Using Intelligence Models to Estimate Evapotranspiration

Abstract

Exact estimation of evapotranspiration is an important parameter in water cycle, study, design and management of rrigation systems. In this study, the efficiency of intelligent models such as fuzzy rule base, fuzzy regression and rtificial Neural Networks for estimating daily evapotranspiration has been examined and the results are compared to real data measured by lysimeter on the basis of a grass reference crop. Using daily climatic data from Ekbatan station in Hamadan in western Iran, including maximum and minimum temperatures, maximum and minimum relative humidities, wind speed and sunny hours, evapotranspiration was estimated by the aforementioned intelligent models. The predicted evapotranspiration values from fuzzy rule base, fuzzy linear regression and artificial neural network provided root ean square error (RMSE) of 0.72, 0.86 and 0.74 mm/day and determination coefficient (R2) of 0.88, 0.86 and 0.84, respectively. The fuzzy rule base was hence found to be the most appropriate method employed for estimating evapotranspiration.