A neural network approach for regional vertical total electron content modelling

Abstract

A Neural Network model has been developed for estimating 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 errors that impact GNSS (Global Navigation Satellite Systems) observations. Ionospheric delay is particularly a problem for single frequency receivers, which cannot eliminate the (first-order) 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. A regional 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. Analysis 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, regional ionospheric model, neural network

Investigating the performance of neural network backpropagation algorithms for TEC estimations using South African GPS data

“…Diurnal and seasonal variation representations, sunspot number, and geographic latitudes and longitudes have been used previously in the modelling of foF2 and TEC using neural networks (e.g. Cander et al, 1998;McKinnell, 2002;McKinnell and Poole, 2004;Leandro and Santos, 2007).…”

“…Hernàndez-Pajares et al, 1997;Tulunay et al, 2004Tulunay et al, , 2006Leandro and Santos, 2007;Senalp et al, 2008;Yilmaz et al, 2009). The main work in the application of this nonlinear technique involves finding a relationship between known input and output parameters using a relevant training algorithm.…”

“…For its simplicity, SBP algorithm has been widely used for TEC modelling and mapping in both feed forward and recurrent neural networks (e.g. Leandro and Santos, 2007;Yilmaz et al, 2009;Habarulema et al, 2007Habarulema et al, , 2009Habarulema et al, , 2010. Research has shown that different problems require different training algorithms and types of neural networks.…”

Regional ionospheric modeling using wavelet network model

“…In addition, the resolution of these products might not be sufficient to support high quality GPS positioning, especially in the presence of local ionospheric disturbances. The need to produce regional ionosphere models for accurate positioning was investigated by many researchers (Komjathy and Langley, 1996;Hernández-Pajares et al, 1997;Hernandez-Pajares et al 1999;Liu and Gao, 2003;Wielgosz et al, 2003;Moon, 2004;Leandro and Santos 2007;Sayin et al, 2008;Maruyama, 2007;Liu et al, 2011;Liu et al, 2014;Ohashi et al, 2015 andRazin et al, 2015), where different algorithms were employed for regional ionosphere modeling such as Spherical harmonics, Spline interpolation, Gaussian process, kriging and artificial neural networks. However, due to the nonlinearity of ionosphere physical properties a highly nonlinear model a highly nonlinear wavelet network method is proposed in this paper to model and predict the temporal and spatial variations of ionosphere modeling.…”

Nonlinear dynamic systems modeling using Gaussian processes: Predicting ionospheric total electron content over South Africa

“…[11] Nevertheless, neural networks have found considerable use in the modeling of TEC for over a decade, and in fact, besides the commonly encountered global International Reference Ionosphere (IRI) empirical model [Bilitza, 2001] which suffers from a historic scarcity of data in the Southern Hemisphere [McKinnel, 2002], the most interesting contributions to TEC modeling from a practical point of view have arguably been the development of several regional neural network models (see for example the work by HernandezPajares et al [1997] which made use of GPS observations, Xenos et al [2003] which employed Faraday-rotation derived TEC, Tulunay et al [2006] where NNs were used to predict TEC maps, as well as the work by Leandro and Santos [2007], Habarulema et al [2009], andYilmaz et al [2009]). …”