An Approach to Automatic Classification of Auroras Based on All-Sky Cameras Observation Data

Cover Page

Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription Access

Abstract

An original approach to automatic classification of auroras by machine identification of images received from sky photo recorders, also known as all-sky imagers, is proposed. The total of 163899 sky images taken at 10-minute intervals within the auroral oval (Kola Peninsula, Russia) were selected over a 10-year period. We propose an intelligent information system designed to classify each acquired image into one of seven predefined categories. Analysis of the quality metrics of the system built on the basis on the ResNet50 neural network architecture showed the accuracy of the classification at the level of 96 %, which is practically unachievable when manually processing data samples of such a volume. The result of automatic classification of sky images based on the proposed system is available at the link: (https://disk.yandex.ru/i/76OMyWR4YyVYuw).

About the authors

A. V. Vorobev

Geophysical Center of the RAS; Ufa University of Science and Technology

Author for correspondence.
Email: geomagnet@list.ru
Moscow, Russia; Ufa, Russia

A. N. Lapin

Ufa University of Science and Technology

Email: meccos160@yandex.ru
Ufa, Russia

G. R. Vorobeva

Ufa University of Science and Technology

Email: gulnara.vorobeva@gmail.com
Ufa, Russia

References

  1. Воробьев А.В., Лапин А.Н., Воробьева Г.Р. Программное обеспечение для автоматизированного распознавания и оцифровки архивных данных оптических наблюдений полярных сияний // Информатика и автоматизация. Т. 22. № 5. С. 1177−1206. 2023. https://doi.org/10.15622/ia.22.5.8
  2. Селиванов В.Н., Аксенович Т.В., Билин В.А., Колобов В.В., Сахаров Я.А. База данных геоиндуцированных токов в магистральной электрической сети “Северный транзит” // Солнечно-земная физика. Т. 9. № 3. С. 100–110. 2023. https://doi.org/10.12737/szf-93202311
  3. Clausen L.B.N., Nickisch H. Automatic classification of auroral images from the Oslo Auroral THEMIS (OATH) data set using machine learning // J. Geophys. Res − Space. V. 123. № 7. P. 5640−5647. 2018. https://doi.org/10.1029/2018JA025274
  4. Deng J., Dong W., Socher R., Li L.-J., Li K. Fei-Fei L. ImageNet: A large-scale hierarchical image database / Proc. IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 20−25, 2009. Miami, FL. P. 248−255. 2009. https://doi.org/10.1109/CVPR.2009.5206848
  5. De Diego I.M., Redondo A.R., Fernández R.R., Navarro J., Moguerza J.M. General performance score for classification problems // Appl. Intell. V. 52. № 10. P. 12049−12063. 2022. https://doi.org/10.1007/s10489-021-03041-7
  6. Endo T., Matsumoto M. Aurora image classification with deep metric learning // Sensors. V. 22. № 17. ID 6666. 2022. https://doi.org/10.3390/s22176666
  7. Gallardo-Lacourt B., Nishimura Y., Donovan E., Gillies D.M., Perry G.W., Archer W.E., Nava O.A., Spanswick E.L. A statistical analysis of STEVE // J. Geophys. Res. − Space. V. 123. № 11. P. 9893−9905. 2018. https://doi.org/10.1029/2018JA025368
  8. Glorot X., Bengio Y. Understanding the difficulty of training deep feedforward neural networks / Proc. Thirteenth International Conference on Artificial Intelligence and Statistics. May 13–15, 2010. Sardinia, Italy. Proceedings of Machine Learning Research. V. 9. P. 249−256. 2010.
  9. He K., Zhang X., Ren S., Sun J. Deep residual learning for image recognition / Proc. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). June 26 – July 1, 2016. Las Vegas. V. P. 770−778. 2016. https://doi.org/10.1109/CVPR.2016.90
