Designing an End-to-End Urban Air Pollution Forecasting Framework: A Data-Driven Pipeline Approach

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Abstract Air pollution forecasting plays a vital role in mitigating the adverse impacts of deteriorating air quality on public health and urban sustainability. This study presents a data-driven framework for urban air quality forecasting, focusing on the accurate prediction of PM 2.5 concentrations. To ensure reliable model training, the Beijing Air Quality dataset was carefully preprocessed, including handling of missing values, removal of outliers, and feature selection based on correlation analysis. The proposed model introduces a residual-enhanced hybrid forecasting framework that integrates the statistical interpretability of Prophet with the nonlinear learning capacity of Long Short-Term Memory (LSTM) networks. Prophet is first employed to capture long-term trend and seasonality components of PM 2.5 time series, while an LSTM is trained on the residuals to model complex, nonlinear dependencies that Prophet cannot explain. Extensive experiments conducted on the air quality dataset demonstrate that the proposed Prophet+LSTM model significantly outperforms both traditional statistical methods and advanced deep learning baselines, achieving lower MAE and RMSE compared to AC-LSTM, LSTM-FC, CNN-LSTM, and XGBoost. These results highlight the effectiveness of preprocessing and hybrid modeling for accurate air quality forecasting and provide a framework for urban air quality monitoring.
Full text 27,092 characters · extracted from preprint-html · click to expand
Designing an End-to-End Urban Air Pollution Forecasting Framework: A Data-Driven Pipeline Approach | 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 Article Designing an End-to-End Urban Air Pollution Forecasting Framework: A Data-Driven Pipeline Approach Musa Milli This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7537438/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 11 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted 12 You are reading this latest preprint version Abstract Air pollution forecasting plays a vital role in mitigating the adverse impacts of deteriorating air quality on public health and urban sustainability. This study presents a data-driven framework for urban air quality forecasting, focusing on the accurate prediction of PM 2.5 concentrations. To ensure reliable model training, the Beijing Air Quality dataset was carefully preprocessed, including handling of missing values, removal of outliers, and feature selection based on correlation analysis. The proposed model introduces a residual-enhanced hybrid forecasting framework that integrates the statistical interpretability of Prophet with the nonlinear learning capacity of Long Short-Term Memory (LSTM) networks. Prophet is first employed to capture long-term trend and seasonality components of PM 2.5 time series, while an LSTM is trained on the residuals to model complex, nonlinear dependencies that Prophet cannot explain. Extensive experiments conducted on the air quality dataset demonstrate that the proposed Prophet+LSTM model significantly outperforms both traditional statistical methods and advanced deep learning baselines, achieving lower MAE and RMSE compared to AC-LSTM, LSTM-FC, CNN-LSTM, and XGBoost. These results highlight the effectiveness of preprocessing and hybrid modeling for accurate air quality forecasting and provide a framework for urban air quality monitoring. Earth and environmental sciences/Climate sciences Physical sciences/Engineering Earth and environmental sciences/Environmental sciences Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 11 Dec, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 06 Oct, 2025 Reviews received at journal 04 Oct, 2025 Reviews received at journal 01 Oct, 2025 Reviewers agreed at journal 21 Sep, 2025 Reviewers agreed at journal 18 Sep, 2025 Reviewers agreed at journal 18 Sep, 2025 Reviewers agreed at journal 17 Sep, 2025 Reviewers invited by journal 16 Sep, 2025 Editor assigned by journal 16 Sep, 2025 Editor invited by journal 12 Sep, 2025 Submission checks completed at journal 11 Sep, 2025 First submitted to journal 11 Sep, 2025 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-7537438","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":518389350,"identity":"b7f0f9d3-3772-4178-a465-146182d013ba","order_by":0,"name":"Musa