Evaporation modelling using soft computing techniques

Evaporation, which is one of the most important components of the hydrological cycle, is of great importance for developing, planning, operating, and managing water resources. In the present study, the average weekly evaporation and other hydrometeorological data measured by Manasgoan [1] between 1990 and 2004 were modelled using extreme learning machine (ELM), minimax probability machine regression (MPMR), and Gaussian process regression (GPR) methods. Wind speed, air temperature, relative humidity, and the number of sunshine hours were used as model input, and evaporation was the output. The correlation coefficient, mean absolute error (MAE), root mean square error (RMSE), and performance index were used as performance criteria in the evaluation of the model results. The model results indicated that the Gaussian process regression (GPR) model is more accurate and provides more successful results compared to other methods. © by PSP