{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T09:49:05Z","timestamp":1786441745822,"version":"3.56.0"},"reference-count":34,"publisher":"MDPI AG","issue":"17","license":[{"start":{"date-parts":[[2022,9,3]],"date-time":"2022-09-03T00:00:00Z","timestamp":1662163200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In recent years, neural networks have been increasingly used for classifying aurora images. In particular, convolutional neural networks have been actively studied. However, there are not many studies on the application of deep learning techniques that take into account the characteristics of aurora images. Therefore, in this study, we propose the use of deep metric learning as a suitable method for aurora image classification. Deep metric learning is one of the deep learning techniques. It was developed to distinguish human faces. Identifying human faces is a more difficult task than standard classification tasks because this task is characterized by a small number of sample images for each class and poor feature variation between classes. We thought that the face identification task is similar to aurora image classification in that the number of labeled images is relatively small and the feature differences between classes are small. Therefore, we studied the application of deep metric learning to aurora image classification. As a result, our experiments showed that deep metric learning improves the accuracy of aurora image classification by nearly 10% compared to previous studies.<\/jats:p>","DOI":"10.3390\/s22176666","type":"journal-article","created":{"date-parts":[[2022,9,8]],"date-time":"2022-09-08T04:18:32Z","timestamp":1662610712000},"page":"6666","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Aurora Image Classification with Deep Metric Learning"],"prefix":"10.3390","volume":"22","author":[{"given":"Takeru","family":"Endo","sequence":"first","affiliation":[{"name":"Department of Informatics, The University of Electro-Communications, 1-5-1, Chofugaoka, Chofu-shi, Tokyo 182-8585, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2715-1530","authenticated-orcid":false,"given":"Mitsuharu","family":"Matsumoto","sequence":"additional","affiliation":[{"name":"Department of Informatics, The University of Electro-Communications, 1-5-1, Chofugaoka, Chofu-shi, Tokyo 182-8585, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1109\/LGRS.2011.2163616","article-title":"Numeric image features for detection of aurora","volume":"9","author":"Mikko","year":"2012","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_2","first-page":"5049","article-title":"Auroral sequence representation and classification using hidden Markov models","volume":"12","author":"Qiuju","year":"2012","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","first-page":"10","article-title":"Auroral Image Classification With Deep Neural Networks","volume":"125","author":"Andreas","year":"2020","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_4","unstructured":"Kaiming, H., Xiangyu, Z., Shaoqing, R., and Jian, S. (2016, January 27\u201330). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA."},{"key":"ref_5","unstructured":"Florian, S., Dmitry, K., and James, P. (2015, January 7\u201312). FaceNet: A Unified Embedding for Face Recognition and Clustering. Proceedings of the Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA."},{"key":"ref_6","first-page":"7447","article-title":"Automatic classification of auroral images from the Oslo auroral THEMIS (OATH) data set using machine learning","volume":"9","author":"Lasse","year":"2015","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.5194\/angeo-22-1103-2004","article-title":"Diurnal auroral occurrence statistics obtained via machine vision","volume":"22","author":"Donovan","year":"2004","journal-title":"Ann. Geophys."},{"key":"ref_8","unstructured":"Syrj\u00e4suo, M.T., and Donovan, E.F. (2015, January 16\u201317). Using relevance feedback in retrieving auroral images. Proceedings of the 4th IASTED International Conference on Computational Intelligence, Innsbruck, Austria."},{"key":"ref_9","first-page":"180","article-title":"Aurora images classification via features salient coding","volume":"30","author":"Han","year":"2013","journal-title":"J. Xidian Univ."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2758","DOI":"10.3724\/SP.J.1001.2013.04481","article-title":"Aurora image classification based on LDA combining with saliency information","volume":"24","author":"Han","year":"2013","journal-title":"J. Softw."