and Spatio-Temporal Data: An Empirical Study with the GLA Model\u003c/p\u003e","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":"explainable AI, ozone prediction, spatiotemporal forecasting","lastPublishedDoi":"10.21203/rs.3.rs-9217650/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9217650/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOzone (O₃) exhibits strong spatiotemporal heterogeneity, posing challenges to environmental monitoring and pollution control. Current observation and forecasting approaches fail to effectively integrate remote sensing data and spatiotemporal feature learning, limiting high-resolution daily O₃ prediction and precise pollution management.\u003c/p\u003e \u003cp\u003eThis study proposes a hybrid machine learning model, GCN-LSTM-Attention, combining Graph Convolutional Networks, Long Short-Term Memory networks, and an attention mechanism with uncertainty quantification. The model captures spatial dependencies via GCN, extracts long-term temporal patterns through LSTM, and enhances interpretability and uncertainty estimation using attention.\u003c/p\u003e \u003cp\u003eApplied to spatiotemporal O₃ forecasting in Tianjin with multi-source data (satellite remote sensing, ground observations, meteorology, air pollutants, and land use), results demonstrate high accuracy (R\u0026sup2;=0.847, uncertainty\u0026thinsp;=\u0026thinsp;12.807), strong long-term stability and robustness. Attention analysis identifies dew point temperature as the dominant driver. Control experiments verify the value of multi-source data.\u003c/p\u003e \u003cp\u003eThe GCN-LSTM-Attention model provides reliable O₃ early warning, supports mechanistic analysis, and offers technical support for targeted pollution control, making it suitable for environmental remote sensing applications.\u003c/p\u003e","manuscriptTitle":"Explainable AI for Accurate Ozone Prediction Based on Remote Sensing and Spatio-Temporal Data: An Empirical Study with the GLA Model","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-04 22:42:43","doi":"10.21203/rs.3.rs-9217650/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":"4feebb47-076a-4da2-8c0a-0a3b7e8a559d","owner":[],"postedDate":"May 4th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-11T18:46:14+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T19:33:50+00:00","index":35,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-11T18:55:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-04 22:42:43","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9217650","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9217650","identity":"rs-9217650","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}