A neural network approach for regional vertical total electron content modelling

Abstract

A Neural Network model has been developed for estim ating the total electron content (TEC) of the ionosphere. TEC is proportional to the delay suffered by electromagnetic signals crossing the ionosphere and is among the er rors that impact GNSS (Global Navigation Satellite Systems) observations. Ionosph eric delay is particularly a problem for single frequency receivers, which cannot elimin ate the (first-order) ionospheric delay by combining observations at two frequencies. Singl e frequency users rely on applying corrections based on prediction models or on region al models formed based on actual data collected by a network of receivers. A regiona l model based on a neural network has been designed and tested using data sets collected by the Brazilian GPS Network (RMBC) covering periods of low and high solar activity. An alysis of the results indicates that the model is capable of recovering, on average, 85% of TEC values. K e y w o r d s : total electron content, ionosphere, regi onal ionospheric model, neural network