Skip to main content


We’d like to understand how you use our websites in order to improve them. Register your interest.

Prediction of the geomagnetic storm associated Dst index using an artificial neural network algorithm


In order to enhance the reproduction of the recovery phase Dst index of a geomagnetic storm which has been shown by previous studies to be poorly reproduced when compared with the initial and main phases, an artificial neural network with one hidden layer and error back-propagation learning has been developed. Three hourly Dst values before the minimum Dst in the main phase in addition to solar wind data of IMF southward-component Bs, the total strength Bt and the square root of the dynamic pressure, \(sqrt {n{V^2}}\), for the minimum Dst, i.e., information on the main phase was used to train the network. Twenty carefully selected storms from 1972–1982 were used for the training, and the performance of the trained network was then tested with three storms of different Dst strengths outside the training data set. Extremely good agreement between the measured Dst and the modeled Dst has been obtained for the recovery phase. The correlation coefficient between the predicted and observed Dst is more than 0.95. The average relative variance is 0.1 or less, which means that more than 90% of the observed Dst variance is predictable in our model. Our neural network model suggests that the minimum Dst of a storm is significant in the storm recovery process.


  1. Baker, D. N., Statistical analyses in the study of solar wind-magnetosphere coupling, in Solar Wind-Magnetosphere Coupling, edited by Y. Kamide and J. A. Slavin, pp. 17–38, Terra Scientific Pub., Tokyo, 1986.

  2. Burton, R. K., R. L. McPherron, and C. T. Russell, An empirical relationship between interplanetary conditions and Dst, J. Geophys. Res., 80, 4204–4214, 1975.

  3. Clauer, C. R., The technique of linear prediction filters applied to studies of solar wind-magnetosphere coupling, in Solar Wind-Magnetosphere Coupling, edited by Y. Kamide and J. A. Slavin, pp. 39–57, Terra Scientific Pub., Tokyo, 1986.

  4. Daglis, I. A., The role of magnetosphere-ionosphere coupling in magnetic storm dynamics, in Magnetic Storms, edited by B. T. Tsurutani, W. D. Gonzalez, Y. Kamide, and J. K. Arballo, pp. 107–116, AGU, Washington, D.C., 1997.

  5. Detman, T. R. and D. Vassiliadis, Review of techniques for magnetic storm forecasting, in Magnetic Storms, edited by B. T. Tsurutani, W. D. Gonzalez, Y. Kamide, and J. K. Arballo, pp. 253–266, AGU, Washington, D.C., 1997.

  6. Fausett, L., Fundamentals of Neural Networks: Architectures, Algorithms, and Applications, 461 pp., Prentice Hall, Englewood Cliffs, NJ 07632, 1994.

  7. Fok, M.-C., J. U. Kozyra, A. F. Nagy, and T. E. Cravens, Lifetime of ring current particles due to Coulomb collisions in the plasmasphere, J. Geophys. Res., 96, 7861–7867, 1991.

  8. Freeman, J., A. Nagai, P. Reiff, W. Denig, S. Gussenhoven, M. A. Shea, M. Heinemann, F. Rich, and M. Hairston, The use of neural networks to predict magnetospheric parameters for input to a magnetospheric forecast model, in Proceedings of the International Workshop on Artificial Intelligence Applications in Solar Terrestrial Physics, edited by J. Joselyn, H. Lundstedt, and J. Trolinger, pp. 167–182, Lund, Sweden, 1993.

  9. Gleisner, H. and H. Lundstedt, Response of the auroral electrojets to the solar wind modeled with neural networks, J. Geophys. Res., 102, 14269–14278, 1997.

  10. Gleisner, H., H. Lundstedt, and P. Wintoft, Predicting geomagnetic storms from solar wind data using time-delay neural networks, Ann. Geophys., 14, 679–686, 1996.

