{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T03:19:49Z","timestamp":1775704789240,"version":"3.50.1"},"reference-count":21,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100006752","name":"Universidade do Porto","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100006752","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    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\u00a0\u00c5, and AIA 335\u00a0\u00c5. 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\u2014CatFuse (simple concatenation), CBAMC (CBAM-based module), and TransEnc (transformer encoder)\u2014were implemented and tested. Statistically analysing the results via the Friedman test (\n                    <jats:italic>p<\/jats:italic>\n                    =0.05) revealed significant performance differences among the evaluated models, which were confirmed through pairwise Wilcoxon post-hoc tests. From the approaches tested, CatFuse with early fusion achieved significantly higher detection performance than the other models, with a mAP@0.5:0.95 of 0.52 and a mAP@0.5 of 0.94, an improvement of\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\Delta $$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    =0.02\u20130.36 for mAP@0.5:0.95 and\n                    <jats:inline-formula>\n                      <jats:tex-math>$$\\Delta $$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    =0.02\u20130.28 for mAP@0.5, depending on the baseline model. 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.\n                  <\/jats:p>","DOI":"10.1007\/s00138-026-01807-y","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T02:19:28Z","timestamp":1775701168000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multispectral YOLO: generic feature fusion framework for solar active region detection"],"prefix":"10.1007","volume":"37","author":[{"given":"Ant\u00f3nio","family":"Santos","sequence":"first","affiliation":[]},{"given":"Filipa S.","family":"Barros","sequence":"additional","affiliation":[]},{"given":"J. J. G.","family":"Lima","sequence":"additional","affiliation":[]},{"given":"Rui F.","family":"Pinto","sequence":"additional","affiliation":[]},{"given":"Andr\u00e9","family":"Restivo","sequence":"additional","affiliation":[]},{"given":"Lu\u00eds F.","family":"Teixeira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,9]]},"reference":[{"issue":"8","key":"1807_CR1","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/s11214-023-01006-5","volume":"219","author":"MA Weber","year":"2023","unstructured":"Weber, M.A., Schunker, H., Jouve, L., I\u015f\u0131k, E.: Understanding active region origins and emergence on the sun and other cool stars. Space Sci. Rev. 219(8), 63 (2023)","journal-title":"Space Sci. Rev."},{"key":"1807_CR2","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1007\/s11207-004-1105-z","volume":"223","author":"PC Liewer","year":"2004","unstructured":"Liewer, P.C., Neugebauer, M., Zurbuchen, T.: Characteristics of active-region sources of solar wind near solar maximum. Sol. Phys. 223, 209\u2013229 (2004)","journal-title":"Sol. Phys."},{"issue":"2","key":"1807_CR3","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.1007\/s11227-020-03325-8","volume":"77","author":"MA Talib","year":"2021","unstructured":"Talib, M.A., Majzoub, S., Nasir, Q., Jamal, D.: A systematic literature review on hardware implementation of artificial intelligence algorithms. J. Supercomput. 77(2), 1897\u20131938 (2021)","journal-title":"J. Supercomput."},{"key":"1807_CR4","doi-asserted-by":"publisher","first-page":"387","DOI":"10.7494\/csci.2019.20.4.3163","volume":"20","author":"A Gupta","year":"2019","unstructured":"Gupta, A.: Current research opportunities for image processing and computer vision. Comput. Sci. 20, 387\u2013410 (2019)","journal-title":"Comput. Sci."},{"key":"1807_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.ascom.2020.100385","volume":"32","author":"S Carvalho","year":"2020","unstructured":"Carvalho, S., Gomes, S., Barata, T., Louren\u00e7o, A., Peixinho, N.: Comparison of automatic methods to detect sunspots in the coimbra observatory spectroheliograms. Astron. Comput. 32, 100385 (2020)","journal-title":"Astron. Comput."},{"issue":"10","key":"1807_CR6","doi-asserted-by":"publisher","first-page":"5833","DOI":"10.3390\/app13105833","volume":"13","author":"J Santos","year":"2023","unstructured":"Santos, J., Peixinho, N., Barata, T., Pereira, C., Coimbra, A.P., Cris\u00f3stomo, M.M., Mendes, M.: Sunspot detection using yolov5 in spectroheliograph h-alpha images. Appl. Sci. 13(10), 5833 (2023)","journal-title":"Appl. Sci."},{"key":"1807_CR7","doi-asserted-by":"crossref","unstructured":"Abd, M.A., Majed, S.F., Zharkova, V.: Automated classification of sunspot groups with support vector machines. In: Technological Developments in Networking, Education and Automation, pp. 321\u2013325 (2010). Springer","DOI":"10.1007\/978-90-481-9151-2_56"},{"issue":"3","key":"1807_CR8","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1007\/s42979-022-01088-y","volume":"3","author":"M Almahasneh","year":"2022","unstructured":"Almahasneh, M., Paiement, A., Xie, X., Aboudarham, J.: Msmt-cnn for solar active region detection with multi-spectral analysis. SN Comput. Sci. 3(3), 197 (2022)","journal-title":"SN Comput. Sci."