ANGEO Annales Geophysicae ANGEO 1432-0576 Copernicus GmbH Göttingen, Germany 10.5194/angeo-27-2111-2009 A recurrent neural network approach to quantitatively studying solar wind effects on TEC derived from GPS; preliminary results Habarulema J. B. 1 2 McKinnell L.-A. 1 2 Opperman B. D. L. 1 Hermanus Magnetic Observatory, 7200 Hermanus, South Africa Department of Physics and Electronics, Rhodes University, 6140, Grahamstown, South Africa 07 05 2009 27 5 2111 2125 This is an open-access article ditributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. This article is available from http://www.ann-geophys.net/27/2111/2009/angeo-27-2111-2009.html The full text article is available as a PDF file from http://www.ann-geophys.net/27/2111/2009/angeo-27-2111-2009.pdf

This paper attempts to describe the search for the parameter(s) to represent solar wind effects in Global Positioning System total electron content (GPS TEC) modelling using the technique of neural networks (NNs). A study is carried out by including solar wind velocity (<I>V<sub>sw</sub></I>), proton number density (<I>N<sub>p</sub></I>) and the <I>B<sub>z</sub></I> component of the interplanetary magnetic field (IMF <I>B<sub>z</sub></I>) obtained from the Advanced Composition Explorer (ACE) satellite as separate inputs to the NN each along with day number of the year (DN), hour (HR), a 4-month running mean of the daily sunspot number (R4) and the running mean of the previous eight 3-hourly magnetic A index values (A8). Hourly GPS TEC values derived from a dual frequency receiver located at Sutherland (32.38&deg; S, 20.81&deg; E), South Africa for 8 years (2000–2007) have been used to train the Elman neural network (ENN) and the result has been used to predict TEC variations for a GPS station located at Cape Town (33.95&deg; S, 18.47&deg; E). Quantitative results indicate that each of the parameters considered may have some degree of influence on GPS TEC at certain periods although a decrease in prediction accuracy is also observed for some parameters for different days and seasons. It is also evident that there is still a difficulty in predicting TEC values during disturbed conditions. The improvements and degradation in prediction accuracies are both close to the benchmark values which lends weight to the belief that diurnal, seasonal, solar and magnetic variabilities may be the major determinants of TEC variability.

 References Biktash, L Z., Maruyama, T., and Nozaki, K.: The solar wind control of the equatorial ionosphere dynamics during geomagnetic storms, Adv. Space Res., 41, 562–568, 2008. Bishop, C M.: Neural Networks for Pattern Recognition, Oxford University Press Inc., New York, 1995. Bodén, M.: A guide to recurrent neural networks and backpropagation, in: In the Dallas project, SICS Technical Report T2002:03, SICS, 2002. Buonsanto, M J.: Ionospheric storms: A review, Space Sci. Rev., 88, 563–601, 1999. Elman, J L.: Finding Structure in Time, Cognitive Science, 14, 179–211, 1990. Fausett, L.: Fundamentals of Neural Networks; Architectures, Algorithms and Applications, Prentice-Hall, Inc. New Jersey, 07632, 1994. Fedrizzi, M., de~Paula, E R., Langley, R B., Komjathy, A., Batista, I S., and Kantor, I.: Study of the March 31, 2001 magnetic storm effects on the ionosphere using GPS data, Adv. Space Res., 36, 534–545, 2005. Girish, T E., Jayachandran, B., and Shamsudeen, S P.: Influence of solar wind on the TEC variations at mid and subauroral latitudes during sunspot maximum, Acta geod. Geoph. Hung., 32(3–4), 287–292, 1997. Habarulema, J B.: A feasibility study into Total Electron Content prediction using Neural Networks, Master's thesis, Rhodes University, Grahamstown, South Africa, 2007. Habarulema, J B., McKinnell, L A., and Cilliers, P J.: Prediction of global positioning system total electron content using neural networks over South Africa, J. Atmos. Solar Terr. Phys., 69, 1842–1850, 2007. Habarulema, J B., McKinnell, L.