Milli","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYPACCRk+ZuYDEPYBIrXwsDGzJcC0MDYQo4eHjYHHgDgtujPSH35gzLHgYWPn+brxZxuDHN+NBPbHFXi0mN3IMZZg3AZyGO+227xtDMaSNxIYG8/g18KA0MLYxpC4AaQFn8vMbqQ//gHRwvPsJtBh9URoSTCD2sLDdgPosAQDglrOvDGzSARrYTO7zXNOwnDmmYeNM/FqOZ7++MbHbXVy/PyHn938UWYjz3c8+cBHfFrAIAHBlABi4mJyFIyCUTAKRgEeAABUGUglcGyF/QAAAABJRU5ErkJggg==","orcid":"","institution":"Turkish Naval Academy, National Defense University","correspondingAuthor":true,"prefix":"","firstName":"Musa","middleName":"","lastName":"Milli","suffix":""}],"badges":[],"createdAt":"2025-09-04 15:08:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7537438/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7537438/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-27510-y","type":"published","date":"2025-12-11T15:59:12+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":92190506,"identity":"3a8b3a74-9726-4a8a-83c2-9b08c15bda5d","added_by":"auto","created_at":"2025-09-25 15:06:00","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3390,"visible":true,"origin":"","legend":"","description":"","filename":"8acf974424eb465fa383e06329d3af47.json","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/6924235d2181fbc00e63a6d2.json"},{"id":92190496,"identity":"d914f569-90a2-4565-80ff-31ea381c6157","added_by":"auto","created_at":"2025-09-25 15:05:59","extension":"ldf","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":49107,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaall.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/00a15a2a5f4e07c6990d7b77.ldf"},{"id":92190507,"identity":"c1060732-a4e6-4220-9828-3f0dd61752a2","added_by":"auto","created_at":"2025-09-25 15:06:01","extension":"ldf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":268657,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrvltwaen.ldf","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/7fb0204cc052945e3126e615.ldf"},{"id":92191842,"identity":"1f362c69-2248-46fe-8735-2c94e159646e","added_by":"auto","created_at":"2025-09-25 15:13:52","extension":"sty","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15480,"visible":true,"origin":"","legend":"","description":"","filename":"jabbrv.sty","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/0c04b5b38cc109f1c0ef8742.sty"},{"id":92190501,"identity":"023438f4-fa3d-4f26-8e55-973d2860aab9","added_by":"auto","created_at":"2025-09-25 15:05:59","extension":"aux","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13858,"visible":true,"origin":"","legend":"","description":"","filename":"main.aux","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/4dae6bb201adc1d84ac06af0.aux"},{"id":92190422,"identity":"d362ad84-59eb-46fb-8f48-dabdbccbec40","added_by":"auto","created_at":"2025-09-25 15:05:56","extension":"bbl","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23227,"visible":true,"origin":"","legend":"","description":"","filename":"main.bbl","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/d360c14fc9671bc46d29653c.bbl"},{"id":92190486,"identity":"d47720b0-2777-4b34-9fd4-02e863ee7bf8","added_by":"auto","created_at":"2025-09-25 15:05:59","extension":"blg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1062,"visible":true,"origin":"","legend":"","description":"","filename":"main.blg","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/041de6be9cb7370f0cc4b019.blg"},{"id":92190325,"identity":"dae3a7d3-3fd3-459f-b01d-60a6b50e43ce","added_by":"auto","created_at":"2025-09-25 15:05:53","extension":"log","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41195,"visible":true,"origin":"","legend":"","description":"","filename":"main.log","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/76fba9573d6fbac5cd84fe85.log"},{"id":92190504,"identity":"92d8f64c-cc02-4791-848a-c4227864d41a","added_by":"auto","created_at":"2025-09-25 15:06:00","extension":"out","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":101,"visible":true,"origin":"","legend":"","description":"","filename":"main.out","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/245eb0ac434f2c07bb2fd781.out"},{"id":92190502,"identity":"b72a98f6-add7-49b1-9263-6d1ca43ccf3e","added_by":"auto","created_at":"2025-09-25 15:05:59","extension":"pdf","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6441245,"visible":true,"origin":"","legend":"","description":"","filename":"main.