Neural network modeling of the ionospheric electron content at global scale using GPS data

Abstract

The adaptative classification of the rays received from a constellation of geodetic satellites (the Global Positioning System (GPS)) by a set of ground receivers is performed using neural networks. This strategy allows us to improve the reliability of reconstructing the ionospheric electron distribution from GPS data. As an example, we present the evolution at global scale of the radially integrated electron density (total electron content (TEC)) for October 18, 1995, coinciding with an important geomagnetic storm.