A Comparison between Artificial Neural Network Prediction Models for Coronal Hole Related High-Speed Streams

Authors: Rehab Abdulmajed, Amr Hamada, Ahmed Elsaid, Hisashi Hayakawa, Ayman Mahrous

Abstract:

Solar emissions have a high impact on the Earth’s magnetic field, and the prediction of solar events is of high interest. Various techniques have been used in the prediction of the solar wind using mathematical models, MHD models and neural network (NN) models. This study investigates the coronal hole (CH) derived high-speed streams (HSSs) and their correlation to the CH area and create a neural network model to predict the HSSs. Two different algorithms were used to compare different models to find a model that best simulated the HSSs. A dataset of CH synoptic maps through Carrington rotations 1601 to 2185 along with Omni-data set solar wind speed averaged over the Carrington rotations is used, which covers Solar Cycles (SC) 21, 22, 23, and most of 24.

Keywords: Artificial Neural Network, ANN, Coronal Hole Area Feed-Forward neural network models, solar High-Speed Streams, HSSs.

References:

[1] Y. Yang, F. Shen, Z. Yang, and X. Feng, “Prediction of solar wind speed at 1 au using an artificial neural network,” Space Weather, vol. 16, no. 9, pp. 1227–1244, 2018.
[2] V. Upendran, M. C. Cheung, S. Hanasoge, and G. Krishnamurthi, “Solar wind prediction using deep learning,” Space Weather, vol. 18, no. 9, p. e2020SW002478, 2020.
[3] Y. Nakagawa, S. Nozawa, and A. Shinbori, “Relationship between the low-latitude coronal hole area, solar wind velocity, and geomagnetic activity during solar cycles 23 and 24,” Earth, Planets and Space, vol. 71, no. 1, pp. 1–15, 2019.
[4] S. R. Cranmer, “Coronal holes,” Living Reviews in Solar Physics, vol. 6, pp. 1–66, 2009.
[5] S. J. Hofmeister, A. Veronig, M. Temmer, S. Vennerstrom, B. Heber, and B. Vrˇsnak, “The dependence of the peak velocity of high-speed solar wind streams as measured in the ecliptic by ace and the stereo satellites on the area and co-latitude of their solar source coronal holes,” Journal of Geophysical Research: Space Physics, vol. 123, no. 3, pp. 1738–1753, 2018.
[6] J. Nolte, A. Krieger, A. Timothy, R. Gold, E. Roelof, G. Vaiana, A. Lazarus, J. Sullivan, and P. McIntosh, “Coronal holes as sources of solar wind,” Solar Physics, vol. 46, no. 2, pp. 303–322, 1976.
[7] V. Abramenko, V. Yurchyshyn, and H. Watanabe, “Parameters of the magnetic flux inside coronal holes,” Solar Physics, vol. 260, no. 1, pp. 43–57, 2009.
[8] N. V. Karachik and A. A. Pevtsov, “Solar wind and coronal bright points inside coronal holes,” The Astrophysical Journal, vol. 735, no. 1, p. 47, 2011.
[9] Y.-M. Wang and N. Sheeley Jr, “Magnetic flux transport and the sunspot-cycle evolution of coronal holes and their wind streams,” The Astrophysical Journal, vol. 365, pp. 372–386, 1990.
[10] B. Vrˇsnak, M. Temmer, and A. M. Veronig, “Coronal holes and solar wind high-speed streams: I. forecasting the solar wind parameters,” Solar Physics, vol. 240, no. 2, pp. 315–330, 2007.
[11] S. Robbins, C. Henney, and J. Harvey, “Solar wind forecasting with coronal holes,” Solar Physics, vol. 233, pp. 265–276, 2006.
[12] B. Vrˇsnak, M. Temmer, and A. M. Veronig, “Coronal holes and solar wind high-speed streams: Ii. forecasting the geomagnetic effects,” Solar Physics, vol. 240, pp. 331–346, 2007.
[13] H. Simon, Neural networks: a comprehensive foundation. Prentice hall, 1999.
[14] M. H. Sazli, “A brief review of feed-forward neural networks,” Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, vol. 50, no. 01, 2006.
[15] J. Lazz´us, P. Vega, P. Rojas, and I. Salfate, “Forecasting the dst index using a swarm-optimized neural network,” Space Weather, vol. 15, no. 8, pp. 1068–1089, 2017.
[16] H. Lundstedt, “Progress in space weather predictions and applications,” Advances in Space Research, vol. 36, no. 12, pp. 2516–2523, 2005.
[17] “Nasa/nssdc omni dataset.” (Online). Available: https://omniweb.gsfc. nasa.gov/
[18] I. G. Richardson and H. V. Cane, “Solar wind drivers of geomagnetic storms during more than four solar cycles,” Journal of Space Weather and Space Climate, vol. 2, p. A01, may 2012. (Online). Available: http://www.swsc-journal.org/10.1051/swsc/2012001
[19] A. Hamada, T. Asikainen, and K. Mursula, “A uniform series of low-latitude coronal holes in 1973–2018,” Solar Physics, vol. 296, no. 2, pp. 1–22, 2021.
[20] “Noaa national centers for environmental information,” mcIntosh archive Dataset. (Online). Available: https://www.ngdc.noaa.gov/stp/space-weather/solar-data/solar-imagery/ composites/synoptic-maps/mc-intosh/
[21] K. Yotov, E. Hadzhikolev, and S. Hadzhikoleva, “Determining the number of neurons in artificial neural networks for approximation, trained with algorithms using the jacobi matrix,” TEM Journal, vol. 9, no. 4, p. 1320, 2020.
[22] F. Burden and D. Winkler, “Bayesian regularization of neural networks,” Artificial neural networks: methods and applications, pp. 23–42, 2009.
[23] J. M. Caswell, “A nonlinear autoregressive approach to statistical prediction of disturbance storm time geomagnetic fluctuations using solar data,” Journal of Signal and Information Processing, vol. 2014, 2014.
[24] “University of oulu database of solar euv and coronal hole synoptic maps.” (Online). Available: http://satdat.oulu.fi/solar data