CR prepress abstract   -  DOI: https://doi.org/10.3354/cr01723

ABSTRACT: Accurate estimation of reference evapotranspiration (ET₀) is vital for hydrological studies and irrigation scheduling. This study aims to estimate ET₀ using four machine learning algorithms: random forest, support vector machine, light gradient boosting decision trees and extreme gradient decision trees. Daily data for 2001 to 2020 at eleven (arid and semi-arid) stations was used for modelling. Eighteen scenarios with different input combinations were evaluated using the data of maximum and minimum air temperature, mean relative humidity and wind speed, number of sunshine hours, solar radiation, and extra-terrestrial radiation data at these stations. The ET₀ estimated using FAO 56 Penman-Monteith was chosen as the target value for model fitting. The best input combination was found in the models that used all inputs, while the least accurate were the models that used temperature data only. The results showed that the SVM models outperformed the other models at most stations. The application of various input combinations indicated that the use of lesser number of inputs also gave reasonable accuracy in the modelling. Also, wind speed and solar radiation were found to be important parameters for precise estimation.