Regional TEC mapping using neural networks

Abstract

[1] Characterization and modeling of ionospheric variability in space and time is very important for communications and navigation. To characterize the variations, the ionosphere should be monitored, and the sparsity of the measurements has to be compensated by interpolation algorithms. The total electron content (TEC) is a major parameter that can be used to obtain regional ionospheric maps. In this study, neural networks (NNs), specifically multilayer perceptrons (MLPs) and radial basis function networks (RBFN), are investigated for the merits of their nonlinear modeling capability. In order to assess the performance of MLP and RBFN structures with respect to mapping and ionospheric parameters, these algorithms are applied to synthetically generated TEC surfaces representing various ionospheric states. Synthetic TEC data are sampled homogenously and randomly for a varying number of data points. The reconstruction errors show that the performance improves significantly when homogenous sampling is preferred to random station distribution. The best MLP and RBFN structures for any possible realistic scenario are determined by examining the performance parameters for all possible cases. It is also observed that RBFN with local receptive fields relies more on the number of training data points. In contrast to RBFN, MLP as a global approximator depends strongly on ionospheric trends. Finally, chosen MLP and RBFN models are applied to a set of real GPS-TEC values obtained from central Europe, and their performances are compared with well known Global Ionospheric Maps produced by the International GNSS Service. The resolution and interpolation quality of the generated maps indicate that NNs offer a powerful and reliable alternative to the conventional TEC mapping algorithms.

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

“…Chan and Canon, 2002;Yilmaz et al, 2009). TEC modelled and forecasted results for models, which utilised the L-MBP algorithm, have also been presented (Tulunay et al, 2006;Yilmaz et al, 2009). This algorithm is credited for its time savings during NN training/learning processes (Jang et al, 1997).…”

“…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.…”

“…Radial basis function networks have also been used in the generation of TEC data for ionospheric TEC mapping, as well as short term forecasting of foF2 (e.g. Chan and Canon, 2002;Yilmaz et al, 2009). TEC modelled and forecasted results for models, which utilised the L-MBP algorithm, have also been presented (Tulunay et al, 2006;Yilmaz et al, 2009).…”

“…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.…”

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]). …”