Comparative forecasting of geomagnetic Storms: Artificial Neural Networks vs. Supervised Machine Learning

Comparative forecasting of geomagnetic Storms: Artificial Neural Networks vs. Supervised Machine Learning | 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 Comparative forecasting of geomagnetic Storms: Artificial Neural Networks vs. Supervised Machine Learning Mostafa Hegy, Amira M. El Nazer, Adnene Laf, Efrem Amanuel Data This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9461478/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 This study presents a forecasting and comparative analysis of moderate geomagnetic storms using artificial neural networks (ANNs). Four moderate geomagnetic storm events that occurred during 2022, in the ascending phase of Solar Cycle 25, are investigated. The primary objective is to identify and model precursors associated with coronal mass ejections (CMEs) to forecast the SYM-H index. A supervised machine learning approach is employed, with ANNs serving as the core predictive model. The model’s performance is evaluated using standard metrics, including mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and the coefficient of determination (R 2 ). To benchmark the efficacy of the proposed method, the ANN-derived forecasts are compared against observed data and the outputs of several alternative algorithms: Decision Tree Regressor, Gradient Boosting Regressor, AdaBoost Regressor, and Linear Regression. The results demonstrate that the ANN model achieves superior predictive accuracy, characterized by low error metrics and a strong correlation with observed values, outperforming the other machine learning models in forecasting the SYM-H index during moderate geomagnetic storms. Geomagnetic storms SYM-H index Coronal mass ejections Artificial neural networks Space weather 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-9461478","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":625682842,"identity":"040425d4-7572-44d6-a3a3-092615862a23","order_by":0,"name":"Mostafa Hegy","email":"data:image/png;base64,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","orcid":"","institution":"National Research Institute of Astronomy and Geophysics","correspondingAuthor":true,"prefix":"","firstName":"Mostafa","middleName":"","lastName":"Hegy","suffix":""},{"id":625682843,"identity":"d7f9fc51-28a3-4ac7-b64a-ee3356a88ed0","order_by":1,"name":"Amira M. El Nazer","email":"","orcid":"","institution":"Mineral Resources and Mining Industries Authority","correspondingAuthor":false,"prefix":"","firstName":"Amira","middleName":"M. El","lastName":"Nazer","suffix":""},{"id":625682844,"identity":"6699eac7-a510-4095-80ff-caba51634e28","order_by":2,"name":"Adnene Laf","email":"","orcid":"","institution":"Sfax University","correspondingAuthor":false,"prefix":"","firstName":"Adnene","middleName":"","lastName":"Laf","suffix":""},{"id":625682845,"identity":"64cabe2f-3084-4d49-92df-db225a018002","order_by":3,"name":"Efrem Amanuel Data","email":"","orcid":"","institution":"Wolaita Sodo University","correspondingAuthor":false,"prefix":"","firstName":"Efrem","middleName":"Amanuel","lastName":"Data","suffix":""}],"badges":[],"createdAt":"2026-04-19 11:08:05","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9461478/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9461478/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107909740,"identity":"12bd7b89-5f98-4778-936e-85b0ca55228b","added_by":"auto","created_at":"2026-04-27 13:11:29","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":599441,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9461478/v1_covered_c2bb47a5-534f-4572-a00b-7772ab133d79.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Comparative forecasting of geomagnetic Storms: Artificial Neural Networks vs. Supervised Machine Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Geomagnetic storms, SYM-H index, Coronal mass ejections, Artificial neural networks, Space weather forecasting","lastPublishedDoi":"10.21203/rs.3.rs-9461478/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9461478/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study presents a forecasting and comparative analysis of moderate geomagnetic storms using artificial neural networks (ANNs). Four moderate geomagnetic storm events that occurred during 2022, in the ascending phase of Solar Cycle 25, are investigated. The primary objective is to identify and model precursors associated with coronal mass ejections (CMEs) to forecast the SYM-H index. A supervised machine learning approach is employed, with ANNs serving as the core predictive model. The model\u0026rsquo;s performance is evaluated using standard metrics, including mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), and the coefficient of determination (R\u003csup\u003e2\u003c/sup\u003e). To benchmark the efficacy of the proposed method, the ANN-derived forecasts are compared against observed data and the outputs of several alternative algorithms: Decision Tree Regressor, Gradient Boosting Regressor, AdaBoost Regressor, and Linear Regression. The results demonstrate that the ANN model achieves superior predictive accuracy, characterized by low error metrics and a strong correlation with observed values, outperforming the other machine learning models in forecasting the SYM-H index during moderate geomagnetic storms.\u003c/p\u003e","manuscriptTitle":"Comparative forecasting of geomagnetic Storms: Artificial Neural Networks vs. Supervised Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 03:49:46","doi":"10.21203/rs.3.rs-9461478/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":"637aa86f-ca7f-4119-be9f-4c36e2652c6f","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-27T13:08:41+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 03:49:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9461478","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9461478","identity":"rs-9461478","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}