Yapay sinir a?i ve uydu datalari kullanilarak güneş radyasyonunun tahmini

In this study, a model was developed to estimate monthly-average daily solar radiation over Turkey. Artificial neural network method was used in improved model. The solar radiation values of 53 different locations over Turkey were taken as data. Land surface temperature, altitude, latitude, longitude and month values were used as input variables for modeling artificial neural network and solar radiation has been estimated as output of artificial neural network model. The RMSE, MBE and correlation coefficient for the best developed model were calculated as 1.550 MJ/m2, -0.172 MJ/m2 and 0.972, respectively. © 2017 IEEE.