},{"key":"ref_11","first-page":"67","article-title":"Aurora image search with contextual CNN feature","volume":"3","author":"Xi","year":"2013","journal-title":"Neurocomputing"},{"key":"ref_12","first-page":"7985","article-title":"ASI aurora search: An attempt of intelligent image processing for circular fisheye lens","volume":"1","author":"Xi","year":"2018","journal-title":"Opt. Express"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e2019JA027590","DOI":"10.1029\/2019JA027590","article-title":"Automatic Aurora Image Classification Framework Based on Deep Learning for Occurrence Distribution Analysis: A Case Study of All-Sky Image Data Sets From the Yellow River Station","volume":"125","author":"Yanfei","year":"2020","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_15","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7133","DOI":"10.1109\/TGRS.2018.2848725","article-title":"Weakly supervised semantic segmentation for joint key local structure localization and classification of aurora image","volume":"56","author":"Chuang","year":"2018","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_17","first-page":"523","article-title":"Representation and Classification of Auroral Images Based on Convolutional Neural Network","volume":"13","author":"Qiuju","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1941","DOI":"10.1109\/LGRS.2020.3012620","article-title":"Extension of Image Data Using Generative Adversarial Networks and Application to Identification of Aurora","volume":"18","author":"Aoi","year":"2021","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"ref_19","first-page":"e2021JA029683","article-title":"Transfer Learning Aurora Image Classification and Magnetic Disturbance Evaluation","volume":"127","author":"Pascal","year":"2021","journal-title":"J. Geophys. Res. Space Phys."},{"key":"ref_20","first-page":"1","article-title":"Auroral Image Classification With Very Limited Labeled Data Using Few-Shot Learning","volume":"19","author":"Qiuju","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"44111","DOI":"10.1109\/ACCESS.2020.2978090","article-title":"Cloud shape classification system based on multi-channel cnn and improved fdm","volume":"8","author":"Mengyang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"123649","DOI":"10.1109\/ACCESS.2020.3005687","article-title":"Deep Facial Diagnosis: Deep Transfer Learning From Face Recognition to Facial Diagnosis","volume":"8","author":"Bo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_23","unstructured":"Suriya, G., Blake, W., Srinadh, B., Behnam, N., and Nathan, S. (2017). Implicit Regularization in Matrix Factorization. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"15844","DOI":"10.1109\/ACCESS.2018.2810849","article-title":"Improvement of Generalization Ability of Deep CNN via Implicit Regularization in Two-Stage Training Process","volume":"6","author":"Qinghe","year":"2018","journal-title":"IEEE Access"},{"key":"ref_25","unstructured":"Elad, H., and Nir, A. (2014). Deep metric learning using Triplet network. arXiv."},{"key":"ref_26","first-page":"1857","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume":"29","author":"Sohn","year":"2016","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Wang, X., Han, X., Huang, W., Dong, D., and Scott, M.R. (2019, January 15\u201320). Multi-similarity loss with general pair weighting for deep metric learning. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00516"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Liu, W., Wen, Y., Yu, Z., Li, M., Raj, B., and Song, L. (2017, January 21\u201326). Sphereface: Deep hypersphere embedding for face recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.713"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, Y., Zhou, Z., Ji, X., Gong, D., Zhou, J., Li, Z., and Liu, W. (2018, January 18\u201323). Cosface: Large margin cosine loss for deep face recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00552"},{"key":"ref_30","unstructured":"Jiankang, D., Jia, G., Niannan, X., and Stefanos, Z. (2018). ArcFace: Additive Angular Margin Loss for Deep Face Recognition. arXiv."},{"key":"ref_31","unstructured":"(2022, August 26). Scikit-Learn. Available online: https:\/\/scikit-learn.org\/stable\/."},{"key":"ref_32","unstructured":"(2022, February 03). Pytorch-Metric-Learning. Available online: https:\/\/github.com\/KevinMusgrave\/pytorch-metric-learning."},{"key":"ref_33","unstructured":"Tan, M., and Le, Q. (2019, January 10\u201315). Efficientnet: Rethinking model scaling for convolutional neural networks. Proceedings of the International Conference on Machine Learning, Long Beach, CA, USA."},{"key":"ref_34","unstructured":"Alexey, D., Lucas, B., Alexander, K., Dirk, W., Xiaohua, Z., Thomas, U., Mostafa, D., Matthias, M., Georg, H., and Sylvain, G. (2020). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6666\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:22:50Z","timestamp":1760142170000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/17\/6666"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,3]]},"references-count":34,"journal-issue":{"issue":"17","published-online":{"date-parts":[[2022,9]]}},"alternative-id":["s22176666"],"URL":"https:\/\/doi.org\/10.3390\/s22176666","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,3]]}}}