Key points are not available for this paper at this time.
Evapotranspiration is considered as one of the fundamental and primary components of paramount significance to hydrological water cycle. But due to global warming, numerous regions especially arid and semi-arid regions are faced with insufficiency of water. Therefore, this research was aimed at forecasting the effect, climate change may have on reference evapotranspiration (ETo) for Girne and Larnaca regions of Cyprus for the next 3 decades (2017 – 2050). CROPWAT 8.0 software computed the past using Penman-Monteith method while Artificial Neural Network (ANN) predict for the future. A three-layer network trained by FFBP (Feed Forward Back Propagation) and LM (Levenberg-Marquardt) optimization algorithm was used. Two approaches were adopted for the study; in the first approach, the input parameters remained static while changing the number of hidden neurons; in the second approach, the inputs varied from 2 to 6 parameters and the hidden neurons doubled the inputs. Determination Coefficient (R2) and Root Mean Square Error (RMSE) were used as the criterion for performance evaluation of the network. The results disclosed that ANN can efficiently predict future ETo in the regions even with limited climate parameters, but the performance significantly increased by adding more inputs, as R2 difference from 0.8959 – 0.9997 and 0.8633 – 0.9996 in the regions were observed.
Abdullahi et al. (Sun,) studied this question.