INTERNATIONAL JOURNAL OF GEOMAGNETISM AND AERONOMY VOL. 5, GI2010, doi:10.1029/2004GI000065, 2004

Forecasting of the critical frequency of the ionosphere shape F2 layer by the method of artificial neural networks

N. A. Barkhatov, and S. E. Revunov
Department of Physics, Nizhny Novgorod State Pedagogical University, Nizhny Novgorod, Russia

V. P. Uryadov
Radiophysical Research Institute, Nizhny Novgorod, Russia


Abstract

[1]  An algorithm of forecasting of the ionosphere F2 layer critical frequency for time intervals: 1, 2, 3, 12, and 24 hours was developed on the basis of the technology of artificial neural networks (ANN). The experimental search for a valid training array and architecture of ANN was performed. The solar wind parameters, interplanetary magnetic field, and geomagnetic disturbance indexes were additionally used in the forecasting. This made it possible to improve its effectiveness. The practical importance of the performed work is in the application of its results for efficient correction of the ionosphere model for an improvement of the ionosphere shortwave radio communication.

Received 2 February 2004; revised 14 September 2004; accepted 15 October 2004; published 28 December 2004.

Keywords: Ionospheric F2 layer; forecasting of the critical frequency; artificial neural networks.

Index Terms: 2447 Ionosphere: Modeling and forecasting; 2487 Ionosphere: Wave propagation; 2435 Ionosphere: Ionospheric disturbances.


AGU

Citation: Barkhatov, N. A., S. E. Revunov, and V. P. Uryadov (2004), Forecasting of the critical frequency of the ionosphere F2 layer by the method of artificial neural networks, Int. J. Geomagn. Aeron., 5, GI2010, doi:10.1029/2004GI000065.

Copyright 2004 by the American Geophysical Union

Powered by TeXWeb (Win32, v.1.5).