Time-Series Forecasting of Geomagnetic Activity: A Data-Driven Approach for K_P Index Prediction

Document Type : Research Paper

Authors

Faculty of Physics, University of Tabriz, PO Box 51666-16471, Tabriz, Iran

Abstract

The geomagnetic index $\emph K_{\rm p}$ is a fundamental metric for quantifying geomagnetic activity and understanding solar-terrestrial physics. Accurately modeling and predicting its non-linear fluctuations remains a significant challenge in the study of space climate. In this research, we propose a robust statistical approach using a Long Short-Term Memory (LSTM) neural network for the time-series forecasting of the $\emph K_{\rm p}$ index. Our models are trained and evaluated on a comprehensive dataset spanning a 25-year period from 1999 to 2024, utilizing high-resolution solar wind data sourced from the NASA OMNIWeb database. We incorporate eight critical physical parameters as input features, including three-dimensional magnetic field components and plasma properties. A critical aspect of sequential modeling is determining the optimal historical context. Therefore, we systematically evaluate the impact of various input time windows (6, 12, 24, 48, 72, and 120 hours) on the predictive performance of the network. Our empirical analysis reveals that the 6-hour input window yields the highest precision, achieving an $R^2$ score of 0.7233 and minimizing the root mean square error (RMSE). These results indicate that short-term solar memory contains the most relevant dynamical features for forecasting geomagnetic variations. This study highlights the effectiveness of LSTM architectures in capturing the short-term dynamical evolution of the Earth's magnetic environment, offering valuable insights for future data-driven research in space physics.

Keywords

References

[1] Rangarajan, G. K., & Barreto, L. M. 1999, Earth, Planets and Space, 51, 363.
[2] Matzka, J., et al. 2021, Space Weather, 19, e2020SW002641.
[3] Elliott, H. A., et al. 2013, Space Weather, 11, 339.
[4] Lockwood, M., et al. 2017, Journal of Space Weather and Space Climate, 7, A25.
[5] Chakraborty, S., & Morley, S. K. 2020, Journal of Space Weather and Space Climate, 10, 36.
[6] Zhang, J., et al. 2007, Journal of Geophysical Research (Space Physics), 112, A10102.
[7] Saiz, E., et al. 2013, Journal of Space Weather and Space Climate, 3, A26.
[8] Kim, S., Li, X., Damas, M. C., & Ngwira, C. 2017, AGU Fall Meeting Abstracts, Vol. 2017 of AGU Fall Meeting Abstracts, ED11D.
[9] Osmane, A., et al. 2015, Journal of Geophysical Research (Space Physics), 120, 9307.
[10] Boroyev, R. N. 2019, Advances in Space Research, 63, 302.
[11] Lazzeri, C., et al. 2024, European Geosciences Union General Assembly 2024 (EGU24), EGU General Assembly Conference Abstracts
[12] Lockwood, M. 2022, Space Weather, 20, e2021SW002989.
[13] Tasnim, S., et al. 2025, Frontiers in Astronomy and Space Sciences, 12, 1675769.
[14] Liu, W., et al. 2021, 101st Annual AMS Meeting 2021, Vol. 101 of American Meteorological Society Meeting Abstracts PUBLISHER , p. Joint.
[15] Masuda, A., Hebishima, H., & ichi Inage, S. 2026, Next Sustainability, 7, 100225.
[16] Camporeale, E. 2019, Space Weather, 17, 1166.
[17] Detman, T., & Joselyn, J. 1999, Solar Wind Nine, Vol. 471 of American Institute of Physics Conference Series, edited by Habbal, S. R., Esser, R., Hollweg, J. V., & Isenberg, P. A. AIP , 729.
[18] Lockwood, M., et al. 2020, Journal of Space Weather and Space Climate, 10, 23.
[19] Khabarova, O., & Price, C. 2024, Frontiers in Astronomy and Space Sciences, 11, 1493917.
[20] Lazzeri, C., et al. 2024, Journal of Geophysical Research (Space Physics), 129, e2023JA032160.
[21] Boberg, F., Wintoft, P., & Lundstedt, H. 2000, Physics and Chemistry of the Earth, Part C: Solar, Terrestrial & Planetary Science, 25, 275.
[22] Wing, S., et al. 2005, Journal of Geophysical Research: Space Physics, 110.
[23] Tan, Y., Hu, Q., Wang, Z., & Zhong, Q. 2018, Space Weather, 16, 406.
[24] Zhelavskaya, I. S., Shprits, Y. Y., & Spasojević, M. 2019, Space Weather, 17, 1016.
[25] Gruet, M. A., Chandorkar, M., Sicard, A., & Camporeale, E. 2018, Space Weather, 16, 1882.
[26] Conde, D., et al. 2023, Space Weather, 21, e2023SW003474, e2023SW003474 2023SW003474.
[27] Azlan, A., Yusof, Y., & Mohsin, M. F. M. 2019, International Journal of Advanced Computer Research, 9, 260.
[28] Houndekindo, F., & Ouarda, T. B. M. J. 2025, Energy, 328, 136498.
[29] Alguhi, A. A., & Al-Shaalan, A. M. 2025, Energies, 18, 4594.
[30] Jeon, E., Jin, D., & Kim, Y. 2026, Machines, 14, 135.
[31] Javaherian, M., et al. 2025, Scientific Reports, 15, 44006.
[32] Stone, E. C., et al. 1998, Space Sci. Rev., 86, 1.
[33] Wang, J., et al. 2015, Space Weather, 13, 831.
[34] Hassani, Z., Mohammadpur, D., & Safari, H. 2025, ApJS, 279, 27.
[35] Hochreiter, S., & Schmidhuber, J. 1997, Neural Computation, 9, 1735.
[36] Goodfellow, I. Deep learning, 2016.
[37] Kingma, D. P., & Ba, J. 2014, arXiv preprint arXiv:1412.6980.
[38] Chakraborty, S., & Morley, S. K. 2020, Journal of Space Weather and Space Climate.
[39] Lin, J.-W. 2021, European Journal of Geosciences.
Iranian Journal of Astronomy and Astrophysics
Volume 12, Issue 4
January 2026
Pages 323-334

Files

Share

How to cite

Statistics