NEURO-FUZZY MODELING OF REFERENCE EVAPOTRANSPIRATION BASED ON THE CAMARGO METHOD

Abstract

Knowledge about evapotranspiration is essential to determine the water balance of a given region, since it can affect the basin's water management policy. In this context, the use of mathematical modeling with diffuse approach as fuzzy modeling, in which its origin was rightly due to the challenge of working with uncertainties, it can assist in the determination of evapotranspiration, helping in the decision-making process. Thus, in this article, he developed a neuro-fuzzy model (based on fuzzy logic and neural networks) to determine the reference evapotranspiration by the Camargo method. The input variables were temperature and solar radiation, both collected at the National Meteorology Institute (INMET) at the Tupã station, the data were considered for a period of one year. Such a system allows the producer to instantly obtain the reference evapotranspiration value, in addition to the qualitative classification in classes. Based on the processes conducted in this work, the established computational method could instantly calculate the reference evapotranspiration from the Camargo equation, based on solar radiation and temperature variables, reporting that the lower the values of temperature and solar radiation, the lower will be the reference evapotranspiration value.