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/783cc9f181bdbe41310d73a9.pdf"},{"id":92190485,"identity":"122e5950-0f76-4b9f-8f89-4898f314fa07","added_by":"auto","created_at":"2025-09-25 15:05:58","extension":"gz","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":247831,"visible":true,"origin":"","legend":"","description":"","filename":"main.synctex.gz","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/440f443ea80818dfbd1ce51d.gz"},{"id":92190311,"identity":"edea957c-5d83-49a0-98c1-a84408293098","added_by":"auto","created_at":"2025-09-25 15:05:52","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":68603,"visible":true,"origin":"","legend":"","description":"","filename":"milli1.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/b090767d75d6d04f527a9205.png"},{"id":92190337,"identity":"ea6170d4-c5a7-46d9-b132-8897aedc9757","added_by":"auto","created_at":"2025-09-25 15:05:54","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":529292,"visible":true,"origin":"","legend":"","description":"","filename":"milli10.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/1158f35c68a8c8355f0976fe.png"},{"id":92190362,"identity":"d1f75d46-f96f-4c39-b6f0-99b56dab2a5d","added_by":"auto","created_at":"2025-09-25 15:05:56","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":312684,"visible":true,"origin":"","legend":"","description":"","filename":"milli11.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/80b0bbb93a39e6b2824cec8a.png"},{"id":92190340,"identity":"ff648729-0cbf-489c-89b0-1e476feafb98","added_by":"auto","created_at":"2025-09-25 15:05:54","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":869592,"visible":true,"origin":"","legend":"","description":"","filename":"milli12.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/f3e324e87fadb2ec4ac557d1.png"},{"id":92191867,"identity":"194851b4-29c7-4612-80d7-bd0ea1e819e9","added_by":"auto","created_at":"2025-09-25 15:13:57","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":825948,"visible":true,"origin":"","legend":"","description":"","filename":"milli13.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/520735e006d1dfa01290ab7a.png"},{"id":92190456,"identity":"84a03f30-40fa-4b74-aa77-b6eebb66261e","added_by":"auto","created_at":"2025-09-25 15:05:57","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":514297,"visible":true,"origin":"","legend":"","description":"","filename":"milli14.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/a041d89e132a69ab03d6fe2a.png"},{"id":92191870,"identity":"5fe77516-0a7a-4108-8494-df6bfa74652c","added_by":"auto","created_at":"2025-09-25 15:13:58","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":385442,"visible":true,"origin":"","legend":"","description":"","filename":"milli15.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/59642267c99f785fd0f7ab75.png"},{"id":92190288,"identity":"ac5ad6ec-ba14-417a-9929-3eee3d159d58","added_by":"auto","created_at":"2025-09-25 15:05:52","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":189451,"visible":true,"origin":"","legend":"","description":"","filename":"milli16.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/02a66a4b76df126ffaa46666.png"},{"id":92190505,"identity":"f3c72170-b1d6-4dff-baf5-75c0066c6cee","added_by":"auto","created_at":"2025-09-25 15:06:00","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124723,"visible":true,"origin":"","legend":"","description":"","filename":"milli17.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/a43a2120646e4947e1fe5478.png"},{"id":92190499,"identity":"a12261b7-6454-4284-8df7-e21b3e111015","added_by":"auto","created_at":"2025-09-25 15:05:59","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":393666,"visible":true,"origin":"","legend":"","description":"","filename":"milli18.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/1679f3de1126dee26e608c96.png"},{"id":92190503,"identity":"73ac1578-43f4-46f2-8dca-d732c9533522","added_by":"auto","created_at":"2025-09-25 15:06:00","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103207,"visible":true,"origin":"","legend":"","description":"","filename":"milli2.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/44fd115556effccc9c661cb7.png"},{"id":92190509,"identity":"535fbab6-c4e3-49a3-b527-d8e40ae06916","added_by":"auto","created_at":"2025-09-25 15:06:01","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81933,"visible":true,"origin":"","legend":"","description":"","filename":"milli3.