Abstract
In this paper, a tentative prediction of daily geomagnetic field and storms is implanted by analyzing the International Real-Time Magnetic Observatory Network data using the artificial neural network (ANN). Solar geomagnetic storms have a big effect on plasma ionospheric disturbance, and our study intend to introduce this effect when predicting ionospheric physical response. The implanted method is based on the prediction of future geomagnetic field components using a multilayer perceptron neural network model. The input is the time, and the output is the X, Y, and Z magnetic field components. Application to geomagnetic data of May 2002 shows that the implanted ANN model can greatly help the geomagnetic storms prediction.
Similar content being viewed by others
References
Banerjee A, Bej A, Chatterjee TN (2012) On the existence of a long range correlation in the geomagnetic disturbance storm time (Dst) index. Astrophys Space Sci 337(1):23–32
Danilov AD (2013) Ionospheric F-region response to geomagnetic disturbances. Adv Space Res 52(3):343–366
Li Z, Wei F, Feng X, Guo J, Emery B, Zhao X (2012) Large ionospheric disturbances during a minor geomagnetic storm on June 23, 2000. Ann Geophys 55(2):253–263
Lundstedt H, Wintoft P (1994) Prediction of geomagnetic storms from solar wind data with the use of a neural network. Ann Geophys 12 (1):19–24
Mirikitani DT, Ouarbya L (2009) Modeling Dst with recurrent EM neural networks. Lect Notes Comput Sci 5768:975–984
Ouadfeul S, Hamoudi M (2012) Fractal Analysis of InterMagnet Observatories Data, Fractal Analysis and Chaos in Geosciences, Dr. Sid-Ali Ouadfeul (Ed), ISBN: 978-953-51-0729-3, InTech, doi: 10.5772/51259. Available from: http://www.intechopen.com/books/fractal-analysis-and-chaos-in-geosciences/fractal-analysis-of-intermagnet-observatories-data
Shang S, Guo J, Shi J, Zhang M, Liu Q, Luo X (2003) Morphologies of global ionospheric disturbances during geomagnetic disturbance events of different type. Chin J Geophys 46(1):1–10
Sutcliffe PR (2000) The development of a regional geomagnetic daily variation model using neural networks. Ann Geophys 18:120–128
Thomson AWP (1993) Non-linear predictions of Ap by activity class and numerical value. Pure Appl Geophys 146(1):163–193
Yu C, Manry MT (2002) A modified hidden optimization algorithm for feedforward neural networks. Conference Record of the Thirty-Sixth Asilomar Conference on Signals, Systems and Computers. IEEE 2:1034–1038. doi: 10.1109/ACSSC.2002.1196941
Acknowledgments
Authors would like to thank the INTERMAGNET network for the free access to Wingst geomagnetic observatory data.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ouadfeul, SA., Tourtchine, V. & Aliouane, L. Daily geomagnetic field prediction of INTERMAGNET observatories data using the multilayer perceptron neural network. Arab J Geosci 8, 1223–1227 (2015). https://doi.org/10.1007/s12517-014-1308-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12517-014-1308-z