Estimating the Hourly Reference Evapotranspiration with FuzzyInference Systems and Limited Weather Data

Evapotranspiration is the most important part of the hydrological cycle, which playsa key role in water resource management, crop yield simulation, and irrigationscheduling. Therefore, developing a cost-effective and precise model is essential forestimating hourly grass crop reference evapotranspiration (ETo). In this study thepotential of the fuzzy inference system (FIS) is investigated as a simple technique formodeling hourly ETo obtained using the FAO-56 Penman-Monteith and ASCEequations. Then, combinations of efficient hourly climatic data namely temperature,wind speed, relative humidity and solar radiation were used as inputs to the fuzzymodel. Four fuzzy models were developed based on different combinations of inputs.Common statistics such as Mean square error, average absolute relative error anddetermination coefficient and two more statistics of Jacovides (t) and R2/t are used ascomparison criteria for evaluation of the model performance. Here, Training andtesting fuzzy models were done with Fariman meteorological data – an arid region inthe northeast of Iran. The fuzzy model whose inputs are solar radiation, airtemperature, relative humidity and wind speed, yield the highest correlation andcompatibility to reference models of FAO-56 PM and ASCE, based on commonstatistics. Whereas, the fuzzy model whose inputs are solar radiation, air temperatureand relative humidity, are selected as the best model based on combination ofcommon and additional statistics. The fuzzy model with two inputs namely solarradiation and relative humidity has acceptable results, too. The results show that solarradiation is the most effective parameter on hourly reference evapotranspiration andtemperature, relative humidity and wind speed were other effective parameters,respectively. These results for training and testing phase are alike. It was found thatthe developed fuzzy models could be successfully employed in estimating the hourlyETo with a limited weather data.

Keywords:

Fuzzy Inference System , Hourly Reference , Evapotranspiration , Asce Model , Fao-56 Penman-Monteith Model