Modeling and interpolation of ionosphere total electron content using artificial neural network and GPS observation

Authors

Abstract

Global positioning system (GPS) signals provide valuable information about ionosphere physical structure. Using these signals, can be derived total electron content (TEC) for each line of sight between the receiver and the satellite. For historic and other sparse data sets, the reconstruction of TEC images is often performed using multivariate interpolation techniques. Recently it has become clear that the techniques derived from artificial intelligence research and modern computer science provide a number of system aids to analyze and predict the behavior of complex solar-terrestrial dynamic systems. Methods of artificial intelligence have provided tools which potentially make the task of ionospheric modeling possible. Artificial neural network (ANN) provides an inexplicit non-linear model to learn relations between inputs and outputs using training data.
Neural network is an information processing system which is formed by a large number of simple processing elements, known as artificial nerves. The input data are multiplied by the corresponding weight and the summation are entered into neurons. Each neuron has an activation function. Inputs pass to the activation function and determine the output of neurons. The behavior of neural network is related to communication between nodes. Using training data, the designed ANN can be adjusted in an iterative procedure to determine optimal parameters of ANN. Then for an unknown input, we can compute corresponding output using the trained ANN. The neurons of input and output layers are determined according to the number of input and output parameters. The number of neurons in the hidden layer can be determined by trial and error through minimizing total error of the ANN. For this minimization, each ANN parameter’s share in the total error should be computed which can be achieved by a back-propagating algorithm.
Radial basis function neural network (RBFNN) is known from the approximation theory as it is applied to the real multivariate interpolation problem. RBFNN is popularized by Moody and Darken (1989), and many researchers suggested it as an alternative ANN structure to MLP. RBFNN is very useful for function approximation and classification problems because of its more compact topology and faster learning speed. RBFNN is configured with three layers. An input layer consists of source neurons and distributes input vectors to each of the neurons in the hidden layer without any multiplicative factors. The single hidden layer has receptive field units (hidden neurons) each of which represents a nonlinear transfer function called a basis function. The output layer produces a linear weighted sum of hidden neuron outputs and supplies the response of RBFNN.
Due to the nonlinearity of ionosphere physical properties, in this paper, multi-layer perceptron artificial neural networks (MLP-ANN) and RBFNN used to model and predict the spatial and temporal variations of vertical TEC (VTEC) over Iran. The used model is able to estimate and predict the VTEC within and also near the network. For this work, observations of 22 GPS stations in northwest of Iran (360

Keywords

Main Subjects


صیادی، ا، 1387، آشنایی مقدماتی با شبکه‌‌های عصبی مصنوعی، دانشگاه صنعتی شریف.
غفاری رزین، م. ر. و محمدزاده، ع.، 1393، مدل‌سازی‌‌‌ منطقه‌‌ای TEC با استفاده از شبکه‌‌های عصبی مصنوعی و مدل چند جمله‌‌ای در ایران، م. علمی-پژوهشی علوم و فنون نقشه‌برداری، 4(3)، 60-51.
غفاری رزین، م. ر. و مشهدی حسینعلی، م، 1388، تعیین دانسیته الکترونی لایه یون‌سپهر در منطقه ایران با استفاده از تکنیک توموگرافی براساس مشاهدات GPS ایران سراسری، نشریه فناوری اطلاعات مکانی، شماره اول، 12-26.
غفاری رزین، م. ر. و مشهدی حسینعلی، م، 1390، مدل‌سازی‌‌‌ 3بعدی تغییرات چگالی الکترونی یون‌سپهردر سه فصل مختلف با استفاده از مشاهدات GPS شبکه ژئودینامیک ایران، فصلنامه علمی-پژوهشی علوم و فناوری فضایی، 4(1 و 2)، 1-12.
 