  11. Gloeckler, G. and D. C. Hamilton, AMPTEE ion composition results, Phys. Scr., T18, 73–84, 1987.

  12. Hamilton, D. C., 5. Storm dynamics/ring current, in Magnetic Storms, edited by B. T. Tsurutani, W. D. Gonzalez, Y. Kamide, and J. K. Arballo, pp. 6–7, AGU, Washington, D.C., 1997.

  13. Hamilton, D. C., G. Gloeckler, F. M. Ipavich, W. Studemann, B. Wilken, and G. Kremser, Ring current development during during the great geomagnetic storm of February 1986, J. Geophys. Res., 93, 14343–14355, 1988.

  14. Hertz, J., A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation, lecture notes vol. 1, Santa Fe Institute Studies in the sciences of complexity, 327 pp., Addison-Wesley, Redwood City, CA 94065, 1991.

  15. Ichikawa, H., Layered Neural Networks, 184 pp., Kyoritu Pub., Tokyo, 108, 1993.

  16. Iyemori, T. and H. Maeda, Prediction of geomagnetic activities from solar wind parameters based on the linear prediction theory, in Solar-Terrestrial Predictions Proceedings, Vol. 4, U.S. Dept. of Commerce, Boulder, CO, A–1–A–7, 1980.

  17. Iyemori, T., H. Maeda, and T. Kamei, Impulse response of geomagnetic indices to interplanetary magnetic fields, J. Geomag. Geoelectr., 31, 1–9, 1979.

  18. Kamide, Y., N. Yokoyama, W. Gonzalez, B. T. Tsurutani, I. A. Daglis, A. Brekke, and S. Masuda, Two step development of geomagnetic storms, J. Geophys. Res., 103, 6917–6921, 1998.

  19. Lundstedt, H. and P. Wintoft, Prediction of geomagnetic storms from solarwind data with the use of a neural network, Ann. Geophys., 12, 19–24, 1994.

  20. Ogilvie, K. W., L. F. Burlaga, and T. D. Wilkerson, Plasma observations on Explorer 34, J. Geophys. Res., 73, 6809–6824, 1968.

  21. Pudovkin, M. I., S. A. Zaitseva, and L. Z. Sizova, Growth and decay of magnetospheric ring current, Planet. Space Sci., 33, 1097–1102, 1985.

  22. Rostoker, G. and C.-G. Fälthammar, Relationships between changes in the interplanetary magnetic field and the variations in the magnetic field at the earth’s surface, J. Geophys. Res., 72, 5853–5863, 1967.

  23. Siscoe, G. L., V. Formisano, and A. J. Lazarus, Relation between geomagnetic sudden impulses and solar wind pressure changes—an experimental investigation, J. Geophys. Res., 73, 4869–4874, 1968.

  24. Smith, P. H. and N. K. Bewtra, Charge exchange lifetimes for ring current ions, Space Sci. Rev., 22, 301–318, 1978.

  25. Sugiura, M., Hourly values of equatorial Dst for the IGY, Ann. Int. Geophys. Year, 35, 49, 1964.

  26. Vassiliadis, D., A. J. Klimas, D. N. Baker, and D. A. Roberts, A description of solar wind magnetosphere coupling based on nonlinear filters, J. Geophys. Res., 100, 3495–3512, 1995.

  27. Vassiliadis, D., A. J. Klimas, and D. N. Baker, Nonlinear ARMA models for the Dst index and their physical interpretation, paper presented at the Third International Conference on Substorms (ICS-3), Versailles, France, May 12–17, 1996.

  28. Wu, J.-G. and H. Lundstedt, Prediction of geomagnetic storms from solar wind data using Elman recurrent neural networks, Geophys. Res. Lett., 23, 319–322, 1996.

Download references

Author information



Corresponding author

Correspondence to Samuel Kugblenu.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Kugblenu, S., Taguchi, S. & Okuzawa, T. Prediction of the geomagnetic storm associated Dst index using an artificial neural network algorithm. Earth Planet Sp 51, 307–313 (1999).

Download citation


  • Solar Wind
  • Root Mean Square Error
  • Hide Layer
  • Storm Event
  • Recovery Phase