Document Type : Research Paper
Authors
Abstract
Evapotranspiration is one of the important components of hydrological
cycle whose accurate estimate is needed for design and management of
irrigation systems, simulation of crops products, and programming water
resources management. In this research, to predict monthly reference
evapotranspiration, ANFIS and GP models were employed and 38 years
(1973-2010) of data were collected from six synoptic weather stations
located in the northwest of Iran. At first, monthly reference
evapotranspiration was estimated by FAO-Penman-Montieth method for
the selected stations and was considered as the output of GP and ANFIS
models. Then, a regression equation between effective meteorological
parameters and evapotranspiration was fitted and different input patterns
for the models were determined. Relative humidity as the less effective
parameter was deleted from input of the models. Also, in this study, to
investigate effect of “memory” on prediction of evapotranspiration, one,
two, three and four months lags were used as the input of the models.
Results showed that both models estimated monthly evapotranspiration
with high accuracy, but ANFIS model was better than GP model.
)