Estimation of Monthly Pan Evaporation using Artificial Neural Network Based on Meteorological Data- Case Study; Southern Coasts of the Caspian Sea

Evaporation is one of the major components of the hydrologic cycle and its accurate estimation is of paramount importance for many studies such as hydrologic water balance and water resources planning and management. Evaporation is a complex and nonlinear phenomenon which depends on several interacting climatological factors. In this study, eight combinations of weather parameters were used as input data for estimating pan evaporation (Ep) for the northern part of Iran. Daily observed weather data for a ten year period (from 1996 to 2005) were used from 8 weather stations located in the southern coasts of the Caspian Sea. This study indicated that the minimum weather data required for estimation of the pan evaporation are maximum and minimum air temperature, relative humidity, wind speed, and sunshine hours. For the data that was studied, the Root Mean Square Error (RMSE) and the coefficient of determination (R2) for the comparison between observed and estimated Ep are 0.32 mm d-1 and 0.93, respectively. A graphical comparison between the observed and the predicted values of Ep showed that 76 percent of the values lie within a scatter of ±15%.