Accurate subsurface soil moisture (SM) estimation is critical for vegetation growth, drought monitoring, and climate change mitigation, yet remains a significant challenge. Previous data assimilation (DA) approaches are limited to only surface SM assimilation. In this study, we utilized the proxy subsurface SM estimated via the exponential filter method (ExpF) as another assimilation variable in our 2-dimensional DA. Meanwhile, the dual updating DA scheme was implemented to simultaneously update model parameters and states. The two DA pathways were incorporated into the proposed framework (DA_1E_D), which enhanced the subsurface SM accuracy, with the effects of 2-dimensional assimilation being more significant. Under 2-dimensional DA, the information transfer between layers was more accurately characterized, leading to overall improvements with unbiased root-mean-square error (ubRMSE) reductions of 0.015 and 0.005 m³ · m⁻³, and Kling–Gupta efficiency (KGE) increases of 0.248 and 0.067 for surface and subsurface SM, respectively, across five SM networks. The soil thickness (d₂) and hydraulic conductivity exponent (expt₂) are the most influential parameters affecting subsurface SM dynamics through model propagation. DA_1E_D also outperformed ExpF in subsurface SM accuracy, particularly in SM networks with weak surface-subsurface correlation, achieving an average ubRMSE reduction of 0.003 m³ · m⁻³ and an average KGE increase of 0.202. It was also applied to Soil Moisture Active Passive data at regional scale, demonstrating significant improvements. The model surface-subsurface SM coupling was adjusted toward the actual coupling after subsurface assimilation and dual updating. This study may provide new insights into the diagnosis and refinements of the model representation of surface-subsurface processes.

中文翻译：

---

使用结合双状态参数方案的二维数据同化框架改进地下土壤湿度估计


准确的地下土壤湿度（SM）估算对于植被生长、干旱监测和减缓气候变化至关重要，但仍然是一个重大挑战。以前的资料同化（DA）方法仅限于表面 SM 同化。在本研究中，我们利用通过指数滤波器方法 (ExpF) 估计的代理地下 SM 作为二维 DA 中的另一个同化变量。同时，采用双重更新DA方案，同时更新模型参数和状态。将两条DA路径纳入所提出的框架（DA_1E_D）中，提高了地下SM的精度，并且二维同化的效果更加显着。在二维 DA 下，层间的信息传输得到了更准确的表征，导致整体改进，无偏均方根误差 (ubRMSE) 降低了 0.015 和 0.005 m ³ · m ⁻³ ，并且 Kling-Gupta 效率 (KGE ）在五个 SM 网络中，地表和地下 SM 分别增加了 0.248 和 0.067。土壤厚度 ( d ₂ ) 和导水率指数 (expt ₂ ) 是通过模型传播影响地下 SM 动力学的最有影响力的参数。 DA_1E_D 在地下 SM 精度方面也优于 ExpF，特别是在地表-地下相关性较弱的 SM 网络中，平均 ubRMSE 降低了 0.003 m ³ · m ⁻³ ，平均 KGE 提高了 0.202。它还应用于区域范围的土壤湿度主动被动数据，显示出显着的改进。 经过地下同化和双重更新后，将模型地表-地下SM耦合调整为实际耦合。这项研究可能为地表-地下过程模型表示的诊断和改进提供新的见解。