RF-LSTM carbon price prediction based on CEEMDAN decomposition and multiscale entropy reconstruction

RF-LSTM carbon price prediction based on CEEMDAN decomposition and multiscale entropy reconstruction | 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 RF-LSTM carbon price prediction based on CEEMDAN decomposition and multiscale entropy reconstruction Heping Wang, Yaping Li This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7062258/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 14 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted 14 You are reading this latest preprint version Abstract This paper proposed an RF-LSTM hybrid prediction model based on CEEMDAN decomposition and multiscale entropy reconstruction. The new model solves the problem of insufficient prediction accuracy caused by the carbon price series’ nonlinearity, non-stationarity, and multifractal characteristics. The method first decomposes price series into IMFs using CEEMDAN, then reconstructs components through multiscale entropy analysis to reduce noise interference. A dual prediction framework combines Random Forest (capturing nonlinear patterns in high-frequency components) and LSTM (modeling long-term dependencies in low-frequency components). Empirical tests on Hubei and EU carbon market data show: (1) The model achieves superior accuracy over benchmarks (CEEMDAN-LSTM/LSTM) across multiple metrics; (2) Maintains high computational efficiency; (3) Demonstrates optimal comprehensive performance. Results verify that entropy-based reconstruction effectively mitigates mode mixing, while RF-LSTM synergy enhances cross-frequency prediction capability, providing methodological support for carbon market risk management. Physical sciences/Engineering Physical sciences/Mathematics and computing carbon price forecasting CEEMDAN multi-scale entropy RF LSTM Full Text Additional Declarations No competing interests reported. Supplementary Files Hubeidata.csv EUAdata.csv Cite Share Download PDF Status: Published Journal Publication published 14 Jan, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 19 Sep, 2025 Reviews received at journal 18 Sep, 2025 Reviews received at journal 18 Sep, 2025 Reviewers agreed at journal 16 Sep, 2025 Reviews received at journal 10 Sep, 2025 Reviewers agreed at journal 10 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers agreed at journal 08 Sep, 2025 Reviewers invited by journal 02 Sep, 2025 Editor assigned by journal 01 Sep, 2025 Editor invited by journal 20 Aug, 2025 Submission checks completed at journal 18 Aug, 2025 First submitted to journal 18 Aug, 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-7062258","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":510516891,"identity":"445b4198-f111-4e04-8bf1-3b53cd2d036d","order_by":0,"name":"Heping Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwklEQVRIiWNgGAWjYBACAwhlw8AGonhI0JLGwMZGopbDDAxEazGX7jH8XPDrfB6ffAPjg7dtDPLmhLRYzjljLD2z73Yx0GHMhnPbGAx3NhBy2I3cDdK8PbcT29gY2KR52xgSDA4Q1rL5N2/POZAW9t/EatkmzfPjANgWZuK03Dn/zZq3IRmoJbFZcs45CcMNBLXcbku+zfPHLnF+8+GDH96U2cgTtIVBAogZ20AsxgYolxgtDH+IUDgKRsEoGAUjFwAA8s89VbpEjxkAAAAASUVORK5CYII=","orcid":"","institution":"Nanchang Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Heping","middleName":"","lastName":"Wang","suffix":""},{"id":510516892,"identity":"4a340714-a30c-4d8a-81eb-13b2fca0fd40","order_by":1,"name":"Yaping Li","email":"","orcid":"","institution":"Nanchang Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Yaping","middleName":"","lastName":"Li","suffix":""}],"badges":[],"createdAt":"2025-07-07 07:08:35","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7062258/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7062258/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-026-35085-5","type":"published","date":"2026-01-14T16:30:55+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":100614813,"identity":"55b7b8e5-76e3-453f-8917-c09f447c520b","added_by":"auto","created_at":"2026-01-19 17:25:55","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1189077,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7062258/v1_covered_0819e639-901a-4382-8417-f7b313c34c25.pdf"},{"id":90835498,"identity":"d7045f9f-2985-4d0f-b548-d7604c4db4f1","added_by":"auto","created_at":"2025-09-08 17:36:15","extension":"csv","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":48000,"visible":true,"origin":"","legend":"","description":"","filename":"Hubeidata.csv","url":"https://assets-eu.researchsquare.com/files/rs-7062258/v1/4437aaef87f15a4938eb3d50.csv"},{"id":90837399,"identity":"2fb470a4-8567-4b09-bb16-e8a4b341ef6c","added_by":"auto","created_at":"2025-09-08 18:08:15","extension":"csv","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":48160,"visible":true,"origin":"","legend":"","description":"","filename":"EUAdata.csv","url":"https://assets-eu.researchsquare.com/files/rs-7062258/v1/dab8a2b1b46864ea88c99770.csv"}],"financialInterests":"No competing interests reported.","formattedTitle":"RF-LSTM carbon price prediction based on CEEMDAN decomposition and multiscale entropy reconstruction","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":"carbon price forecasting, CEEMDAN, multi-scale entropy, RF, LSTM","lastPublishedDoi":"10.21203/rs.3.rs-7062258/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7062258/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis paper proposed an RF-LSTM hybrid prediction model based on CEEMDAN decomposition and multiscale entropy reconstruction. The new model solves the problem of insufficient prediction accuracy caused by the carbon price series\u0026rsquo; nonlinearity, non-stationarity, and multifractal characteristics. The method first decomposes price series into IMFs using CEEMDAN, then reconstructs components through multiscale entropy analysis to reduce noise interference. A dual prediction framework combines Random Forest (capturing nonlinear patterns in high-frequency components) and LSTM (modeling long-term dependencies in low-frequency components). Empirical tests on Hubei and EU carbon market data show: (1) The model achieves superior accuracy over benchmarks (CEEMDAN-LSTM/LSTM) across multiple metrics; (2) Maintains high computational efficiency; (3) Demonstrates optimal comprehensive performance. Results verify that entropy-based reconstruction effectively mitigates mode mixing, while RF-LSTM synergy enhances cross-frequency prediction capability, providing methodological support for carbon market risk management.\u003c/p\u003e","manuscriptTitle":"RF-LSTM carbon price prediction based on CEEMDAN decomposition and multiscale entropy reconstruction","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-08 17:36:10","doi":"10.21203/rs.3.rs-7062258/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-09-19T08:01:57+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-18T10:00:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-18T05:46:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"9714977542325961101143292872307598586","date":"2025-09-16T14:07:52+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-09-10T13:13:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"256369403885863802137631320988567616400","date":"2025-09-10T05:57:01+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"37453719285727964778699892365031706486","date":"2025-09-08T11:55:14+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"203050107898361690302068883906597095461","date":"2025-09-08T09:29:45+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"144843639120827938853216665218937908363","date":"2025-09-08T08:30:15+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-03T02:44:05+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-01T12:27:34+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-08-20T09:35:12+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-18T08:32:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-08-18T08:28:20+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":"6390d692-9888-4052-a7e2-3e94c1d03165","owner":[],"postedDate":"September 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":54227566,"name":"Physical sciences/Engineering"},{"id":54227567,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-01-19T16:50:05+00:00","versionOfRecord":{"articleIdentity":"rs-7062258","link":"https://doi.org/10.1038/s41598-026-35085-5","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2026-01-14 16:30:55","publishedOnDateReadable":"January 14th, 2026"},"versionCreatedAt":"2025-09-08 17:36:10","video":"","vorDoi":"10.1038/s41598-026-35085-5","vorDoiUrl":"https://doi.org/10.1038/s41598-026-35085-5","workflowStages":[]},"version":"v1","identity":"rs-7062258","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7062258","identity":"rs-7062258","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}