Improvement of Temperature Based ANN Models for ETo Prediction in Coastal Locations by Means of Preliminary Models and Exogenous Data

This paper reports the application of artificial neural networks for estimating reference evapotranspiration (ETo) as a function of local maximum and minimum air temperatures and exogenous relative humidity and evapotranspiration in twelve coastal locations of the autonomous Valencia region, Spain. The Penman-Monteith model for ETo prediction, as been proposed by the Food and Agriculture Organization of the United Nations (FAO) as the standard method for ETo forecast, has been used to provide the ANN targets. The number of stations where reliable climatic data are available for the application of the Penman-Monteith equation is limited. Thus, the development of more precise predicting tools for those cases where only scant climatic variables are available is desirable. Concerning models which demand scant climatic inputs, the proposed model provides performances with lower associated errors than the already existing temperature-based models, which only consider local data.