An effective predictive model for daily evapotranspiration based on a limited number of meteorological parameters

Abstract

As temperatures rise globally, parts of the water cycle will likely speed up due to climate change as evapotranspiration rates increase throughout the world. In this study, three models have been applied to predict the daily evapotranspiration (ETo) over Santaella station, which is located in Spain. The models are Hargreaves-Samani (HS), modified Hargreaves-Samani (MHS), and Group Method of Data Handling neural network (GMDH-NN). These models are developed using very limited data (temperature parameter). The study found that the HS approach provides the poorest prediction, while the GMDH performance was superior to the MHS. Furthermore, the GMDH-NN model showed a prediction improvement of 16.45% in terms of uncertainty at 95% compared to the MHS model. The study also showed that it is possible to efficiently predict the ETo using a very limited number of meteorological parameters.