The Significance of Input Features for Domain Adaptation of Spacecraft Data

E. Z. Karimov; Каримов Э. З.; I. N. Myagkova; Мягкова И. Н.; V. R. Shirokiy; Широкий В. Р.; O. G. Barinov; Баринов О. Г.; S. A. Dolenko; Доленко С. А.

doi:10.31857/S0023420623600125

The Significance of Input Features for Domain Adaptation of Spacecraft Data

Autores: Karimov E.Z.¹^,2, Myagkova I.N.², Shirokiy V.R.², Barinov O.G.², Dolenko S.A.³
Afiliações:
1. Faculty of Physics, Moscow State University, 119991, Moscow, Russia
2. Skobeltsyn Institute of Nuclear Physics, Moscow State University, 119991, Moscow, Russia
3. Skobeltsyn Institute of Nuclear Physics, Lomonosov Moscow State University
Edição: Volume 61, Nº 6 (2023)
Páginas: 530-537
Seção: Articles
URL: https://rjmseer.com/0023-4206/article/view/672588
DOI: https://doi.org/10.31857/S0023420623600125
EDN: https://elibrary.ru/CBGXUK
ID: 672588

Citar

Texto integral

Acesso aberto
Acesso é fechado

Acesso está concedido
Acesso é fechado

Acesso é pago ou somente para assinantes

Resumo
Sobre autores
Bibliografia
Arquivos suplementares
Estatísticas

Resumo

The problem of improving the neural network forecast of geomagnetic index Dst under conditions in which the input data for such a forecast are measured by two spacecraft, one of which is close to the end of its life cycle, and the data history of the other is not yet enough to construct a neural network forecast of the required quality. For an efficient transition from the data of one spacecraft to the data of another, it is necessary to use methods of domain adaptation. This paper tests and compares several data translation methods. Also, for each translated attribute, an optimal set of parameters for its translation were found, which further reduces the difference between domains. The paper shows that the use of domain adaptation methods with the selection of significant features can improve the forecast compared to the results of using untranslated data.

Bibliografia

Daglis I.A. Space Storms and Space Weather Hazards. Dordrecht: Kluwer Academic Publishers, 2001.
Cole D.G. Space weather: Its effects and predictability // Space Science Reviews. 2003. V. 107. P. 295–302. https://doi.org/10.1023/A:1025500513499
Vassiliadis D. Forecasting space weather // Space Weather: Physics and Effects. Berlin; Heidelberg: Springer Praxis Books, 2007. P. 403–425. https://doi.org/10.1007/978-3-540-34578-7_14
Kudela K. Space weather near Earth and energetic particles: selected results // J. Physics: Conf. Series. 2013. V. 409. Iss. 1. Art. ID. 012017. https://doi.org/10.1088/1742-6596/409/1/012017
Schrijver C.J., Kauristie K., Aylward A.D. et al. Understanding space weather to shield society: A global road map for 2015–2025 commissioned by COSPAR and ILWS // Advances in Space Research. 2015. V. 55. Iss. 12. P. 2745–2807. https://doi.org/10.1016/j.asr.2015.03.023
McGranaghan R.M., Camporeale E., Georgoulis M. et al. Space Weather research in the Digital Age and across the full data lifecycle: Introduction to the Topical Issue // J. Space Weather and Space Climate. 2021. V. 11. Art. ID. 50. https://doi.org/10.1051/swsc/2021037
Лазутин Л.Л. Мировые и полярные магнитные бури / Под ред. проф. Ю.И. Логачева. М.: МГУ, 2012. 214 с.
Qiu Q., Fleeman J.A., Ball D.R. Geomagnetic disturbance: A comprehensive approach by American electric power to address the impacts / IEEE Electrification Magazine. 2015. V. 3. Iss. 4. P. 22–33. https://doi.org/10.1109/MELE.2015.2480615
Белаховский В.Б., Пилипенко В.А., Сахаров Я.А. и др. Рост геомагнитно-индуцированных токов во время корональных выбросов массы и высокоскоростных потоков солнечного ветра геомагнитных бурь в 2021 году // Изв. РАН. Сер. Физическая. 2023. Т. 87. № 2. С. 271–277. , EDN: AITPFOhttps://doi.org/10.31857/S0367676522700478
Friedel R.H., Reeves W.G.P., Obara T. Relativistic electron dynamics in the inner magnetosphere: A review // J. Atmospheric and Solar-Terrestrial Physics. 2002. V. 64. Iss. 2. P. 265–283. https://doi.org/10.1016/S1364-6826(01)00088-8
Kataoka R., Miyoshi Y. Average profiles of the solar wind and outer radiation belt during the extreme flux enhancement of relativistic electrons at geosynchronous orbit // Annales Geophysicae. 2008. V. 26. Iss. 6. P. 1335–1339. https://doi.org/10.5194/angeo-26-1335-2008
Мягкова И.Н., Шугай Ю.С., Веселовский И.С. и др. Сравнительный анализ влияния рекуррентных высокоскоростных потоков солнечного ветра на радиационное состояние околоземного космического пространства в апреле–июле 2010 года // Астрон. вестн. 2013. Т. 47. № 2. С. 141–155. https://doi.org/10.7868/S0320930X13020060
Белов А.В., Виллорези Дж., Дорман Л.И. и др. Влияние космической среды на функционирование искусственных спутников Земли // Геомагнетизм и аэрономия. 2004. Т. 44. № 4. С. 502–510.
Романова Н.В., Пилипенко В.А., Ягова Н.В. и др. Статистическая связь частоты сбоев на геостационарных спутниках с потоками энергичных электронов и протонов // Косм. исслед. 2005. Т. 43. № 3. С. 186–193.
Summers D., Stone S. Analysis of radiation belt “killer” electron energy spectra // J. Geophysical Research: Space Physics. 2022. V. 127. Iss. 9. Art. ID. e2022JA030698. https://doi.org/10.1029/2022JA030698
Akasofu S.-I., Chapman S. Solar-Terrestrial Physics. Oxford: Clarendon Press, 1972. 901 p.
Riazantseva M.O., Dalin P.A., Dmitriev A.V. et al. A multifactor analysis of parameters controlling solar wind ion flux correlations using an artificial neural network technique // J. Atmospheric and Solar-Terrestrial Physics. 2002. V. 64. Iss. 5–6. P. 657–660. https://doi.org/10.1016/S1364-6826(02)00026-3
Burton R.K., McPherron R.L., Russell C.T. An empirical relationship between interplanetary conditions and Dst // J. Geophysical Research. 1975. V. 80. P. 4204–4214.
Ефиторов А.О., Мягкова И.Н., Широкий В.Р. и др. Прогнозирование Dst-индекса, основанное на методах машинного обучения // Косм. исслед. 2018. Т. 56. № 6. С. 353–364. https://doi.org/10.31857/S002342060002493-0
Мягкова И.Н., Широкий В.Р., Владимиров Р.Д. и др. Прогнозирование значений геомагнитного индекса Dst при помощи адаптивных методов // Метеорология и гидрология. 2021. № 3. С. 38–46. https://doi.org/10.52002/0130-2906-2021-3-38-46
Myagkova I., Shiroky V., Dolenko S. Prediction of geomagnetic indexes with the help of artificial neural networks // E3S Web of Conferences. 2017. V. 20. Art. ID. 02011. 7 p. https://doi.org/10.1051/e3sconf/20172002011