- PII
- 10.31857/S0016794023600084-1
- DOI
- 10.31857/S0016794023600084
- Publication type
- Status
- Published
- Authors
- Volume/ Edition
- Volume 63 / Issue number 3
- Pages
- 321-326
- Abstract
- A neural network forecast of substorms caused by the impact of solar wind plasma flows on the Earth’s magnetosphere has been performed. For this, recurrent neural network models were created based on physical cause-and-effect relationships of the dynamics of high-latitude geomagnetic activity (according to the AL index) with the parameters of the interplanetary magnetic field (IMF) and solar wind plasma (SWP). Two parameters are used as input sequences: the bz-component of the IMF and the integral parameter Σ[NV2], taking into account the prehistory of the process of pumping the kinetic energy of the solar wind into the magnetosphere, where N and V are the plasma density and solar wind velocity, respectively. The forecast of the AL index according to SWP and IMF for 10 min, etc. with 10 min discreteness individually by an individual artificial neural network (ANN) for each point corresponding to the dynamics of the AL index was completed. This means that the prediction of a continuous series of values AL index is achieved by a parallel running of the ANN package. The number of ANNs in the package is determined by the duty cycle of the required predictive series of the AL index, while taking 90 min of the history of input parameters in each of the networks into account provides a prediction of the values AL index with an accuracy of ~80%
- Keywords
- Date of publication
- 01.05.2023
- Year of publication
- 2023
- Number of purchasers
- 0
- Views
- 46
References
- 1. – Barkhatov N.A., Revunov S.E. Uryadov V.P. Artificial neural network technique for predicting the critical frequency of the ionospheric F2 layer // Radiophys. Quantum. Electron. V. 48. P. 1–13. 2005. https://doi.org/10.1007/s11141-005-0043-4
- 2. – Barkhatov N.A., Vorobjev V.G., Revunov S.E., Barkhatova O.M., Revunova E.A. and Yagodkina O.I. Neural network classification of substorm geomagnetic activity caused by solar wind magnetic clouds // J. Atmospheric and Solar-Terrestrial Physics. V. 205. 2020. https://doi.org/10.1016/j.jastp.2020.105301
- 3. – Elman J.L. Learning and development in neural networks: The importance of starting small. Cognition. V. 48. P. 71–99. 1993
- 4. – Hernandez J.V., Tajima T., Horton W. Neural net forecasting for geomagnetic activity // Geophys. Res. Lett. V. 20. № 23. P. 2707–2710. 1993. https://doi.org/10.1029/93GL02848
- 5. – Li X., Oh K.S., Temerin M. Prediction of the AL index using solar wind parameters // J. Geophys. Res. V. 112. A06224. 2007. https://doi.org/10.1029/2006JA011918
- 6. – Valach F., Bochnicek J., Hejda P., Revallo M. Strong magnetic activity forecast by neural networks under dominant southern orientation of interplanetary magnetic field // Adv. SpaceRes. V. 53. № 4. P. 589–598. 2014. https://doi.org/10.1016/j.asr.2013.12.005
- 7. – Weigel R.S., Klimas A.J., Vassiliadis D. Solar wind coupling to and predictability of ground magnetic field and their time derivatives // J. Geophys. Res. V. 107. № A7. P. 1298. 2003. https://doi.org/10.1029/2002JA009627
- 8. – Бархатов Н.А., Беллюстин Н.С., Левитин А.Е., Сахаров С.Ю. Сравнение эффективности предсказания индекса геомагнитной активности Dst искусственными нейронными сетями. // Изв. ВУЗов “Радиофизика”. Т. 43. № 5 С. 385–394. 2000
- 9. – Бархатов Н.А., Воробьев В.Г., Ревунов С.Е., Ягодкина О.И. Проявление динамики параметров солнечного ветра на формирование суббуревой активности // Геомагнетизм и аэрономия. Т. 57. № 3. С. 273–279. 2017
- 10. – Бархатов Н.А., Королев А.В., Левитин А.Е., Сахаров С.Ю. Пересчет современных индексов полярной активности к классическим // Изв. ВУЗов “Радиофизика”. Т. 47. № 3. С. 200–208. 2004
- 11. – Бархатов Н.А., Ревунов С.Е. Искусственные нейронные сети в задачах солнечно-земной физики. Монография. Изд-во “Поволжье”. 407 С. 2010.
- 12. – Хайкин С. Нейронные сети, Полный курс. 2-е изд., пер. с англ., М.: “Вильямс”. 1104 с. 2006.
