Published October 25, 2021 | Version v4
Dataset Open

Understanding the role of the spatial-temporal variability of catchment water storage capacity and its runoff response using deep learning networks

Creators

Description

Abstract

Catchment water storage capacity (CWSC) links the atmosphere and terrestrial ecosystems, which is required as spatial parameters for geoscientific models. However, there are currently no available common datasets of the CWSC on a global scale, especially for hydrological models since conventional evapotranspiration-derived estimates cannot represent the extra storage capacity for the lateral flow and runoff generation. Here, we produce a dataset of the CWSC parameter for global hydrological models. Joint parameter calibration of three commonly used monthly water balance models provides the labels for a deep residual network. The global CWSC is constructed based on the deep residual network at 0.5° resolution by integrating 15 types of meteorological forcings, underlying surface properties, and runoff data. CWSC products are validated with the spatial distribution against root zone depth datasets and validated in the simulation efficiency on global grids and typical catchments from different climatic regions. We provide the global CWSC parameter dataset as a benchmark for geoscientific modelling by users.

A global terrestrial CWSC dataset with 0.5  spatial resolution is now available. All input factors and the global CWSC data are publicly available as NetCDF files or download from smsc_data.zip at Zenodo. Python codes are available to calculate the basin average CWSC value from grid values in any interested basin on a global scale.

The Fortran codes for parameter calibration of semi distributed global monthly water balance models are available at https://github.com/xiekangwhu/CWSC_monthly_water_balance_models. The Python codes of deep residual network we developed for the global reconstruction map of CWSC are available at https://github.com/xiekangwhu/CWSC_deep_residual_network.

 

Major code contributor: Kang Xie (PhD Student, Wuhan University), Liting Zhou (PhD Student, Wuhan University), Shujie Cheng (PhD Student, Wuhan University), and Shuanghong Shen (PhD Student, University of Science and Technology of China)

 

Citations

If you find our code to be useful, please cite the following papers:

Xie, K. et al. Identification of spatially distributed parameters of hydrological models using the dimension-adaptive key grid calibration strategy - ScienceDirect. Journal of Hydrology 598, doi:10.1016/j.jhydrol.2020.125772 (2020).

Xie, K. et al. Physics-guided deep learning for rainfall-runoff modeling by considering extreme events and monotonic relationships. Journal of Hydrology 603, doi:10.1016/j.jhydrol.2021.127043 (2021).

Xie, K. et al. Verification of a New Spatial Distribution Function of Soil Water Storage Capacity Using Conceptual and SWAT Models. Journal of Hydrologic Engineering 25, doi:10.1061/(asce)he.1943-5584.0001887 (2020).

Files

basin_average_smsc_calculate.zip

Files (429.4 MB)

Name Size Download all
md5:9886b3db1d97c030ec215b3578e2b02d
2.0 kB Preview Download
md5:14cb7c533989c9d0172bb8b82ca90ec3
29.3 MB Preview Download
md5:f20857906a61d5b5731dc6ebe2a5f424
277.7 kB Preview Download
md5:49754ece4b73dbcb3b06438a61acfdcb
397.4 MB Preview Download
md5:9f3d19ccefe8fa3539fdc8978a974233
2.4 MB Preview Download