The performance of fuzzy regression method for estimating of reference evapotranspiration under controlled environment

Abstract

With the objective of evaluating the performance of fuzzy regression method for estimating the reference evapotranspiration in greenhouse, a lysimeter study was conducted to determine the evapotranspiration (ETo) rates for grass crop. Daily outputs from model have been tested against reference evapotranspiration data computed by the lysimeter to assess the accuracy of the model. The estimated ETo values from a fuzzy regression model using five input parameters, including maximum and minimum temperature, mean relative humidity, wind speed and solar radiation were obtained with RMSE = 0.68 mm/day, R2 = 0.98. The accuracy of fuzzy 1 was the best but the accuracy of the fuzzy 3 was the worse for estimating daily evapotranspiration. The RMSE values of fuzzy 1, fuzzy 2, Fuzzy 3 were 0.68, 0.99 and 1.307, respectively. Thus, fuzzy 1 approaches work well for the data set used in greenhouse condition.