Multispectral YOLO: Generic Feature Fusion Framework for Solar Active Region Detection

Multispectral YOLO: Generic Feature Fusion Framework for Solar Active Region Detection | 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 Multispectral YOLO: Generic Feature Fusion Framework for Solar Active Region Detection António Santos, Filipa S. Barros, J. J. G. Lima, Rui F. Pinto, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7600800/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 09 Apr, 2026 Read the published version in Machine Vision and Applications → Version 1 posted 12 You are reading this latest preprint version Abstract Monitoring solar phenomena, such as sunspots and active regions, is crucial for ensuring astronaut safety, telecommunications reliability, and predicting terrestrial events like auroras. Traditional methods for detecting these phenomena have limitations in accuracy and baseline maintenance. This paper presents a novel deep learning object detection method that leverages multispectral image data from satellites to enhance the detection of "sunspots" and active regions. Utilizing images from the SDO satellite and annotations from the DeepSDO dataset, we constructed a new dataset composed of aligned observations from HMI Ic, AIA 211\,\AA, and AIA 335\,\AA. We adapted and developed a stock YOLOv5-based model capable of handling and fusing any number of input images. Two fusion methodologies, early and late fusion, and three different fusion modules --- CatFuse (simple concatenation), CBAMC (CBAM-based module), and TransEnc (transformer encoder) --- were implemented and tested. Our critical evaluation of the models, supported by statistical analysis, proved the developed models to be statistically significantly different among themselves at a p-value of 0.05, and helped us to identify the best-performing model: CatFuse with early fusion, which achieved a [email protected] :0.95 of 0.52 and a [email protected] of 0.94. This result was marginally better than the best baseline (YOLOv5 with a single HMI image) and comparable to other state-of-the-art models, demonstrating a modest but consistent improvement of multispectral image fusion for this task. YOLO Multispectral Active Regions Object Detection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 09 Apr, 2026 Read the published version in Machine Vision and Applications → Version 1 posted Editorial decision: Revision requested 21 Jan, 2026 Reviews received at journal 02 Dec, 2025 Reviews received at journal 29 Nov, 2025 Reviewers agreed at journal 12 Nov, 2025 Reviewers agreed at journal 11 Nov, 2025 Reviewers agreed at journal 11 Nov, 2025 Reviewers agreed at journal 10 Nov, 2025 Reviewers agreed at journal 10 Nov, 2025 Reviewers invited by journal 10 Nov, 2025 Editor assigned by journal 13 Sep, 2025 Submission checks completed at journal 13 Sep, 2025 First submitted to journal 12 Sep, 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-7600800","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":514543340,"identity":"2805d923-d266-4f62-a1a4-0d753a090586","order_by":0,"name":"António Santos","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0UlEQVRIiWNgGAWjYFAC5gMHPhhIyLExMyQ+IFILW+LDGRU2xvzsDY8NQHwewlp4jI15zqQlzuw5+EyCKC0GtxvMJHjbDhsb3EhOq+bdwZBnT1DLnQNpEpJth+UMbqSl3eY9w1BM2JYbCcckDMG25AC1tDEk9hDWktgmkdh2OHHDjfxvxURqSWY2OAD2/oE0ZqK0SN45xviwARLIyZJzz0gU8xwgoIXvdv+Hw3+gUfnh7Q6bPPYGQtZIIHMYGyQSCGnA0MJAhJZRMApGwSgYaQAApJBICL1FTYQAAAAASUVORK5CYII=","orcid":"","institution":"LIACC, Faculdade de Engenharia, Universidade do Porto","correspondingAuthor":true,"prefix":"","firstName":"António","middleName":"","lastName":"Santos","suffix":""},{"id":514543341,"identity":"32c112f9-3d5b-42ec-aa4b-1029a8a6609a","order_by":1,"name":"Filipa S. Barros","email":"","orcid":"","institution":"LIACC, Faculdade de Engenharia, Universidade do Porto","correspondingAuthor":false,"prefix":"","firstName":"Filipa","middleName":"S.","lastName":"Barros","suffix":""},{"id":514543342,"identity":"b2cbcb9d-38d4-44ac-8092-c5ea854e119b","order_by":2,"name":"J. J. G. Lima","email":"","orcid":"","institution":"Instituto de Astrofísica e Ciências do Espaço, CAUP","correspondingAuthor":false,"prefix":"","firstName":"J.","middleName":"J. G.","lastName":"Lima","suffix":""},{"id":514543343,"identity":"0dba0e71-521e-4a4d-b431-adbc259df43f","order_by":3,"name":"Rui F. Pinto","email":"","orcid":"","institution":"Institut de Recherche and Astrophysique et Planétologie, OMP/CNRS, CNES, University of Toulouse","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"F.","lastName":"Pinto","suffix":""},{"id":514543344,"identity":"e395ae26-a27d-4f97-954b-696f1cdc8886","order_by":4,"name":"André Restivo","email":"","orcid":"","institution":"LIACC, Faculdade de Engenharia, Universidade do Porto","correspondingAuthor":false,"prefix":"","firstName":"André","middleName":"","lastName":"Restivo","suffix":""},{"id":514543345,"identity":"a997fea1-b6a3-47c4-bfff-316729f041ed","order_by":5,"name":"Luís F. Teixeira","email":"","orcid":"","institution":"Instituto