A Neural Network (NN) algorithm was developed to estimate global surface soil moisture for April 2015 to March 2017 with a 2-3 day repeat frequency using passive microwave observations from the Soil Moisture Active Passive (SMAP) satellite, surface soil temperatures from the NASA Goddard Earth Observing System Model version 5 (GEOS-5) land modeling system, and Moderate Resolution Imaging Spectroradiometer-based vegetation water content. The NN was trained on GEOS-5 soil moisture target data, making the NN estimates consistent with the GEOS-5 climatology, such that they may ultimately be assimilated into this model without further bias correction. Evaluated against in situ soil moisture measurements, the average unbiased root mean square error (ubRMSE), correlation and anomaly correlation of the NN retrievals were 0.037 m3m-3, 0.70 and 0.66, respectively, against SMAP core validation site measurements and 0.026 m3m-3, 0.58 and 0.48, respectively, against International Soil Moisture Network (ISMN) measurements. At the core validation sites, the NN retrievals have a significantly higher skill than the GEOS-5 model estimates and a slightly lower correlation skill than the SMAP Level-2 Passive (L2P) product. The feasibility of the NN method was reflected by a lower ubRMSE compared to the L2P retrievals as well as a higher skill when ancillary parameters in physically-based retrievals were uncertain. Against ISMN measurements, the skill of the two retrieval products was more comparable. A triple collocation analysis against Advanced Microwave Scanning Radiometer 2 (AMSR2) and Advanced Scatterometer (ASCAT) soil moisture retrievals showed that the NN and L2P retrieval errors have a similar spatial distribution, but the NN retrieval errors are generally lower in densely vegetated regions and transition zones.

中文翻译：

---

使用神经网络技术从 SMAP 观测估计表层土壤水分

开发了一种神经网络 (NN) 算法来估计 2015 年 4 月至 2017 年 3 月的全球表层土壤湿度，使用来自土壤湿度主动被动 (SMAP) 卫星的被动微波观测和来自 NASA 的表层土壤温度，重复频率为 2-3 天Goddard 地球观测系统模型第 5 版 (GEOS-5) 陆地建模系统，以及基于中分辨率成像光谱仪的植被含水量。神经网络在 GEOS-5 土壤水分目标数据上进行了训练，使神经网络估计与 GEOS-5 气候学一致，这样它们最终可能会被同化到这个模型中，而无需进一步的偏差校正。根据原位土壤水分测量值进行评估，NN 反演的平均无偏均方根误差 (ubRMSE)、相关性和异常相关性分别为 0.037 m3m-3、0.70 和 0.66，分别针对 SMAP 核心验证站点测量值和 0.026 m3m-3、0.58 和 0.48，分别针对国际土壤水分网络 (ISMN) 测量值。在核心验证站点，NN 检索的技能明显高于 GEOS-5 模型估计，而相关技能略低于 SMAP 2 级被动 (L2P) 产品。当基于物理的检索中的辅助参数不确定时，NN 方法的可行性体现在与 L2P 检索相比更低的 ubRMSE 以及更高的技能。与 ISMN 测量相比，两种检索产品的技能更具可比性。