Early Estimation of Daily Reference Evapotranspiration Using Machine Learning Techniques for Efficient Management of Irrigation Water

Abstract Assessing the right amount of water needs for a specific crop is a key task for farmers and agronomists to achieve efficient and optimal irrigation scheduling, and then an optimal crop yield. To this end, the reference evapotranspiration (ET 0 ) was developed. It represents the atmospheric evaporation demand, and therefore an important variable for irrigation management. In this regard, several methods such as the FAO’s Penman-Monteith and Hargreaves have been used to model and estimate ET 0 . These methods use climatic parameters data for calculation procedures such as solar net radiation (R n ), saturation vapour pressure(e s ), and min-max air temperatures or a combination of them. In this paper, we investigated two proposed data-driven methods to predict ET 0 values in a semi-arid region in Morocco. The first approach is based on forecasting techniques and the second one uses end-to-end modeling of ET 0 based on meteorological data and machine learning models. The feature selection and engineering results show that solar global radiation (R g ) and mean air temperature (T a ) have a significance of more than 87% as relevant predictors features for the ET 0 . We then used them as input to machine learning regression models. Regression evaluation metrics showed that The XGboost regressor model performs well in both cross-validation with R 2 =0.93 in the first fold, and in hold-out validation with R 2 =0.92 and RMSE=0.55. As a final step, we compared the univariate time series forecasting of ET 0 using the Facebook Prophet model versus the machine learning modeling method that we proposed. As goodness-of-fit measures, forecasting using machine learning modeling of ET 0 showed better results in terms of both R 2 and RMSE.