Application of Machine Learning in Agriculture the Reference Evapotranspiration Model Prediction

Given its key role in solving many complex engineering problems, such as robots, aircraft, electronics, etc., artificial intelligence (AI) has become more and more employed. One among the most widely employed AI methods is machine learning. In this paper, this latter has been investigated to predict the daily reference evapotranspiration
$(ET_{0})$
, which presents significant data in agriculture, especially water resources management and planning for irrigation. This variable depends on the maximum and minimum temperature, wind speed, and relative humidity values. Distinct combinations of these values have been considered. The MATLAB learner regression toolbox has been exploited to simulate the machine learning technique. It includes 19 different models. Simulation results demonstrate the efficacy of the Gaussian Process Regression (GPR) models versus alternative machine learning models to predict the
$ET_{0}$
.