Modeling the monthly pan evaporation rates using artificial intelligence methods: a case study in Iraq

In arid areas, the estimation of evaporation rates plays a considerable role on both water resources management and agricultural activities. Hence, it is of utmost importance to determine the best model to predict these rates. This study investigates the applicability of using quantile regression forest in predicting the pan evaporation. The model was configured using data from three different meteorological stations located in arid to semi-arid climates in Iraq. These stations were in the cities of Baghdad, Basrah, and Mosul, which are located in the middle, south, and north of the country, respectively. The performance of quantile regression forests was compared with three kinds of artificial intelligence methods i.e. random forests, support vector machine, and artificial neural network in addition to the conventional multiple linear regression models. The maximum temperature (°C), minimum temperature (°C), relative humidity (%), and wind speed (m/sec) were used as input parameters to the predictive models. The collected data (from 1990 to 2013) was randomly partitioned into two periods; 75% for calibration and 25% for validation. The fivefold cross validation was used during the calibration stage for better model predictability. The results were evaluated using three performance criteria: determination coefficient (R2), root mean square error (RMSE), and Nash and Sutcliff coefficient efficiency (NSE). Results showed that the quantile regression forests model attained the optimum performance among the evaluated methods. The value of R2, RMSE, and NSE during validation was 0.99, 17.96 mm, and 0.99 at Baghdad; 0.98, 23.36 mm, and 0.98 at Basrah; and 0.99, 14.44 mm, and 0.99 at Mosul, respectively. Therefore, this method is the most appropriate one to use for predicting evaporation rates in arid to semi-arid climates.