Estimating daily reference evapotranspiration with reduced data input using ensemble learning models in arid and humid regions of China

Abstract

Accurate estimation of reference evapotranspiration (ET_o) is key to irrigation system design and agricultural water management. Utilizing meteorological data (1960–2019) from 20 stations in China’s humid and arid regions, a reference ET_o value was calculated using the FAO56-Penman-Monteith (PM) method. The accuracy of 6 ensemble learning models [e.g., Adaptive boosting (AdaBoost), Gradient Boosting Decision Tree (GBDT), Categorical boosting (CatBoost), Extreme gradient boosting (XGBoost), Extra trees, and Light Gradient Boosting Method (LightGBM)] in estimating daily ET_o using all available inputs was investigated. The performance of the best three models (CatBoost, GBDT and XGBoost) was then evaluated under 7 input combinations [i.e., complete and incomplete combinations of maximum and minimum temperature (T_max and T_min), relative humidity (RH), wind speed (U₂), total and extra-terrestrial solar radiation (R_s and R_a)], and 4 dataset sizes (20, 30, 40 and 60 years). CatBoost showed the highest estimation accuracy (average R² = 0.93), stability, and robustness. Using incomplete combinations based on temperature and other indicators to estimate daily ET_o also achieved satisfactory results (R² > 0.91), and the key indicators contributing to a difference in ET_o prediction accuracy between humid and arid regions were RH and R_a. Different models’ accuracy in estimating daily ET_o was not affected by dataset size (the difference of RMSE＜0.025), but its stability improves with the increase of the dataset. This study evaluated the models’ performance under different data constraints and different regional applications, which provides a methodological reference for ET_o simulation in global multiclimatic zones, takes into account accuracy and practicality.