Deep learning PM 2.5 hybrid prediction model based on clustering- secondary decomposition strategy

Deep learning PM 2.5 hybrid prediction model based on clustering- secondary decomposition strategy | 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 Deep learning PM 2.5 hybrid prediction model based on clustering- secondary decomposition strategy Tao Zeng, Yahui Liu, Ruru Liu, Jinli Shi, Tao luo, Yunyun Xi, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4801409/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 Accurate prediction of PM 2.5 concentration is important for pollution control, public health and ecological protection. To this end, this paper proposes a deep learning hybrid prediction model based on clustering and secondary decomposition, aiming to achieve accurate prediction of PM 2.5 concentration. The model utilizes the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to decompose the PM 2.5 sequences into multiple intrinsic modal function components (IMFs), and clusters and re-fuses the sub-sequences with similar complexity by permutation entropy (PE) and K-means clustering. For the fused high-frequency sequences a secondary decomposition is performed using the whale optimization algorithm (WOA) optimized variational modal decomposition (VMD). Finally, prediction is performed using the two basic frameworks combined with the long and short-term memory neural network (LSTM). Experiments show that this proposed model exhibits good stability and generalization ability. It does not only make accurate predicts in the short term, but also captures the trends in the long-term prediction. There is a significant performance improvement over the four deep learning baseline models. Further comparisons with existing models outperform the current state-of-the-art models. Earth and environmental sciences/Environmental sciences Physical sciences/Mathematics and computing/Computer science PM2.5 concentration prediction Clustering Secondary decomposition Whale optimization algorithm Hybrid framework Long and short-term memory neural network Full Text Additional Declarations No competing interests reported. Supplementary Files AppendixA.docx Graphicalabstract.tif 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-4801409","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":345148300,"identity":"02aabd83-0456-4114-b337-e89a01240bff","order_by":0,"name":"Tao Zeng","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Zeng","suffix":""},{"id":345148301,"identity":"b69636f1-cef6-4cd8-9c31-7e085c4e3f7f","order_by":1,"name":"Yahui Liu","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Yahui","middleName":"","lastName":"Liu","suffix":""},{"id":345148302,"identity":"f05b552b-2ffc-4d6c-8091-bb6b7c984fa0","order_by":2,"name":"Ruru Liu","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Ruru","middleName":"","lastName":"Liu","suffix":""},{"id":345148303,"identity":"8daf55b4-9f8e-4aa7-a49c-dc7c269d4fc8","order_by":3,"name":"Jinli Shi","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Jinli","middleName":"","lastName":"Shi","suffix":""},{"id":345148304,"identity":"00b5b1ee-4548-4fb5-99c9-6441ba7ef9e2","order_by":4,"name":"Tao luo","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"luo","suffix":""},{"id":345148305,"identity":"1e8c7fee-0fa0-4243-ac86-cc4d58dc8fc3","order_by":5,"name":"Yunyun Xi","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Yunyun","middleName":"","lastName":"Xi","suffix":""},{"id":345148306,"identity":"d2f37358-73f1-4740-a203-b85abe28add7","order_by":6,"name":"Shuo Zhao","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Shuo","middleName":"","lastName":"Zhao","suffix":""},{"id":345148307,"identity":"5b62554f-d0f9-4709-b816-64e6633b5f46","order_by":7,"name":"Chunpeng Chen","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Chunpeng","middleName":"","lastName":"Chen","suffix":""},{"id":345148308,"identity":"bf74ff9a-846e-4fc1-8b6a-a991084c9d4b","order_by":8,"name":"Guangrui Pan","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Guangrui","middleName":"","lastName":"Pan","suffix":""},{"id":345148309,"identity":"e311dd71-b786-408c-9082-12d1ace032b3","order_by":9,"name":"Yuming Zhou","email":"","orcid":"","institution":"Shihezi University","correspondingAuthor":false,"prefix":"","firstName":"Yuming","middleName":"","lastName":"Zhou","suffix":""},{"id":345148310,"identity":"7129fa6d-23fa-46df-87f8-95410ae3ad07","order_by":10,"name":"Liping