SolARED: Solar Active Region Emergence Dataset for Machine Learning Aided Predictions

SolARED: Solar Active Region Emergence Dataset for Machine Learning Aided Predictions | 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 SolARED: Solar Active Region Emergence Dataset for Machine Learning Aided Predictions Spiridon Kasapis, Eren Dogan, Irina Kitiashvili, Alexander Kosovichev, and 5 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8508121/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract The development of accurate forecasts of solar eruptive activity has become increasingly important for preventing potential impacts on space technologies and exploration. Therefore, it is crucial to detect Active Regions (ARs) before they start forming on the solar surface. This will enable the development of early-warning capabilities for upcoming space weather disturbances. For this reason, we prepared the Solar Active Region Emergence Dataset (SolARED). The dataset is derived from full-disk maps of the Doppler velocity, magnetic field, and continuum intensity, obtained by the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO). SolARED includes 1D averaged data that characterize the evolution of acoustic power of solar oscillations, unsigned magnetic flux, and continuum intensity for 50 large ARs before, during, and after their emergence on the solar surface, as well as surrounding areas observed on the solar disc between 2010 and 2023. The resulting ML-ready SolARED dataset is designed to support enhancements of predictive capabilities, enabling the development of operational forecasts for the emergence of active regions. The SolARED dataset is available at https://sun.njit.edu/sarportal/ , through an interactive visualization web application. Active Regions Magnetic Fields Photosphere Machine Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 17 Feb, 2026 Reviews received at journal 13 Feb, 2026 Reviewers agreed at journal 22 Jan, 2026 Reviewers invited by journal 20 Jan, 2026 Editor assigned by journal 05 Jan, 2026 Submission checks completed at journal 05 Jan, 2026 First submitted to journal 03 Jan, 2026 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-8508121","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":577429036,"identity":"4009863c-bd81-4b5b-9c29-07e1969ea425","order_by":0,"name":"Spiridon Kasapis","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYDACHjApwcAPJA+giRLQItkA0SJBrBYGBgOoFYS1yPccfvzh5w4Le+PbvQ8PF9TY1PFLNzA+eNuGW4vB2TYzyd4zEonb7hw3ODzjWJqE5JwDzIZz8WnhZzBj4G2TSDC7kcZwmLfhsITBjQQ2aV48WuT72T9//NsmYW88A6zlP0gL+298WhjO9hgAzZRg3CAB1nIAbAszPi0GZ86UScsC/TLjzjGGwzzHkiVnzkhslpxzDo/DetI3f3y7o86ef3Yb82eeGjt+fonkgx/elOFxGAgwNjDAIgTOJU3LKBgFo2AUjAJUAABYSE+TOBWLCwAAAABJRU5ErkJggg==","orcid":"","institution":"Princeton University","correspondingAuthor":true,"prefix":"","firstName":"Spiridon","middleName":"","lastName":"Kasapis","suffix":""},{"id":577429037,"identity":"643b6514-7cef-4c18-8183-870f6859dda0","order_by":1,"name":"Eren Dogan","email":"","orcid":"","institution":"New Jersey Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Eren","middleName":"","lastName":"Dogan","suffix":""},{"id":577429038,"identity":"74b374a1-5b29-4e96-a534-e47e3d63ead4","order_by":2,"name":"Irina Kitiashvili","email":"","orcid":"","institution":"Ames Research Center","correspondingAuthor":false,"prefix":"","firstName":"Irina","middleName":"","lastName":"Kitiashvili","suffix":""},{"id":577429039,"identity":"8adbb5f6-300b-4450-a617-21ebfab531c1","order_by":3,"name":"Alexander Kosovichev","email":"","orcid":"","institution":"New Jersey Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Alexander","middleName":"","lastName":"Kosovichev","suffix":""},{"id":577429041,"identity":"5d696853-0234-48cd-9ce2-066970beffb3","order_by":4,"name":"John Stefan","email":"","orcid":"","institution":"New Jersey Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"John","middleName":"","lastName":"Stefan","suffix":""},{"id":577429043,"identity":"0f7e4804-6227-4375-ad97-7c2a009501dd","order_by":5,"name":"Jake Butler","email":"","orcid":"","institution":"Ames Research Center","correspondingAuthor":false,"prefix":"","firstName":"Jake","middleName":"","lastName":"Butler","suffix":""},{"id":577429045,"identity":"d374e660-c259-4d87-9b26-67b787df67b0","order_by":6,"name":"Jonas Tirona","email":"","orcid":"","institution":"New Jersey Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Jonas","middleName":"","lastName":"Tirona","suffix":""},{"id":577429047,"identity":"21fe59f4-6441-4d05-8f39-9836462f95c5","order_by":7,"name":"Sarang Patil","email":"","orcid":"","institution":"New Jersey Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Sarang","middleName":"","lastName":"Patil","suffix":""},{"id":577429049,"identity":"0c86b042-b4e2-43cb-a9f8-c006a6613016","order_by":8,"name":"Mengjia