Spatiotemporal seamless global surface soil moisture

Accurate and spatiotemporal seamless soil moisture (SM) products are important for hydrological drought monitoring and agricultural water management. Currently, physically-based process models with data assimilation are widely used for global seamless SM generation, such as soil moisture active passive level 4 (SMAP L4), the land component of the fifth generation of European Reanalysis (ERA5-land) and Global Land Data Assimilation System Noah (GLDAS-Noah). These datasets are usually produced using high-performance computation platforms and may subject to potential uncertainties from model structure and parameters, limiting their practical application capacity in a flexible way in local or global areas. Here, we proposed a data-driven artificial intelligence (AI)-based method to generate spatiotemporal seamless daily soil moisture data using triple collocation, machine learning and data assimilation. Specifically, the triple collocation correlation coefficients (TCR) method is employed to combine different SM datasets in order to obtain high-accuracy label data for model training first. A LightGBM machine learning (ML) model is constructed to simulate global daily soil moisture at 0.25°, using ERA5 meteorological forcings and MSWEP precipitation data as inputs. In addition, the satellite-based soil moisture SMAP level 3 (SMAP L3) is assimilated into the developed machine learning model using the simple Newtonian nudging technique to update the soil moisture simulation states. The incorporation of data assimilation into machine learning mimics the idea of physical models and brings much room for adaptable soil moisture simulations. The developed data-driven model is examined over global land areas from March 31, 2015 to May 31, 2023 with a ten-fold cross validation scheme, evaluated using 1094 in-situ soil moisture stations from International Soil Moisture Network (ISMN). The results indicate that the ML-based assimilated soil moisture dataset (ML-DA) demonstrates a median correlation (R) of 0.741 and an unbiased root mean square error (ubRMSE) of 0.0437 m3/m3, better than SMAP L4 (R=0.717, ubRMSE=0.0452 m3/m3), ERA5-land (R=0.706, ubRMSE=0.0452 m3/m3) and GLDAS (R=0.633, ubRMSE=0.0501 m3/m3). Compared to the three model-based soil moisture products, the ML-DA dataset exhibits superior performance in time and space and also in dry-wet zones. Therefore, the developed ML-DA framework offers significant potential for accurate, spatiotemporal soil moisture simulations globally.

精确且时空无缝的土壤水分（SM）产品对于水文干旱监测和农业水资源管理至关重要。目前，基于物理过程模型与数据同化的方法在全球无缝土壤水分生成中得到了广泛应用，例如土壤水分主动被动级4（SMAP L4）、欧洲第五代再分析（ERA5-land）陆地成分以及全球陆地数据同化系统Noah（GLDAS-Noah）。这些数据集通常采用高性能计算平台生成，并可能受到模型结构和参数的不确定性影响，限制了其在局部或全球范围内灵活应用的能力。在此，我们提出了一种基于数据驱动的人工智能（AI）方法，利用三重定位、机器学习和数据同化技术生成时空无缝的每日土壤水分数据。具体而言，采用三重定位相关系数（TCR）方法结合不同的土壤水分数据集，首先获得高精度标签数据以供模型训练。构建了一个LightGBM机器学习（ML）模型，以模拟0.25°分辨率的全日土壤水分，输入数据包括ERA5气象强迫和MSWEP降水数据。此外，利用简单的牛顿微扰技术将基于卫星的土壤水分SMAP级3（SMAP L3）同化到开发的机器学习模型中，以更新土壤水分模拟状态。将数据同化融入机器学习模拟，模仿了物理模型的理念，为适应性土壤水分模拟提供了广阔空间。所开发的数据驱动模型在全球陆地范围内进行了检验，时间跨度为2015年3月31日至2023年5月31日，采用十折交叉验证方案，并使用国际土壤水分网络（ISMN）的1094个实测土壤水分站点进行评估。结果表明，基于机器学习的同化土壤水分数据集（ML-DA）表现出中值相关系数（R）为0.741，无偏均方根误差（ubRMSE）为0.0437 m3/m3，优于SMAP L4（R=0.717，ubRMSE=0.0452 m3/m3）、ERA5-land（R=0.706，ubRMSE=0.0452 m3/m3）和GLDAS（R=0.633，ubRMSE=0.0501 m3/m3）。与三种基于模型的土壤水分产品相比，ML-DA数据集在时间和空间上以及干湿区均表现出卓越的性能。因此，所开发的ML-DA框架在全球范围内进行精确、时空土壤水分模拟具有显著潜力。