Improving terrestrial evapotranspiration estimation across China during 2000–2018 with machine learning methods

•Five process-based ET models were integrated based on Gaussian process regression.•Gaussian process regression was better than the other five machine learning methods.•Integrated ET estimates were more accurate than currently available eight ET products.•China terrestrial ET with a spatial and temporal resolution of 1 km and 10 days is generated. Estimating terrestrial evapotranspiration (ET) accurately at various temporal and spatial scales is crucial for understanding the hydrological cycle and water resource management. The currently available ET estimates have some uncertainties and need to be further improved. In this study, six machine learning methods including the random forests, support vector machine, Gaussian process regression (GPR), ensemble trees, general regression neural network, and Bayesian Model Averaging, are applied and evaluated to improve China terrestrial ET estimation by integrating five process-based ET algorithms including SEMI-PM, RS-PM, RRS-PM, MOD16, and PMLv2. Then evaluations are conducted with the eddy covariance flux observations at 14 China flux tower sites distributing in forest, shrub, wetland, grassland, and cropland, as well as with water balance-based ET at basin scale. According to the multiple training, validation, and testing, the GPR method is superior to all the other methods. Compared with the individual algorithms, the GPR method can reduce the root mean square error (RMSE) by 0.45 mm day−1 (for SEMI-PM) ~0.81 mm day−1 (for PMLv2), improve the coefficientofdetermination (R2) by 0.061 (for PMLv2) ~ 0.33 (for MOD16), and decrease the absolute relative percent error (RPE) by 8.32% (for RS-PM) ~42.47% (for PMLv2) for all the test data. At basin scale, the results demonstrate that the annual GPR-merged China terrestrial ET is reliable (R2 = 0.88, RMSE = 57.18 mm year−1, RPE = −0.26%) and has higher accuracy than the currently available eight high-resolution ET products and the estimates from the other five machine learning methods and the five single ET models. The annual average terrestrial ET across China for 2000–2018 estimated by the GPR method is approximately 397.65 mm year−1. More ground-based observations of terrestrial ET covering various land types should be collected to update the integrating methods and improve ET estimates. The resultant China terrestrial ET product with a spatial and temporal resolution of 1 km and 10 days (ChinaET1km10days) produced by the GPR method is available at https://doi.org/