Estimation of daily evaporation using Artificial Neural Networks

Abstract

In recent years using of Artificial Neural Networks (ANN's) has been increasing in hydrology engineering. In this study, Feed Forward Backpropagation Neural Network (FFNN) and Radial Basis Artificial Neural Networks (RBNN) models have been used to estimate daily evaporation amount for Lake Sapanca and compared,with Penman-Monteith model. FFNN and RBNN models have been applied to daily evaporation estimation depending on daily min and max temperature, wind speed, relative humidity, real solar period and maximum solar period. When performances of the FFNN, RBNN and PM models compared; correlation coefficient R(1)= 0.651, R(2)= 0.716 and R(3)= 0.700; Mean Absolute Error, MAE(1)= 68.540%, MAE(2)=59.484% and MAE(3)=59.207%; Mean Square Error MSE(1)=.2.674, MSE(2)= 2.512 and MSE(3)= 2.557 are found respectively. It is clearly seen that FFNN model yields the best result.