Artificial Neural Network-Based Modeling for Monthly Average Global Solar Radiation Estimation in South East Nigeria

Reliable estimation of global solar radiation (GSR) is essential for the proper planning and performance evaluation of solar power systems. This research presents a neural network–based approach for estimating monthly mean GSR across South East Nigeria, covering Enugu, Imo, Ebonyi, Anambra, and Abia States. Twenty years of meteorological records (2005–2025), including air temperature, relative humidity, and wind speed, were utilized for model development. A feedforward multilayer perceptron trained using the backpropagation technique was implemented for the prediction task.
Model evaluation indicates good agreement between predicted and observed values, with a mean absolute percentage error (MAPE) of less than 5%, a coefficient of determination (R²) of 0.95451, and a root mean square error (RMSE) of 0.32 MJ/m²/day. The findings demonstrate that the developed model can effectively estimate solar radiation in tropical locations where measured solar data are scarce. This approach can support informed decision-making in the design and expansion of solar energy projects within the region.

Global solar radiation (GSR), Artificial Neural Network (ANN), South East Nigeria, neuralnet, backpropagation algorithm.

1. Aliyu, S., Zakari, A. S., Isma, M., & Ahmed, M. A. (2020). An artificial neural network model for estimating daily solar radiation in Northwest Nigeria. FUOYE Journal of Engineering and Technology, 5(2), 1–5. http://dx.doi.org/10.46792/fuoyejet.v5i2.563 [Google Scholar] [Crossref]

2. Amadi, S. O., Eze, I. A., Enyi, V. S., Nwokolo, S. C., & Kalu, P. N. (2025). Multi-parameter based models for estimating global solar radiation in selected locations in Ebonyi State, Southeastern Nigeria. TRE, 11(2), 213–236. https://doi.org/10.17737/tre.2025.11.2.00191 [Google Scholar] [Crossref]

3. Anuradha, K., Erlapally, D., Karuna, G., Srilakshmi, V., & Adilakshmi, K. (2021). Analysis of solar power generation forecasting using machine learning techniques. In E3S Web of Conferences (Vol. 309, 01163). https://doi.org/10.1051/e3sconf/202130901163 [Google Scholar] [Crossref]

4. Enyi, V. S., et al. (2021). Path loss model predictions for different GSM networks in the University of Nigeria, Nsukka campus environment for estimation of propagation loss. International Journal of Advanced Research in Computer and Communication Engineering, 10(8), 108–115. https://doi.org/10.17148/IJARCCE.2021.10816 [Google Scholar] [Crossref]

5. Fadare, D. A. (2009). Modeling of solar energy potential in Nigeria using an artificial neural network model. Applied Energy, 86, 1410–1422. https://doi.org/10.1016/j.apenergy.2008.12.005 [Google Scholar] [Crossref]

6. Ikemba, et al. (2024). Analysis of solar energy potentials of five selected South-East cities in Nigeria using deep learning algorithms. Sustainable Energy Research, 11(2), 1–29. https://doi.org/10.1186/s40807-023-00096-7 [Google Scholar] [Crossref]

7. Neelamegam, P., & Arasu, V. (2016). Prediction of solar radiation for solar systems by using ANN models with different back propagation algorithms. Journal of Applied Research and Technology, 14, 206–214. https://doi.org/10.1016/j.jart.2016.05.001 [Google Scholar] [Crossref]

8. Nwokolo, S., & Ogbulezie, J. (2017). A critical review of theoretical models for estimating global solar radiation between 2012–2016 in Nigeria. International Journal of Physical Research, 5(2), 60. https://doi.org/10.14419/ijpr.v5i2.8160 [Google Scholar] [Crossref]

9. Yacef, R., et al. (2012). Prediction of daily global solar irradiation data using Bayesian neural network: A comparative study. Renewable Energy, 48, 146–154. https://doi.org/10.1016/j.renene.2012.04.036 [Google Scholar] [Crossref]

• A Review of the Relationship Between Sustainable Energy and the Principle of Energy Resilience: A Case Study of Malaysia