Accurate estimates of the spatiotemporal distribution of evapotranspiration (ET) are essential for understanding terrestrial energy, carbon and water cycles. Station-based observations are limited for their spatial coverage whereas satellite-derived ET products exhibit large discrepancies and uncertainties. Here we presented a Deep Neural Networks based Merging ET (DNN-MET) framework that combines information from satellite-derived ET products, eddy covariance (EC) observations and ancillary surface properties to improve the representation of the spatiotemporal distribution of ET, especially in data-sparse regions. DNN-MET was implemented over the Heihe River Basin (HRB) from 2008 to 2015, and the performance of DNN-MET and eight input state-of-the-art satellite-derived ET products (i.e., MOD16, ET-SEMI, ET-JPL, ET-MS, ET-HF, GLEAM, ETMonitor and EB-ET) was evaluated against observations from 19 EC flux tower sites. The results showed that DNN-MET improved ET estimates over HRB, and decreased the RMSE by 0.13 to 1.02 mm/day (14%-56%) when compared with eight products. DNN-MET also yielded superior performance compared to the products derived by other merging methods (i.e., Random Forest, Bayesian model averaging and a simple averaging method). When DNN-MET was validated for data-scarce regions, its performance remained better even when the training samples were decreased to 20% of the available EC sites. An innovation of our approach is by building a multivariate merging model with ancillary surface properties, DNN-MET incorporated geographical proximity effects and spatial autocorrelations into merging procedure, which can be used as a “spatial knowledge engine” to improve ET predictions. The approach can be readily and effectively applied elsewhere to improve the spatiotemporal representation of various hydrometeorological variables.

准确估计蒸散量 (ET) 的时空分布对于理解陆地能量、碳和水循环至关重要。站基观测的空间覆盖范围有限，而卫星衍生的 ET 产品则表现出很大的差异和不确定性。在这里，我们提出了一个基于深度神经网络的合并 ET (DNN-MET) 框架，该框架结合了来自卫星衍生的 ET 产品、涡流协方差 (EC) 观测和辅助表面特性的信息，以改进 ET 时空分布的表示，尤其是在数据中- 稀疏区域。DNN-MET 于 2008 年至 2015 年在黑河流域（HRB）上实施，DNN-MET 和 8 个输入的最先进卫星衍生 ET 产品（即 MOD16、ET-SEMI、ET -喷气推进实验室、ET-MS、ET-HF、GLEAM、ETMonitor 和 EB-ET）根据来自 19 个 EC 通量塔站点的观察结果进行评估。结果表明，与 8 种产品相比，DNN-MET 比 HRB 提高了 ET 估计值，并将 RMSE 降低了 0.13 至 1.02 毫米/天（14%-56%）。与通过其他合并方法（即随机森林、贝叶斯模型平均和简单平均方法）得出的产品相比，DNN-MET 还产生了卓越的性能。当 DNN-MET 被验证用于数据稀缺区域时，即使训练样本减少到可用 EC 站点的 20%，其性能仍然更好。我们方法的一个创新是通过构建具有辅助表面特性的多元合并模型，DNN-MET 将地理邻近效应和空间自相关性纳入合并过程，它可以用作“空间知识引擎”来改进 ET 预测。该方法可以轻松有效地应用于其他地方，以改善各种水文气象变量的时空表示。