-A., Cilliers, P J., and Opperman, B. D L.: Application of neural networks to South African GPS TEC modelling, Adv. Space Res., in press, doi:10.1016/j.asr.2008.08.020, 2009. Haykin, S.: Neural Networks, A Comprehensive Foundation, Macmillan College Publishing Company, 1994. Hernandez-Pajares, M., Juan, J., and Sanz, J.: Neural network modelling of the ionospheric electron content at global scale using GPS, Radio Sci., 32, 1081–1090, 1997. Hofmann-Wellenhof, B., Lichtenegger, H., and Collins, J.: Global Positioning System Theory and Practice, Springer-Verlag Wien New York, 1992. Jakowski, N., Hocke, K., Schluter, S., and Heise, S.: Space weather effects detected by GPS based TEC monitoring, in: Workshop on Space Weather, WPP-155, ESTEC, Noordwijk,, pp. 241–244, 1999. Kouris, S S., Fotiadis, D N., and Zolesi, B.: Specifications of the F-region variations for quiet and disturbed conditions, Phys. Chem. Earth, 24, 1999. Langley, R B.: GPS, the Ionosphere, and the Solar Maximum, GPS World, 11, 44–49, 2000. Li, G., Ning, B., Zhao, B., Liu, L., Liu, J Y., and Yumoto, K.: Effects of geomagnetic storms on GPS ionospheric scintillations at Sanya, J. Atmos. Solar-Terr. Phys., 70(7), 1034–1045, 2008. Lundestedt, H.: Solar activity modelled and forecasted: A new approach, Adv. Space Res., 38, 862–867, 2006. Lyon, J G.: The Solar Wind-Magnetosphere-Ionosphere System, Science Rev., 288, 1987–1991, 2000. Marra, S. and Marabito, F C.: A New Technique for Solar Activity Forecasting using Recurrent Elman Networks, Int. J. Cognitive Intelligence, 3, 8–13, 2005. Meza, A., Zele, M. A V., Brunini, C., and Cabassi, I R.: Vertical total electron content and geomagnetic pertubations at mid- and sub-auroral southern latitudes during geomagnetic storms, J. Atmos. Solar Terr. Phys., 67, 315–323, 2005. Opperman, B.: Reconstructing Ionospheric TEC over South Africa using signals from a Regional GPS network, PhD thesis Rhodes University, Grahamstown, South Africa, 2007. Opperman, B. D L., Cilliers, P J., McKinnell, L A., and Haggard, R.: Development of a regional GPS-based ionospheric TEC model for South Africa, Adv. Space Res., 39, 808–815, 2007. Poole, A W. and McKinnell, L.-A.: On the predictability of foF2 using neural networks, Radio Sci., 1, 225–234, 2000. Sethia, G., Deshpande, M R., and Rastogi, R G.: The solar wind influences plasmasphere electron content, Nature, 276, 482, doi:10.1038/276482a0, 1978. Stankov, S M., Kutiev, I., Jakowski, N., and Wehrenpfennig, A.: A new method for total electron content forecasting using Global Positioning System measurements, in: Proc. ESA Space Weather Workshop, Noordwijk, The Netherlands, pp. 169–172, 2001. Tulunay, E., Senalp, E., Radicella, S., and Tulunay, Y.: Forecasting total electron content maps by neural network technique, Radio Sci., 41, doi:10.1029/2005RS003285, 2006. Vandegriff, J., Wagstaff, K., and ~Ho, G. J P.: Forecasting space weather: Predicting interplanetary shocks using neural networks, Adv. Space Res., 36, 2323–2327, 2005. Weigel, R S., Vassiliadis, D., and Klimas, A J.: Coupling of the solar wind to temporal fluctuations in ground magnetic fields, Geophys. Res. Lett., 29, 19, doi:10.1029/2002GL014740, 2002. Weigel, R S., Klimas, A J., and Vassiliadis, D.: Solar wind coupling to and predictability of ground magnetic fields and their time derivatives, J. Geophys. Res., 108(A7), 1298, doi:10.1029/2002JA009627, 2003. Wu, J.-G. and Lundstedt, H.: Neural network modeling of solar wind-magnetosphere interaction, J. Geophys. Res., 102(A7), 14457–14466, 1997.