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/cc59eabf5d0216f15bcfa182.png"},{"id":92190467,"identity":"ec0681a9-c5a6-467c-a38e-0ade7c3774fb","added_by":"auto","created_at":"2025-09-25 15:05:58","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":107667,"visible":true,"origin":"","legend":"","description":"","filename":"milli4.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/fb939c78ac11feb4837b5f9c.png"},{"id":92190165,"identity":"a14175d1-5051-4b2f-a904-f1548365416f","added_by":"auto","created_at":"2025-09-25 15:05:48","extension":"png","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":127661,"visible":true,"origin":"","legend":"","description":"","filename":"milli5.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/13447efdd40bc2cdd98b4f79.png"},{"id":92190483,"identity":"1ebbc64d-fb7f-475f-bf1c-d011f5ceca18","added_by":"auto","created_at":"2025-09-25 15:05:58","extension":"png","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1466309,"visible":true,"origin":"","legend":"","description":"","filename":"milli6.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/4a60cdaeeb04863ae5ece47a.png"},{"id":92190293,"identity":"9dffa675-91ad-4fd6-800d-ae097cca62b6","added_by":"auto","created_at":"2025-09-25 15:05:52","extension":"png","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":589718,"visible":true,"origin":"","legend":"","description":"","filename":"milli7.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/95f7636b4e26f3cb964e5fc5.png"},{"id":92190419,"identity":"d161167a-e33f-4158-97d2-1b9f9ee72f87","added_by":"auto","created_at":"2025-09-25 15:05:56","extension":"png","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":83306,"visible":true,"origin":"","legend":"","description":"","filename":"milli8.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/9ffc42fa7cbe8b59a2bec409.png"},{"id":92190463,"identity":"0efe15d0-5ead-415a-9060-f0cdb4a8b539","added_by":"auto","created_at":"2025-09-25 15:05:58","extension":"png","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":339802,"visible":true,"origin":"","legend":"","description":"","filename":"milli9.png","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/a549f12d11d1a0244dcb2dd2.png"},{"id":92190379,"identity":"7ea24cd0-e6c4-4a30-8246-238127c1fd95","added_by":"auto","created_at":"2025-09-25 15:05:56","extension":"pdf","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6450155,"visible":true,"origin":"","legend":"","description":"","filename":"milliHighlightedRevision.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/5f6941b7aafed6688ec4a2ec.pdf"},{"id":92190380,"identity":"206c0787-2023-4d20-854a-01b8f281d35a","added_by":"auto","created_at":"2025-09-25 15:05:56","extension":"pdf","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6909213,"visible":true,"origin":"","legend":"","description":"","filename":"milliRevisedVersion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/70c153b7b7fdf1fd01419ea4.pdf"},{"id":92190360,"identity":"af9b523b-4e61-4488-a0e0-e1ccd18d78c7","added_by":"auto","created_at":"2025-09-25 15:05:55","extension":"bst","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36153,"visible":true,"origin":"","legend":"","description":"","filename":"naturemagdoi.bst","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/d4ef36b3684fa323c3c44d86.bst"},{"id":92190500,"identity":"25c470b0-37e5-43a8-8e0e-b093e988f3ea","added_by":"auto","created_at":"2025-09-25 15:05:59","extension":"pdf","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87860,"visible":true,"origin":"","legend":"","description":"","filename":"responses.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/50d1235ce49ef35bd156bd00.pdf"},{"id":92190155,"identity":"23ad9c1e-169e-4a27-9655-8adf5c122315","added_by":"auto","created_at":"2025-09-25 15:05:48","extension":"cls","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5824,"visible":true,"origin":"","legend":"","description":"","filename":"wlscirep.cls","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/cad6337efa7cd7eac248721a.cls"},{"id":92190350,"identity":"f52491dd-51a5-40bf-a0f1-f98c1b164d30","added_by":"auto","created_at":"2025-09-25 15:05:55","extension":"xml","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155904,"visible":true,"origin":"","legend":"","description":"","filename":"8acf974424eb465fa383e06329d3af471structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1/2df3139f96cc47decfd470ba.xml"},{"id":98244810,"identity":"d75e88ae-bbac-4647-8e5b-a10310642327","added_by":"auto","created_at":"2025-12-15 16:15:24","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4842054,"visible":true,"origin":"","legend":"","description":"","filename":"milliRevisedVersion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7537438/v1_covered_d83dada7-1d3d-4359-979e-5c395bdf88ce.