Sensitivity Analysis of the Effective Parameters upon Daily Evaporation Using Garson Equation and Artificial Neural Network (Case Study:Tabriz city)

This study performs a sensitivity analysis to evaluatethe meteorological parametersthat affect daily pan evaporation rate. To this end, five meteorological parameters namely, daily mean temperature, relative humidity, sunshine hours, solar radiation, wind speed and pressure for period of 1386 to 1390 were used at the Tabriz City, Iran. At first, the pan evaporation rate was estimated using Artificial Neural Network (ANN) and the best structure of the ANN was distinguished. Then, weight matrix of selected structure of the network along with the Garson algorithm were used for sensitivity analysis of the input parameters and determine relative importance of the input parameters. The results indicated that the daily mean temperature and relative humidityare the most effective variables. However, the sunshine hours, solar radiation, wind speed and pressure have less effect on the evaporation rate at the Tabriz station.