Bello, S.A.Orisatuyi, M.J.Yusuf, K.A.Shehu, S.J.Oyinkanola, L.O.A.Ige, S.O.Lawal, S.K.Oladipo, M.2023-05-032023-05-032022-12Bello, S.A. Orisatuyi, M.J. Yusuf, K.A. Shehu, S.J. Oyinkanola, L.O.A. Ige, S.O. Lawal, S.K. Oladipo, M. (2022). Performance Estimation of Neural Network TEC Prediction Models over Toro Station, NIP Journal, 31(2), 160-168https://uilspace.unilorin.edu.ng/handle/20.500.12484/9479This 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 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.enNeural network; ionosphere, Total electron content, GNSS, ionosondeArticle