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Designing an End-to-End Urban Air Pollution Forecasting Framework: A Data-Driven Pipeline Approach","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-7537438/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7537438/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Air pollution forecasting plays a vital role in mitigating the adverse impacts of deteriorating air quality on public health and urban sustainability. This study presents a data-driven framework for urban air quality forecasting, focusing on the accurate prediction of PM 2.5 concentrations. To ensure reliable model training, the Beijing Air Quality dataset was carefully preprocessed, including handling of missing values, removal of outliers, and feature selection based on correlation analysis. The proposed model introduces a residual-enhanced hybrid forecasting framework that integrates the statistical interpretability of Prophet with the nonlinear learning capacity of Long Short-Term Memory (LSTM) networks. Prophet is first employed to capture long-term trend and seasonality components of PM 2.5 time series, while an LSTM is trained on the residuals to model complex, nonlinear dependencies that Prophet cannot explain. Extensive experiments conducted on the air quality dataset demonstrate that the proposed Prophet+LSTM model significantly outperforms both traditional statistical methods and advanced deep learning baselines, achieving lower MAE and RMSE compared to AC-LSTM, LSTM-FC, CNN-LSTM, and XGBoost. These results highlight the effectiveness of preprocessing and hybrid modeling for accurate air quality forecasting and provide a framework for urban air quality monitoring.","manuscriptTitle":"Designing an End-to-End Urban Air Pollution Forecasting Framework: A Data-Driven Pipeline Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-25 14:57:07","doi":"10.21203/rs.3.rs-7537438/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-10-06T19:44:05+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-04T23:50:34+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-01T12:56:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"112689508890594120642329276433977772921","date":"2025-09-22T01:05:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"138044812291615287319277794506916672552","date":"2025-09-18T07:04:52+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"182748960804404971280316282649542807415","date":"2025-09-18T04:57:18+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"186672374864956014488315315574480122718","date":"2025-09-17T07:37:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-16T19:17:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-16T15:26:41+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-09-12T16:59:32+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-11T06:09:55+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-09-11T06:05:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"ed25f920-ddf7-455d-a59d-e363461a9682","owner":[],"postedDate":"September 25th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":55082159,"name":"Earth and environmental sciences/Climate sciences"},{"id":55082160,"name":"Physical sciences/Engineering"},{"id":55082161,"name":"Earth and environmental sciences/Environmental sciences"},{"id":55082162,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2025-12-15T16:09:13+00:00","versionOfRecord":{"articleIdentity":"rs-7537438","link":"https://doi.org/10.1038/s41598-025-27510-y","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-12-11 15:59:12","publishedOnDateReadable":"December 11th, 2025"},"versionCreatedAt":"2025-09-25 14:57:07","video":"","vorDoi":"10.1038/s41598-025-27510-y","vorDoiUrl":"https://doi.org/10.1038/s41598-025-27510-y","workflowStages":[]},"version":"v1","identity":"rs-7537438","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7537438","identity":"rs-7537438","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Outcome instruments

MUSA

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-22T02:00:06.705733+00:00
License: CC-BY-4.0