Evaporation Modeling of Free Surface Water Using SVM and LSSVM Models

Evaporation is one of the most important and influential processes in the water cycle. Evaporation results in the loss of more than half of the precipitation in arid areas. Evaporation pan is used as an indicator for determining the evaporation of lakes and reservoirs due to the ease of interpreting its data around the world. On the other hand, the study on evaporation from the pan and the rate of evapotranspiration of the reference plant shows that there is a linear and direct relation between evaporation from the pan and evapotranspiration of the reference plant. Therefore, by correctly recording the amount of evaporation from the bath, the evapotranspiration of the reference plant can be estimated. The empirical relationships presented for estimating evaporation from free surfaces, considering meteorological parameters as inputs, are highly diverse. The accuracy of empirical relationships varies in different regions and needs calibration in each area. Also, it does not have high accuracy and access to all input parameters is difficult or time consuming. The aim of this study was to evaluate the efficiency of backup vector machine and least squares support vector machine for estimating evaporation from free water level in Golestan province. In this research, three synoptic stations (Kelaleh, Gorgan and Bandar-Turkman) were used for daily weather data for 17 years (1997-2015). The results showed that the input patterns with relative humidity input parameters, maximum relative humidity, wind speed and sunshine hours with the highest R2 and the lowest RMSE and MBE.