Utilization of new computational intelligence methods to estimate daily Evapotranspiration of wheat using Gamma pre processing

Abstract

Estimation of evapotranspiration (ET) is needed in water resources management, scheduling of farm irrigation, and environmental assessment. Hence, in practical hydrology, it is often crucial to reliably and constantly estimate evapotranspiration. Accordingly, 3 artificial intelligence (AI) techniques comprising adaptive neuro-fuzzy inference system (ANFIS), artificial neural network (ANN) and adaptive neuro-fuzzy inference- wavelet (ANFIS-Wavelet) were applied in to estimate wheat crop evapotranspiration (ET_c). A case study in a Dashtenaz region located in Mazandaran, Iran, was conducted with weather daily data, including maximum temperature, minimum temperature, maximum relative humidity, minimum relative humidity, wind speed, and solar radiation since 2003 to 2011. The daily climatic data from Dashtenaz stations, (8 stations), were used as inputs AI models for estimating ET₀.The assessments of the AI models were compared with the wheat crop evapotranspiration (ET_c) values measured by crop coefficient approach and standard FAO-56 Penman–Monteith equation. Similarly, determination coefficient (R²), Nash–Sutcliffe (C_NS) efficiency coefficient model and root mean squared error (RMSE) were applied to compare the models performance and to decide on the best one. The outcomes attained with the ANFIS-Wavelet model (with trapezoidal member function’s combination with Mayer wavelet) were better than ANN and ANFIS models for ET_c estimation and confirmed the potential of this technique to provide useful tool in ET_c modeling.