Three meteorological parameters namely sunshine duration, maximum ambient temperature
and relative humidity were used to estimate monthly average global solar irradiation on a
horizontal surface for Gusau, Nigeria. The study used artificial neural networks (ANN) for
the estimation. Results have shown good agreement between the estimated and measured
values of global solar irradiation. A correlation coefficient of 0.9996 was obtained with a
maximum percentage error of 0.8512 and root mean square error of 0.0029. The
comparison between the ANN and some existing empirical models has shown the advantage
of the proposed ANN prediction model.