de Engenharia de Sistemas e Computadores, Tecnologia e Ciência (INESC TEC)","correspondingAuthor":false,"prefix":"","firstName":"Luís","middleName":"F.","lastName":"Teixeira","suffix":""}],"badges":[],"createdAt":"2025-09-12 12:53:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7600800/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7600800/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00138-026-01807-y","type":"published","date":"2026-04-09T15:58:56+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":106810268,"identity":"3d2774c0-0446-47e4-80fc-3601ca10b18c","added_by":"auto","created_at":"2026-04-13 16:15:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1278106,"visible":true,"origin":"","legend":"","description":"","filename":"MultispectralYOLOGenericFeatureFusionFrameworkforSolarActiveRegionDetection.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7600800/v1_covered_b9e65ad0-2c01-4888-8450-0e630dbe793f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multispectral YOLO: Generic Feature Fusion Framework for Solar Active Region Detection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"YOLO, Multispectral, Active Regions, Object Detection","lastPublishedDoi":"10.21203/rs.3.rs-7600800/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7600800/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMonitoring solar phenomena, such as sunspots and active regions, is crucial for ensuring astronaut safety, telecommunications reliability, and predicting terrestrial events like auroras. Traditional methods for detecting these phenomena have limitations in accuracy and baseline maintenance. This paper presents a novel deep learning object detection method that leverages multispectral image data from satellites to enhance the detection of \"sunspots\" and active regions. Utilizing images from the SDO satellite and annotations from the DeepSDO dataset, we constructed a new dataset composed of aligned observations from HMI Ic, AIA 211\\,\\AA, and AIA 335\\,\\AA. We adapted and developed a stock YOLOv5-based model capable of handling and fusing any number of input images. Two fusion methodologies, early and late fusion, and three different fusion modules --- CatFuse (simple concatenation), CBAMC (CBAM-based module), and TransEnc (transformer encoder) --- were implemented and tested. Our critical evaluation of the models, supported by statistical analysis, proved the developed models to be statistically significantly different among themselves at a p-value of 0.05, and helped us to identify the best-performing model: CatFuse with early fusion, which achieved a [email protected]:0.95 of 0.52 and a [email protected] of 0.94. This result was marginally better than the best baseline (YOLOv5 with a single HMI image) and comparable to other state-of-the-art models, demonstrating a modest but consistent improvement of multispectral image fusion for this task.\u003c/p\u003e","manuscriptTitle":"Multispectral YOLO: Generic Feature Fusion Framework for Solar Active Region Detection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-19 06:04:45","doi":"10.21203/rs.3.rs-7600800/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-01-21T18:08:33+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-02T16:30:58+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-11-29T14:22:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"147737714320167927929139630476323176496","date":"2025-11-13T04:29:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"137955518022709138613860395015663539409","date":"2025-11-11T11:04:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"281744199681405465062814904398074517790","date":"2025-11-11T08:28:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"305658259866405106164759266625008506473","date":"2025-11-11T04:13:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"277416074272550569065190061129533021583","date":"2025-11-11T01:34:22+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-10T22:51:35+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-13T10:07:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-13T10:06:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2025-09-12T12:41:55+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d512deca-2751-416a-a103-911f90da3a2c","owner":[],"postedDate":"September 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2026-04-13T16:11:49+00:00","versionOfRecord":{"articleIdentity":"rs-7600800","link":"https://doi.org/10.1007/s00138-026-01807-y","journal":{"identity":"machine-vision-and-applications","isVorOnly":false,"title":"Machine Vision and Applications"},"publishedOn":"2026-04-09 15:58:56","publishedOnDateReadable":"April 9th, 2026"},"versionCreatedAt":"2025-09-19 06:04:45","video":"","vorDoi":"10.1007/s00138-026-01807-y","vorDoiUrl":"https://doi.org/10.1007/s00138-026-01807-y","workflowStages":[]},"version":"v1","identity":"rs-7600800","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7600800","identity":"rs-7600800","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}