Modeling of solar radiation using remote sensing and artificial neural network in Turkey

Artificial neural networks (ANNs) were used to estimate solar radiation in Turkey (26-45°E, 36-42°N) using geographical and satellite-estimated data. In order to train the Generalized regression neural network (GRNN) geographical and satellite-estimated data for the period from January 2002 to December 2002 from 19 stations spread over Turkey were used in training (ten stations) and testing (nine stations) data. Latitude, longitude, altitude, surface emissivity for ɛ4, surface emissivity for ɛ5, and land surface temperature are used in the input layer of the network. Solar radiation is the output. Root Mean Square Error (RMSE) and correlation coefficient (R2) between the estimated and measured values for monthly mean daily sum with ANN values have been found as 0.1630 MJ/m2 and 95.34% (training stations), 0.3200 MJ/m2 and 93.41% (testing stations), respectively. Since these results are good enough it was concluded that the developed GRNN tool can be used to predict the solar radiation in Turkey.