Selecting Essential Factors for Predicting Reference Crop Evapotranspiration Through Tree-based Machine Learning and Bayesian Optimisation

Reference crop evapotranspiration (ETO) is a basic component of the hydrological cycle, and its estimation is critical for agricultural water resource management and scheduling. In this study, three tree-based machine learning algorithms (random forest [RF], gradient boosting decision tree [GBDT], and extreme gradient boosting [XGBoost]) were adopted to determine the essential factors for ETO prediction. The tree-based models were optimised using the Bayesian optimisation (BO) algorithm, and they were compared with three standalone models in terms of daily ETO and monthly mean ETO estimation in North China, with different input combinations of essential variables. The results indicated that solar radiation (Rs) and air temperature (Ts), including the maximum, minimum, and average temperature, in daily ETO were the key parameters affecting model prediction accuracy. Rs was the most influential factor in the monthly average ETO model, followed by Ts. Both relative humidity (RH) and wind speed at 2 m (U2) had little impact on ETO prediction at different scales, although their importance differed. Compared with the GBDT and RF models, the XGBoost model exhibited the highest performance for daily ETO and monthly mean ETO estimation. The hybrid tree-based models with the BO algorithm outperformed the standalone tree-based models. Overall, compared with other inputs, the model with three inputs (Rs, Ts, and RH/U2) had the highest accuracy. The BO-XGBoost model exhibited superior performance in terms of the global performance index (GPI) for daily ETO and monthly mean ETO prediction and it is recommended as a more accurate model predicting daily ETO and monthly mean ETO in North China or areas with a similar climate.

Splitting and Length of Years for Improving Tree-Based Models to Predict Reference Crop Evapotranspiration in the Humid Regions of China

To improve the accuracy of estimating reference crop evapotranspiration for the efficient management of water resources and the optimal design of irrigation scheduling, the drawback of the traditional FAO-56 Penman–Monteith method requiring complete meteorological input variables needs to be overcome. This study evaluates the effects of using five data splitting strategies and three different time lengths of input datasets on predicting ET0. The random forest (RF) and extreme gradient boosting (XGB) models coupled with a K-fold cross-validation approach were applied to accomplish this objective. The results showed that the accuracy of the RF (R2 = 0.862, RMSE = 0.528, MAE = 0.383, NSE = 0.854) was overall better than that of XGB (R2 = 0.867, RMSE = 0.517, MAE = 0.377, NSE = 0.860) in different input parameters. Both the RF and XGB models with the combination of Tmax, Tmin, and Rs as inputs provided better accuracy on daily ET0 estimation than the corresponding models with other input combinations. Among all the data splitting strategies, S5 (with a 9:1 proportion) showed the optimal performance. Compared with the length of 30 years, the estimation accuracy of the 50-year length with limited data was reduced, while the length of meteorological data of 10 years improved the accuracy in southern China. Nevertheless, the performance of the 10-year data was the worst among the three time spans when considering the independent test. Therefore, to improve the daily ET0 predicting performance of the tree-based models in humid regions of China, the random forest model with datasets of 30 years and the 9:1 data splitting strategy is recommended.