Comparison of M5 Model Tree and Artificial Neural Network for Estimating Potential Evapotranspiration in Semi-arid Climates

Abstract

Evaporation is a fundamental parameter in the hydrological cycle. This study examines the performance of M5<br />model tree and artificial neural network (ANN) models in estimating potential evapotranspiration calculated by<br />Penman- Monteith and Hargreaves- Samani equations. Daily weather data from two meteorological stations in a<br />semi-arid climate of Iran, namely Kerman and Zahedan, were collected during 1995-2004 and included the mean,<br />maximum and minimum air temperatures, dewpoint, relative humidity, sunshine hours, and wind speed. Results<br />for both stations showed that the performance of the M5 model tree was more accurate (R=0.982 and 0.98 for<br />Penman-Monteith equation and R=0.983 and 0.98 for Hargreaves-Samani equation in Kerman and Zahedan,<br />respectively) than the ANN model (R=0.975 and 0.978 for Penman-Monteith equation and R=0.967 and 0.974 for<br />Hargreaves-Samani equation in Kerman and Zahedan, respectively), but the models' differences were<br />insignificant at a confidence level of 95%. It also performed better at the Zahedan station using the Penman-<br />Monteith equation. The most significant variables affecting the potential evapotranspiration in the case of the<br />Penman–Monteith equation were found to be mean air temperature, sunshine hours, wind speed, and relative<br />humidity. Similarly, for the Hargreaves-Samani equation, the maximum and minimum temperatures, sunshine<br />hours, and wind speed were determined to be the most significant variables. Further studies in other climates are<br />recommended for further analysis.<br /><br />