Amerian, Y., Mashhadi Hossainali, M., Voosoghi, B. and Ghaffari Razin, M. R., 2010, Tomographic reconstruction of the ionospheric electron density in term of wavelets, Journal of Aerospace Science and Technology, 7(1), 19-29.
Amerian, Y., Hossainali, M. M. and Voosoghi, B., 2013, Regional improvement of IRI extracted ionospheric electron density by compactly supported base functions using GPS observations, J. Atmos Sol Terr Phys., 92, 23-30, doi: 10.1016/j.jastp.2012.09.011.
Bishop C M., 2005, Neural Networks for Pattern Recognition; Oxford University Press, New York, NY, 504p.
Conway, A. J., Macpherson, K. P., Blacklaw, G. and Brown, J. C., 1998, A neural network prediction of solar cycle 23, J. Geophys. Res., 103(A12), 29733-29742.
Cander, R., 1998, Artificial neural network applications in ionospheric studies, Annali di Geofisica, 5-6.
Ghaffari Razin, M. R., Voosoghi, B. and Mohammadzadeh, A., 2015, Efficiency of artificial neural networks in map of total electron content over Iran, Acta Geod Geophys., doi: 10.1007/s40328-015-0143-3.
Ghaffari Razin, M. R. and Voosoghi, B., 2016, Modeling of ionosphere time series using wavelet neural networks (case study: N-W of Iran), Advances in Space Research. doi: http://dx.doi.org/10.1016/j.asr. 2016.04.006.
Ghaffari Razin, M. R., 2015, Development and analysis of 3D ionosphere modeling using base functions and GPS data over Iran, Acta Geod Geophys., doi: 10.1007/s40328-015-0113-9, 51(1), 95-111.
Ghaffari Razin, M. R. and Voosoghi, B., 2016, Regional ionosphere modeling using spherical cap harmonics and empirical orthogonal functions over Iran. Acta Geod Geophys, doi: 10.1007/s40328-016-0162-8.
Ghaffari Razin, M. R. and Voosoghi, B., 2016, Regional application of multi-layer artificial neural networks in 3-D ionosphere tomography. Advances in Space Research. http://dx.doi.org/10.1016/j.asr.2016.04.029.
Habarulema, J. B., McKinnell, L. A. and Cilliers, P. J., 2007, Prediction of global positioning system total electron content using neural networks over South Africa, J. Atmos. Sol. Terr. Phys., 69(15), 1842-1850.
Hernandez-Pajares, M., Juan, J. and Sanz, J., 1997, Neural network modelling of the ionospheric electron content at global scale using GPS, Radio Sci., 32, 1081-1090.
Haykin, S., 1994, Neural Networks, a comprehensive Foundation, Macmillan College Publishing Company, New York.
Komjathy, A., 1997, Global ionospheric total electron content mapping using the global positioning system, Ph.D. thesis, Dep. of Geod. and Geomatics Eng., Univ. of New Brunswick, Fredericton, New Brunswick, Canada.
Leandro, R. F. and Santos, M. C., 2007, A neural network approach for regional vertical total electron content modelling, Stud. Geophys. Geod., 51(2), 279-292.
Moon, Y., 2004, Evaluation of 2-dimensional ionosphere models for national and regional GPS networks in Canada, Master’s thesis, Univ. of Calgary, Calgary, Alberta, Canada.
Moody, J. and Darken, C., 1998, Fast learning in networks of locally-tuned processing units, Neural Comput., 1(2), 281-294.
McKinnell, L., 2002, A neural network based ionospheric model for the Bottomside electron density profile over Grahamstown South Africa, Ph.D. Thesis, Rhodes Université.
Mars, P., Chen, J. R. and Nambiar, R., 1996, Learning algorithms: theory and applications in signal processing, Control and
Communications, CRC Press, Boca Raton, Florida.
Orus, R., 2005, Improvement of global ionospheric VTEC maps by using Kriging interpolation technique, J. Atmos. Sol. Terr. Phys., 67, 1598-1609.
Powell, M. J. D., 1987, Radial basis functions for multivariate interpolation: a review; in: algorithms for approximation (eds) Mason, J. and Cox, M., Clarendon Press, Oxford, 143-167.
Rodrigo, F., Leandro, R. F., 2007, A New Technique to TEC Regional Modeling using a Neural Network. Geodetic Research Laboratory, Department of Geodesy and Geomatics Engineering, University of New Brunswick, Fredericton, Canada.
Schaer, S., 1999, Mapping and predicting the Earth’s ionosphere using the global positioning system, Ph.D. thesis, Astronomical Institute, University of Berne, Berne Switzerland.
Seeber, G., 2003, satellite geodesy: foundations. methods and applications, Walter de Gruyter, Berlin and New York, 53.
Svozil, D., KvasniEka, V. and Pospichal, J., 1997, Introduction to multi-layer feed-forward neural networks, Chemometrics and Intelligent Laboratory Systems, 39, 43-62.
Sayin, I., Arikan, F. and Arikan, O., 2008, Regional TEC mapping with random field priors and Kriging, Radio Sci., 43, RS5012, doi: 10.1029/2007RS003786.
Sarma, A. and Mahdu, T., 2005, Modelling of foF2 using neural networks at an equatorial anomaly station. Curr. Sci., 89(7), 1245-1247.
Simpson, P. K., 1990, Artificial neural systems: foundations, paradigms, applications, and implementations, Pergamon Press, New York.
Tulunay, E., Senalp, E. T., Radicella, S. M. and Tulanay, Y., 2006, Forecasting total electron content maps by neural network technique., Radio Sci. 41, doi: 10.1029/2005RS003285.
Xenos, T. D., Kouris, S. S. and Casimiro, A., 2003, Time-dependent prediction degradation assessment of neural-networks-based TEC forecasting models, Nonlinear Proc. Geophys., 10, 585-587.
 
Wielgosz, P., Brzezinska, D. and Kashani, I., 2003, Regional ionosphere mapping with Kriging and multiquadratic method, J. Global Pos. Syst., 2, 48-55.
Yilmaz, A., Akdogan, K. E. and Gurun, M., 2009, Regional TEC mapping using neural networks, Radio Sci., 44, RS3007, doi: 10.1029/2008RS004049.
Yeung, D. S., Cloete, I., Shi, D. and Ng, W. W. Y., 2010, Sensitivity analysis for neural networks; Springer-Verlag, Berlin Heidelberg, 86p.