Prediction of Yearly Mean Sunspot Number using Machine Learning Methods

Prediction of Yearly Mean Sunspot Number using Machine Learning Methods | 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 Prediction of Yearly Mean Sunspot Number using Machine Learning Methods Nikolaos Paraskakis, Dionissios T. Hristopulos This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4719185/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Jun, 2025 Read the published version in Stochastic Environmental Research and Risk Assessment → Version 1 posted 7 You are reading this latest preprint version Abstract The number of sunspots is an important indicator of solar activity, which has an impact on space weather and the Earth’s climate. Hence, sunspot number prediction is an integral part of solar cycle monitoring for the National Aeronautics and Space Administration, the European Space Agency and other space and environmental agencies. The advent of novel machine learning tools creates new opportunities for modeling and prediction of time series datasets. This paper compares predictions of the yearly sunspot number with three different machine learning methods in terms of prediction performance, computational speed, and interpretability. The methods explored involve a stochastic approach (Gaussian process regression), a method based on decision trees (Light gradient boosting machine), and a long-short-term memory neural network. The relative strengths and weaknesses of each method are discussed. Gaussian process regression Light gradient boosting machine Long short-term memory neural network Solar cycle Sunspots Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 07 Jun, 2025 Read the published version in Stochastic Environmental Research and Risk Assessment → Version 1 posted Editorial decision: Revision requested 01 Oct, 2024 Reviews received at journal 30 Sep, 2024 Reviewers agreed at journal 22 Aug, 2024 Reviewers invited by journal 15 Jul, 2024 Editor assigned by journal 12 Jul, 2024 Submission checks completed at journal 11 Jul, 2024 First submitted to journal 10 Jul, 2024 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-4719185","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":329591762,"identity":"43b70359-727d-4315-925a-741cf774fee4","order_by":0,"name":"Nikolaos Paraskakis","email":"","orcid":"","institution":"Technical University of Crete","correspondingAuthor":false,"prefix":"","firstName":"Nikolaos","middleName":"","lastName":"Paraskakis","suffix":""},{"id":329591763,"identity":"3f8de46d-ac5c-474a-aeec-a0c7f12c2d19","order_by":1,"name":"Dionissios T. Hristopulos","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIie3RsQrCMBCA4SuFutS62qXPcNJBBPFZWgpORRydpCBk6gPoW+gbRAp2iboWXOrsUjeHDEaqFJc0o2D+6ZYP7hIAne4XozZAUI8GBRgrE6xngGlfjUBDsnbi5MdDVXLuDTsp0oqfl5hT87aQEJfNonVI0B+lDPcbcukjC6wRkxAsbB/CBMNtEWPWTQQpwBokbSTgb2LzkyqxPsSiL2JeZcRlsViM+OKWw1zcErkbFhJDRpyc+caDe+LFVruy4pOek2fZXUaaDZvRIAr/+U3ArJSITqfT/UtPgjJTsQhG14oAAAAASUVORK5CYII=","orcid":"","institution":"Technical University of Crete","correspondingAuthor":true,"prefix":"","firstName":"Dionissios","middleName":"T.","lastName":"Hristopulos","suffix":""}],"badges":[],"createdAt":"2024-07-10 16:10:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4719185/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4719185/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00477-025-03024-x","type":"published","date":"2025-06-07T15:57:37+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":84242728,"identity":"9315b96c-9217-4fe0-89db-ece301cb7681","added_by":"auto","created_at":"2025-06-09 16:11:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":14943926,"visible":true,"origin":"","legend":"","description":"","filename":"SERRASunspots.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4719185/v1_covered_3b086588-1aca-4e81-a4d4-0f3c99b3a7b1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Prediction of Yearly Mean Sunspot Number using Machine Learning Methods","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":"stochastic-environmental-research-and-risk-assessment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"serr","sideBox":"Learn more about [Stochastic Environmental Research and Risk Assessment](https://www.springer.com/journal/477)","snPcode":"477","submissionUrl":"https://submission.nature.com/new-submission/477/3","title":"Stochastic Environmental Research and Risk Assessment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Gaussian process regression, Light gradient boosting machine, Long short-term memory neural network, Solar cycle, Sunspots","lastPublishedDoi":"10.21203/rs.3.rs-4719185/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4719185/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The number of sunspots is an important indicator of solar activity, which has an impact on space weather and the Earth’s climate. Hence, sunspot number prediction is an integral part of solar cycle monitoring for the National Aeronautics and Space Administration, the European Space Agency and other space and environmental agencies. The advent of novel machine learning tools creates new opportunities for modeling and prediction of time series datasets. This paper compares predictions of the yearly sunspot number with three different machine learning methods in terms of prediction performance, computational speed, and interpretability. The methods explored involve a stochastic approach (Gaussian process regression), a method based on decision trees (Light gradient boosting machine), and a long-short-term memory neural network. The relative strengths and weaknesses of each method are discussed.","manuscriptTitle":"Prediction of Yearly Mean Sunspot Number using Machine Learning Methods","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-06 05:45:42","doi":"10.21203/rs.3.rs-4719185/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-10-01T12:04:58+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-10-01T03:55:30+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"120315018739008333956695378878536030028","date":"2024-08-22T16:10:46+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-07-15T20:19:28+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-12T11:05:09+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-11T14:00:12+00:00","index":"","fulltext":""},{"type":"submitted","content":"Stochastic Environmental Research and Risk Assessment","date":"2024-07-10T16:07:29+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"stochastic-environmental-research-and-risk-assessment","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"serr","sideBox":"Learn more about [Stochastic Environmental Research and Risk Assessment](https://www.springer.com/journal/477)","snPcode":"477","submissionUrl":"https://submission.nature.com/new-submission/477/3","title":"Stochastic Environmental Research and Risk Assessment","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"4542e52f-3daf-4ddc-ade2-db687cad605b","owner":[],"postedDate":"August 6th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2025-06-09T16:07:15+00:00","versionOfRecord":{"articleIdentity":"rs-4719185","link":"https://doi.org/10.1007/s00477-025-03024-x","journal":{"identity":"stochastic-environmental-research-and-risk-assessment","isVorOnly":false,"title":"Stochastic Environmental Research and Risk Assessment"},"publishedOn":"2025-06-07 15:57:37","publishedOnDateReadable":"June 7th, 2025"},"versionCreatedAt":"2024-08-06 05:45:42","video":"","vorDoi":"10.1007/s00477-025-03024-x","vorDoiUrl":"https://doi.org/10.1007/s00477-025-03024-x","workflowStages":[]},"version":"v1","identity":"rs-4719185","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4719185","identity":"rs-4719185","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}