},{"issue":"8","key":"1807_CR9","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/s11207-024-02362-3","volume":"299","author":"L Gong","year":"2024","unstructured":"Gong, L., Yang, Y., Feng, S., Dai, W., Liang, B., Xiong, J.: Solar active regions detection and tracking based on deep learning. Sol. Phys. 299(8), 121 (2024)","journal-title":"Sol. Phys."},{"key":"1807_CR10","unstructured":"Inc, U.: Ultralytics. https:\/\/www.ultralytics.com\/ Accessed 2025-06-30"},{"key":"1807_CR11","unstructured":"Jocher, G., Stoken, A., Borovec, J., Changyu, L., Hogan, A., Diaconu, L., Ingham, F., Poznanski, J., Fang, J., Yu, L., et al.: ultralytics\/yolov5: v3. 1-bug fixes and performance improvements. Zenodo (2020)"},{"key":"1807_CR12","doi-asserted-by":"crossref","unstructured":"Gallagher, J.E., Oughton, E.J.: Surveying you only look once (yolo) multispectral object detection advancements, applications and challenges. IEEE Access. 13, 7366\u20137395 (2025)","DOI":"10.1109\/ACCESS.2025.3526458"},{"issue":"11","key":"1807_CR13","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1007\/s11207-021-01902-5","volume":"296","author":"J-H Baek","year":"2021","unstructured":"Baek, J.-H., Kim, S., Choi, S., Park, J., Kim, J., Jo, W., Kim, D.: Solar event detection using deep-learning-based object detection methods. Sol. Phys. 296(11), 160 (2021)","journal-title":"Sol. Phys."},{"key":"1807_CR14","unstructured":"Dem\u0161ar, J.: Statistical comparisons of classifiers over multiple data sets. J. Mach. Learn. Res. 7, 1\u201330 (2006)"},{"issue":"6","key":"1807_CR15","doi-asserted-by":"publisher","first-page":"80","DOI":"10.2307\/3001968","volume":"1","author":"F Wilcoxon","year":"1945","unstructured":"Wilcoxon, F.: Individual comparisons by ranking methods. Biometrics Bulletin 1(6), 80\u201383 (1945). https:\/\/doi.org\/10.2307\/3001968","journal-title":"Biometrics Bulletin"},{"issue":"1","key":"1807_CR16","doi-asserted-by":"publisher","first-page":"68","DOI":"10.3847\/1538-4357\/ab4f7a","volume":"890","author":"WT Barnes","year":"2020","unstructured":"Barnes, W.T., Bobra, M.G., Christe, S.D., Freij, N., Hayes, L.A., Ireland, J., Mumford, S., Perez-Suarez, D., Ryan, D.F., Shih, A.Y., et al.: The sunpy project: open source development and status of the version 1.0 core package. Astrophys. J. 890(1), 68 (2020)","journal-title":"Astrophys. J."},{"issue":"40","key":"1807_CR17","doi-asserted-by":"publisher","first-page":"1614","DOI":"10.21105\/joss.01614","volume":"4","author":"K Glogowski","year":"2019","unstructured":"Glogowski, K., Bobra, M.G., Choudhary, N., Amezcua, A.B., Mumford, S.J.: drms: a python package for accessing hmi and aia data. J. open source softw. 4(40), 1614 (2019)","journal-title":"J. open source softw."},{"key":"1807_CR18","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham, M., Van Gool, L., Williams, C.K., Winn, J., Zisserman, A.: The pascal visual object classes (voc) challenge. Int. J. Comput. Vision 88, 303\u2013338 (2010)","journal-title":"Int. J. Comput. Vision"},{"key":"1807_CR19","doi-asserted-by":"crossref","unstructured":"Palladino, L., Ntagiou, E., Klug, J., Palacios, J., Keil, R.: Sunspot groups detection and classification on sdo\/hmi images using deep learning techniques. In: 2022 IEEE Aerospace Conference (AERO), pp. 1\u201310 (2022). IEEE","DOI":"10.1109\/AERO53065.2022.9843222"},{"key":"1807_CR20","doi-asserted-by":"crossref","unstructured":"Kucuk, A., Aydin, B., Angryk, R.: Multi-wavelength solar event detection using faster r-cnn. In: 2017 IEEE International Conference on Big Data (Big Data), pp. 2552\u20132558 (2017). IEEE","DOI":"10.1109\/BigData.2017.8258214"},{"issue":"1","key":"1807_CR21","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1145\/3689037","volume":"57","author":"C Banerjee","year":"2024","unstructured":"Banerjee, C., Nguyen, K., Fookes, C., George, K.: Physics-informed computer vision: a review and perspectives. ACM Comput. Surv. 57(1), 17\u201311738 (2024). https:\/\/doi.org\/10.1145\/3689037","journal-title":"ACM Comput. Surv."}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01807-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00138-026-01807-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-026-01807-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T02:19:32Z","timestamp":1775701172000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00138-026-01807-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,9]]},"references-count":21,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["1807"],"URL":"https:\/\/doi.org\/10.1007\/s00138-026-01807-y","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,9]]},"assertion":[{"value":"12 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 April 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"54"}}