Xu","email":"","orcid":"","institution":"New Jersey Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Mengjia","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2026-01-03 16:23:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8508121/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8508121/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100843495,"identity":"bd0dd175-fd48-4a36-8444-4ca246529160","added_by":"auto","created_at":"2026-01-22 03:25:54","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9752,"visible":true,"origin":"","legend":"","description":"","filename":"20b387b5e9cc4924a5fbeededc77e341.json","url":"https://assets-eu.researchsquare.com/files/rs-8508121/v1/95d0bcc86bb67ae3aa20e0dd.json"},{"id":100859286,"identity":"cca3179f-3691-43ef-bfbb-03ace4e67121","added_by":"auto","created_at":"2026-01-22 07:26:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3627563,"visible":true,"origin":"","legend":"","description":"","filename":"SolAREDPaperSolarPhysicsJournal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8508121/v1_covered_b5893931-f59c-4081-81d0-6b78a5d2973b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SolARED: Solar Active Region Emergence Dataset for Machine Learning Aided Predictions","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"solar-physics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sola","sideBox":"Learn more about [Solar Physics](http://link.springer.com/journal/11207)","snPcode":"11207","submissionUrl":"https://submission.nature.com/new-submission/11207/3","title":"Solar Physics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Active Regions, Magnetic Fields, Photosphere, Machine Learning","lastPublishedDoi":"10.21203/rs.3.rs-8508121/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8508121/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The development of accurate forecasts of solar eruptive activity has become increasingly important for preventing potential impacts on space technologies and exploration. Therefore, it is crucial to detect Active Regions (ARs) before they start forming on the solar surface. This will enable the development of early-warning capabilities for upcoming space weather disturbances. For this reason, we prepared the Solar Active Region Emergence Dataset (SolARED). The dataset is derived from full-disk maps of the Doppler velocity, magnetic field, and continuum intensity, obtained by the Helioseismic and Magnetic Imager (HMI) onboard the Solar Dynamics Observatory (SDO). SolARED includes 1D averaged data that characterize the evolution of acoustic power of solar oscillations, unsigned magnetic flux, and continuum intensity for 50 large ARs before, during, and after their emergence on the solar surface, as well as surrounding areas observed on the solar disc between 2010 and 2023. The resulting ML-ready SolARED dataset is designed to support enhancements of predictive capabilities, enabling the development of operational forecasts for the emergence of active regions. The SolARED dataset is available at https://sun.njit.edu/sarportal/, through an interactive visualization web application.","manuscriptTitle":"SolARED: Solar Active Region Emergence Dataset for Machine Learning Aided Predictions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-22 03:25:49","doi":"10.21203/rs.3.rs-8508121/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-17T16:26:45+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-13T22:46:26+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"248784946199399873835854883717639201979","date":"2026-01-22T19:21:49+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-01-20T11:08:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-06T02:47:54+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-06T02:46:22+00:00","index":"","fulltext":""},{"type":"submitted","content":"Solar Physics","date":"2026-01-03T16:21:37+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"solar-physics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sola","sideBox":"Learn more about [Solar Physics](http://link.springer.com/journal/11207)","snPcode":"11207","submissionUrl":"https://submission.nature.com/new-submission/11207/3","title":"Solar Physics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"6c902088-a4a5-45cb-b974-0bb1e065f7e1","owner":[],"postedDate":"January 22nd, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T02:53:37+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-22 03:25:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8508121","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8508121","identity":"rs-8508121","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}