Prediction of Total Electron Content (TEC) using Neural Network over Anomaly Crest Region Bhopal

Abstract In the present work neural network has been developed for the prediction of Vertical Total Electron Content (VTEC) over Bhopal (23.2°N, 77.4°E & MLAT 14.2°N), an equatorial anomaly crest region. The study is based on the VTEC data recorded by a multi-frequency multi-constellation GNSS receiver installed at Bhopal during May 2016 to August 2017. Neural Network (NN) consists of artificial neurons that are used to learn data patterns adjusting weights between input, hidden and output layers by computational modelling. In order to obtain the optimal number of neurons in the hidden layer, the performance of four systems of neural network have been tested. Out of which, the fourth neural network has been used to predict VTEC with 7 input neurons in the present study. The number of hidden layer neurons is a factor that affects the performance of the trained networks. The input layer of the network includes the year, day of the year, hour of the day, geographic latitude, geographic longitude, SSN and IRI NmF2. We have compared the TEC obtained from the neural network prediction (NN TEC), GPS derived TEC (GPS TEC) and TEC from IRI-2016 model (IRI TEC) and analysis has been made. We observed that the Root Mean Square Error (RMSE) decreases with increase in the number of hidden layer neurons. The RMSE comes out to be lowest (1.96 TECU), when the number of hidden layer neurons are 41.The TEC predicted from the NN model and estimated from GPS receiver have same trend at 01:00 and 07:00 UT. The modelled NN TEC values are in good agreement with GPS TEC values for all seasons and 0.99 correlation coefficient was calculated for summer months, but IRI TEC always underestimates GPS TEC in all seasons. The NN model excellently predicted the TEC values of August 2017 by putting the credentials of August 2016 and only 0.55% to 32.16% relative errors were estimated between them whereas it reaches up to 93.86% with IRI TEC. Thus, the result shows that the proposed NN model can predict the diurnal and seasonal GPS TEC more accurate than IRI over anomaly crest region Bhopal. However, the inclusion of IRI-NmF2 as input layer neuron increases the network performance.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  Daniel Okoh,et al.  A regional GNSS-VTEC model over Nigeria using neural networks: A novel approach , 2016 .

[3]  Sandro M. Radicella,et al.  An analytical model of the electron density profile in the ionosphere , 1990 .

[4]  B. Reinisch,et al.  The Improved Two‐Dimensional Artificial Neural Network‐Based Ionospheric Model (ANNIM) , 2018, Journal of Geophysical Research: Space Physics.

[5]  A. Gwal,et al.  An empirical model for IEC over Lunping , 1996 .

[6]  M. J. Homam Initial prediction of Total Electron Content (TEC) At a low latitude station using neural network , 2014, 2014 IEEE Asia-Pacific Conference on Applied Electromagnetics (APACE).

[7]  Marcelo C. Santos,et al.  A neural network approach for regional vertical total electron content modelling , 2007 .

[8]  P. Cilliers,et al.  Modeling of GPS total electron content over the African low-latitude region using empirical orthogonal functions , 2018, Annales Geophysicae.

[9]  Vladimir Truhlik,et al.  The International Reference Ionosphere 2012 – a model of international collaboration , 2014 .

[10]  Pornchai Supnithi,et al.  TEC prediction with neural network for equatorial latitude station in Thailand , 2012, Earth, Planets and Space.

[11]  D. Sreenivasarao,et al.  Performance evaluation of neural network TEC forecasting models over equatorial low-latitude Indian GNSS station , 2020 .

[12]  Dieter Bilitza,et al.  International reference ionosphere: Recent developments , 1986 .

[13]  J.J. Hopfield,et al.  Artificial neural networks , 1988, IEEE Circuits and Devices Magazine.

[14]  Bodo W. Reinisch,et al.  International Reference Ionosphere 2000 , 2001 .

[15]  D. Bilitza,et al.  International Reference Ionosphere 2007: Improvements and new parameters , 2008 .

[16]  Dieter Bilitza,et al.  Goals and status of the International Reference Ionosphere , 1978 .

[17]  P. R. Shreedevi,et al.  Morphological study on the ionospheric variability at Bharati, a polar cusp station in the southern hemisphere , 2019, Journal of Atmospheric and Solar-Terrestrial Physics.

[18]  Ljiljana R. Cander,et al.  Artificial neural network applications in ionospheric studies , 1998 .

[19]  N. Sethi,et al.  Ionospheric modeling for short‐ and long‐term predictions of F region parameters over Indian zone , 2008 .

[20]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[21]  Aly M. El-naggar,et al.  Artificial neural network as a model for ionospheric TEC map to serve the single frequency receiver , 2013 .

[22]  Lee-Anne McKinnell,et al.  Prediction of global positioning system total electron content using Neural Networks over South Africa , 2007 .

[23]  S. K. Mitra,et al.  Ionospheric total electron content (TEC) studies with GPS in the equatorial region , 2007 .

[24]  Mala S. Bagiya,et al.  TEC variations during low solar activity period (2005–2007) near the Equatorial Ionospheric Anomaly Crest region in India , 2009 .

[25]  Bodo W. Reinisch,et al.  International Reference Ionosphere 2016: From ionospheric climate to real‐time weather predictions , 2017 .

[26]  Ronald F. Woodman,et al.  An empirical model of quiet-day ionospheric electric fields at middle and low latitudes , 1980 .

[27]  P. R. Shreedevi,et al.  Variation of the TEC at a dip equatorial station, Trivandrum and a mid latitude station, Hanle during the descending phase of the solar cycle 24 (2014–2016) , 2018, Journal of Atmospheric and Solar-Terrestrial Physics.

[28]  S. Tiwari,et al.  Nighttime enhancements in TEC near the crest of northern equatorial ionization anomaly during low solar activity period , 2011 .

[29]  Eng Leong Tan,et al.  Validation of the IRI-2012 model with GPS-based ground observation over a low-latitude Singapore station , 2014, Earth, Planets and Space.

[30]  Sudhir R. Jain,et al.  Nighttime enhancements in the VTEC at anomaly crest region Bhopal: Solar and magnetic activity effects , 2020 .

[31]  Miguel Pinzolas,et al.  Neighborhood based Levenberg-Marquardt algorithm for neural network training , 2002, IEEE Trans. Neural Networks.

[32]  S. S. Rao,et al.  Ionospheric variations over Chinese EIA region using fo F 2 and comparison with IRI-2016 model , 2018, Advances in Space Research.