  10. Kvammen A., Wickstrøm K., McKay D., Partamies N. Auroral image classification with deep neural networks // J. Geophys. Res. − Space. V. 125. № 10. ID e2020JA027808. 2020. https://doi.org/10.1029/2020JA027808
  11. Lian J., Liu T., Zhou Y. Aurora classification in all-sky images via CNN–transformer // Universe. V. 9. № 5. ID 230. 2023. https://doi.org/10.3390/universe9050230
  12. MacDonald E.A., Donovan E., Nishimura Y. et al. New science in plain sight: Citizen scientists lead to the discovery of optical structure in the upper atmosphere // Science Advances. V. 4. № 3. ID eaaq0030. 2018. https://doi.org/10.1126/sciadv.aaq0030
  13. Nanjo S., Nozawa S., Yamamoto M., Kawabata T., Johnsen M.G., Tsuda T.T., Hosokawa K. An automated auroral detection system using deep learning: real-time operation in Tromsø, Norway // Scientific Reports. V. 12. ID 8038. 2022. https://doi.org/10.1038/s41598-022-11686-8
  14. Pilipenko V.A., Chernikov A.A., Soloviev A.A., Yagova N.V., Sakharov Y.A., Kudin D.V., Kostarev D.V., Kozyreva O.V., Vorobev A.V., Belov A.V. Influence of space weather on the reliability of the transport system functioning at high latitudes // Russian Journal of Earth Sciences. V. 23. № 2. P. 1−34. 2023. https://doi.org/10.2205/2023ES000824
  15. Sado P., Clausen L.B.N., Miloch W.J., Nickisch H. Transfer learning aurora image classification and magnetic disturbance evaluation // J. Geophys. Res. − Space. V. 127. № 1. ID e2021JA029683. 2022. https://doi.org/10.1029/2021JA029683
  16. Shorten C., Khoshgoftaar T.M. A survey on image data augmentation for deep learning // Journal of Big Data. V. 6. ID 60. 2019. https://doi.org/10.1186/s40537-019-0197-0
  17. Steven R., Barnes M., Garnett S.T., Garrard G., O’Connor J., Oliver J.L., Robinson C., Tulloch A., Fuller R.A. Aligning citizen science with best practice: Threatened species conservation in Australia // Conservation Science and Practice. V. 1. № 10. ID e100. 2019. https://doi.org/10.1111/csp2.100
  18. Vorobev A.V., Lapin A.N., Soloviev A.A., Vorobeva G.R. An approach to interpreting space weather natural indicators to evaluate the impact of space weather on high-latitude power systems // Izv. Phys. Solid Eart. V. 60. № 4. P. 604−611. 2024. https://doi.org/10.1134/S106935132470054X
  19. Vorobev A.V., Soloviev A.A., Pilipenko V.A., Vorobeva G.R., Gainetdinova A.A., Lapin A.N., Belahovskiy V.B., Roldugin A.V. Local diagnostics of aurora presence based on intelligent analysis of geomagnetic data // Solar-Terrestrial Physics. V. 9. № 2. P. 22−30. 2023. https://doi.org/10.12737/stp-92202303
  20. Vorobev A., Soloviev, A., Pilipenko V., Vorobeva G., Sakharov Y. An approach to diagnostics of geomagnetically induced currents based on ground magnetometers data // Applied Sciences. V. 12. № 3. ID 1522. 2022. https://doi.org/10.3390/app12031522
  21. Yarotsky D. Error bounds for approximations with deep ReLU networks // Neural Networks. V. 94. P. 103−114. 2017. https://doi.org/10.1016/j.neunet.2017.07.002
  22. Zhong Y., Huang R., Zhao J., Zhao B., Liu T. Aurora image classification based on multi-feature latent Dirichlet allocation // Remote Sensing. V. 10. № 2. ID 233. 2018. https://doi.org/10.3390/rs10020233

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) 2025 Russian Academy of Sciences

Согласие на обработку персональных данных

 

Используя сайт https://journals.rcsi.science, я (далее – «Пользователь» или «Субъект персональных данных») даю согласие на обработку персональных данных на этом сайте (текст Согласия) и на обработку персональных данных с помощью сервиса «Яндекс.Метрика» (текст Согласия).