Time Series Forecasting for Purposes of Irrigation Management Process

Abstract

Irrigated agriculture is the most water-consuming sector in Brazil, representing one of the main challenges for the sustainable use of water. This study proposes and experimentally evaluates univariate time series models that predict the value of reference evapotranspiration, a metric of the water loss from crop to the environment. Reference evapotranspiration plays an essential role in irrigation management since it can be used to reduce the amount of water that will not be absorbed by the crop. The experiments performed under the meteorological dataset generated by a weather station. Moreover, the results show that the approach is a viable and lower cost solution for predicting ET0, since only a variable needs to be monitored.