Global soil moisture storage capacity at 0.5° resolution for geoscientific modelling

Soil moisture storage capacity (SMSC) links the atmosphere and terrestrial ecosystems, which is required as spatial parameters for geoscientific models, but there are currently no available parameter datasets of SMSC on a global scale especially for hydrological models. Here, we produce a dataset of SMSC parameter for global hydrological models. Parameter calibration of three commonly used monthly water balance models provides the labels for the deep residual network. Calibration on the global grids can significantly reduce parameter discontinuities compared to calibration on individual catchments. The global SMSC is reconstructed at 0.5° resolution by integrating 15 types of meteorological, topographic, and runoff data based on a deep residual network. SMSC products are validated with spatial distribution against root zone depth datasets and validated in terms of simulation efficiency on global grids and 20 catchments from different climatic regions, respectively. We provide the global SMSC parameter dataset as a benchmark for geoscientific modelling by users.