Artificial neural network as a model for ionospheric TEC map to serve the single frequency receiver

Abstract

Ionospheric refraction is one of the most damaging effects on GPS signal. This effect is proportional to the Total Electron Content (TEC), which is the number of free electrons contained in the ionospheric layer. Once the TEC is known, it is possible to determine the delay caused by the ionosphere on GPS signal. This ionospheric delay is particularly a problem for single frequency receivers, which cannot eliminate the ionospheric delay by combining observations at two frequencies. Single frequency users rely on applying corrections based on prediction models or on regional models formed based on actual data collected by a network of receivers.It is necessary to use models that tell the single frequency users how large the ionospheric refraction is. Such is the case of which the GPS broadcast message carries parameters of the Klobuchar model. One other alternative to single frequency users is to create a regional model based on IGS TEC maps. In this case, the regional behavior of ionosphere is modeled in a way that it is possible to estimate the TEC values inside or near this region. This regional model can be based on artificial neural network. In this paper, an approach to modeling the ionospheric Total Electron Content (TEC) based on artificial neural network is presented.The goal of this paper is to estimate Vertical Total Electron Content (VTEC) for void areas and to avoid the gap which occurs between the results of the Global Ionosphere Map (GIM) from two consecutive sessions using ANN to produce high resolution ionospheric model to serve the single frequency receiver.The estimation method and test results of the proposed method indicate that the difference between predicted and observation values of VTEC is very small.