GP-BO-Driven Ensemble Learning for High-Resolution Surface Soil Moisture Retrieval

Abstract

Surface soil moisture (SSM) plays a crucial role in hydrological processes, ecosystem dynamics, and agricultural management. Currently, high-spatial-resolution SSM estimation primarily relies on machine learning methods. However, in heterogeneous environments, the challenges associated with hyperparameter optimization, computational efficiency, and uncertainty control compromise the robustness of these methods. To address this issue, this study introduces and evaluates an integrated strategy that combines Gaussian process Bayesian optimization (GP-BO) with machine learning for high-resolution SSM retrieval. The results demonstrate that the combined method significantly outperforms conventional optimization methods evaluated by the test sets from Heihe River Basin, Naqu, and Shandian River basins. Notably, the integration of GP-BO with extreme gradient boosting (XGBoost) turned out to be the optimal combination, improving $R^{2}$ by 0.01–0.19 and reducing unbiased root-mean-square error (ubRMSE) by 0.02–1.71 percentage points relative to conventional optimizers, while requiring the least training time for ensemble models. Furthermore, vegetation-specific GP-BO-tuned XGBoost models achieve varying degrees of accuracy improvement and reduced uncertainty across various vegetation, particularly in barren and grassland regions. These findings highlight the effectiveness of the GP-BO hyperparameter optimization algorithm in reducing the uncertainties of SSM estimation in heterogeneous environments.