Xu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAtUlEQVRIiWNgGAWjYDACdiB+wGDDw8/fQKwWZiBOYEiTkZxxgDQth20MGhKI1GFwmPfgh8S28zwGDAcYP3zMIUKLZDNfskRi220ec+YGZsmZ24jQws/MYyCRuO02j2XDATZmXmK0sDHzGP9I3HaOx+BAApFagLaYAW05QIIWoF/SLBL/JfNIzjjYTJxfDI73Hr7x4YydPT9/88EPH4nRwsDAA2MwNhClHlnLKBgFo2AUjAIcAAAQgzId/nJKGgAAAABJRU5ErkJggg==","orcid":"","institution":"Shihezi University","correspondingAuthor":true,"prefix":"","firstName":"Liping","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2024-07-25 11:12:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4801409/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4801409/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":65165830,"identity":"e12e4eef-b1e1-4b06-9e05-a9fcefdb72da","added_by":"auto","created_at":"2024-09-24 09:54:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":743619,"visible":true,"origin":"","legend":"","description":"","filename":"Manusrcipt.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4801409/v1_covered_1bf28380-e69a-4b56-a59d-0338bbfcd94d.pdf"},{"id":63549697,"identity":"985aa130-4b5c-405b-9b9f-158be71bbeb7","added_by":"auto","created_at":"2024-08-29 12:06:36","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5033510,"visible":true,"origin":"","legend":"","description":"","filename":"AppendixA.docx","url":"https://assets-eu.researchsquare.com/files/rs-4801409/v1/9c594b85868cea908f7c2179.docx"},{"id":63549696,"identity":"29495885-4aa7-4898-b794-c6fe7e2fa1fb","added_by":"auto","created_at":"2024-08-29 12:06:36","extension":"tif","order_by":2,"title":"","display":"","copyAsset":false,"role":"supplement","size":2381172,"visible":true,"origin":"","legend":"","description":"","filename":"Graphicalabstract.tif","url":"https://assets-eu.researchsquare.com/files/rs-4801409/v1/fc8631c7e3af6c6b4d4f57cb.tif"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep learning PM 2.5 hybrid prediction model based on clustering- secondary decomposition strategy","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":"PM2.5 concentration prediction, Clustering, Secondary decomposition, Whale optimization algorithm, Hybrid framework, Long and short-term memory neural network","lastPublishedDoi":"10.21203/rs.3.rs-4801409/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4801409/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate prediction of PM\u003csub\u003e2.5\u003c/sub\u003e concentration is important for pollution control, public health and ecological protection. To this end, this paper proposes a deep learning hybrid prediction model based on clustering and secondary decomposition, aiming to achieve accurate prediction of PM\u003csub\u003e2.5\u003c/sub\u003e concentration. The model utilizes the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to decompose the PM\u003csub\u003e2.5\u003c/sub\u003e sequences into multiple intrinsic modal function components (IMFs), and clusters and re-fuses the sub-sequences with similar complexity by permutation entropy (PE) and K-means clustering. For the fused high-frequency sequences a secondary decomposition is performed using the whale optimization algorithm (WOA) optimized variational modal decomposition (VMD). Finally, prediction is performed using the two basic frameworks combined with the long and short-term memory neural network (LSTM). Experiments show that this proposed model exhibits good stability and generalization ability. It does not only make accurate predicts in the short term, but also captures the trends in the long-term prediction. There is a significant performance improvement over the four deep learning baseline models. Further comparisons with existing models outperform the current state-of-the-art models.\u003c/p\u003e","manuscriptTitle":"Deep learning PM 2.5 hybrid prediction model based on clustering- secondary decomposition strategy","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-29 12:06:31","doi":"10.21203/rs.3.rs-4801409/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":"75bccb1c-b849-450d-a88c-b3bc2c041d36","owner":[],"postedDate":"August 29th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":36578460,"name":"Earth and environmental sciences/Environmental sciences"},{"id":36578461,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2024-09-24T09:54:22+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-29 12:06:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4801409","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4801409","identity":"rs-4801409","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}