PERFORMANCE ESTIMATION OF NEURAL NETWORK TEC PREDICTION MODELS OVER TORO STATION

Article Sidebar

PDF
Published: Dec 30, 2022
Keywords:
Neural network, Ionosphere, Total Electron Content, GNSS, Ionosonde

Main Article Content

S. A. Bello
M. J. Orisatuyi
K. A. Yusuf
S. J. Shehu
L. O. A. Oyikanola
S. O. Ige
S. K. Lawal
M. Oladipo

Abstract

This paper presents the prediction of hourly Total Electron Content (TEC) obtained from a Global navigation satellite system (GNNS) receiver at Toro station (10.12°N, 9.12°E), Bauchi, Nigeria and developed an ionospheric model using a neural network (NN) by utilizing the TEC data. The studied period is based on the available data during the period from 2014 to 2016. Four neural network configurations with different inputs which include the day number, hour number, sunspot number (SSN) and solar radio flux (F10.7) were used. Each configuration was trained with Total Electron Content (TEC) data between the years 2014 to 2016. The best neural network used for prediction had the least mean squared error (MSE) of 8.68 TECU and root mean squared error (RMSE) value of 2.95 TECU. The comparison was made between TEC from the observatory station and predicted TEC from the best neural network (NN) model. The developed NN model was used to predict some selected days that fall between the four astronomical seasons. The results show that the model performed well on the 17th of March 2014 with an MSE of 12.35 TECU and an RMSE value of 3.11 TECU.

Downloads

Download data is not yet available.

Article Details

How to Cite
Bello, S. A., Orisatuyi, M. J., Yusuf, K. A., Shehu, S. J., Oyikanola, L. O. A., Ige, S. O., Lawal, S. K., & Oladipo, M. (2022). PERFORMANCE ESTIMATION OF NEURAL NETWORK TEC PREDICTION MODELS OVER TORO STATION. Nigerian Journal of Physics, 31(2), 160–168. Retrieved from https://njp.nipngr.org/index.php/njp/article/view/71
Issue
Vol. 31 No. 2 (2022): Nigerian Journal of Physics - Vol. 31 No. 2
Section
Articles

References

Akala, A. O., Seemala, G. K., Doherty, P. H., Valladares, C. E., Carrano, C. S., Espinoza, J., and Oluyo, S. (2013): Comparison Of Equatorial GPS-TEC Observations Over an African Station and an American Station During the Minimum and Ascending Phases of Solar Cycle 24. Annales Geophysicae, 31(11), 2085-2096.

Habarulema, J.B., McKinnell, L.-A., Cilliers, P.J., and Opperman, B.D. (2009):Application of

Neural Networks to South African GPS TEC Modelling. Advances in Space Research, 43, 1711-20.

Kişi, Ö. and Uncuoğlu, E. (2005): Comparison of Three Back-Propagation Training Algorithms for Two Case Studies. Indian Journal of Engineering & Materials Sciences,12, 434-442.

Kumar Dabbakuti, J. R. K., Kowshik Chandu, Y., Sai Koushik Reddy, A., and Prabu, A. V. (2021). Retrieve, Processing and Analysis of Global Positioning System Derived Ionospheric Total Electron Content Using IGS Products. Advances in Electrical and Computer Technologies,719-726.

Muslim, B., Husin, A., and Efendy, J. (2018):Short Term Single Station GNSS TEC Prediction Using Radial Basis Function Neural Network. Journal of Physics: Conference Series, 1005, 012042.

Ogwala, A., Somoye, E.O., Panda, S.K., Ogunmodimu, O., Onori, E., Sharma, S.K., Okoh, D. and Oyedokun, O., (2021): Total Electron Content at Equatorial and Low-, Middle-and High-Latitudes in African Longitude Sector and Its Comparison with IRI-2016 and IRI-PLAS 2017 Models. Advances in Space Research, 68(5), 2160-2176.

Okoh, D., Obafaye, A., Rabiu, B., Seemala, G., Kashcheyev, A., and Nava, B. (2021): New Results of Ionospheric Total Electron Content Measurements from a Low-Cost Global Navigation Satellite System Receiver and Comparisons with Other Data Sources. Advances in Space Research 68, 3835-45.

Oyeyemi, E., Poole, A., and McKinnell, L. (2005): On the Global Model for foF2 Using Neural Networks. Radio Science 40, 1-15.

Poole, A.W. and McKinnell, L.A. (2000): On the predictability of f0F2 using neural networks. Radio Science 35, 225-34.

Rishbeth, H. and Garriott, O.K. (1969): Introduction to Ionosphere Physics. Academic Press, New York.

Seemala, G. and Valladares, C. (2011): Statistics of Total Electron Content Depletions Observed Over the South American Continent for the Year 2008. Radio Science, 46, 1-14.

Sethi, N., Dabas, R., Bhawre, P., and Sarkar, S. (2009): Bottomside Profile Shape Parameters During Low Solar Activity and Comparisons With IRI-2007 Model. Journal of Atmospheric and Solar-Terrestrial Physics, 71, 1935-42.

Siemsen, E., Roth, A., and Oliveira, P. (2010): Common Method Bias in Regression Models With Linear, Quadratic, and Interaction Effects. Organizational Research Methods 13, 456-76.

Sivavaraprasad, G., Deepika, V., SreenivasaRao, D., Kumar, M.R., and Sridhar, M. (2020): Performance Evaluation of Neural Network TEC Forecasting Models Over Equatorial Low-Latitude Indian GNSS Station. Geodesy and Geodynamics, 11, 192-201.

Sur, D., Das, A., and Paul, A. (2012): Neural Network Based TEC Model Using Multistation GPS-TEC Around the Northern Crest of Equatorial Ionization Anomaly. 2012 5th International Conference on Computers and Devices for Communication (CODEC). IEEE, 1-4.

Van Aelst, S., Khan, J.A., and Zamar, R.H. (2008): Fast Robust Variable Selection. COMPSTAT 2008: Proceedings in Computational Statistics, 359-7.

Zeng, W., Zhang, X., and Huang, Z. (1997): Ionospheric Absorption Effects of the Solar Eclipse of 24 October 1995. Terrestrial Atmospheric Ocean. Science, 8, 233-7.

Zolesi, B. and Cander, L.R. (2013): Ionospheric Prediction and Forecasting. Springer Berlin Heidelberg.

Zou, S., Moldwin, M.B., Coster, A., Lyons, L.R. and Nicolls, M.J. (2011): GPS TEC Observations of Dynamics of the Mid-Latitude Trough During Substorms. Geophysical Research Letters, 38(14), 1-7