%0 Dataset
%T GTWS-MLrec: Global terrestrial water storage reconstruction by machine learning from 1940 to present
%J National Cryosphere Desert Data Center
%I National Cryosphere Desert Data Center(www.ncdc.ac.cn)
%U http://www.ncdc.ac.cn/portal/metadata/6b23bed9-627c-4653-8157-2ddd5b323888
%W NCDC
%R 10.5281/zenodo.10040927
%A None
%K Land based water storage;climate change;global
%X This study presents a long-term (i.e. 1940-2022) and high-resolution (i.e. 0.25 °) monthly time series of global land surface TWS anomalies. Reconstruction is achieved through a set of machine learning models that contain a large number of predictive factors, including climate and hydrological variables, land use/cover data, and vegetation indicators such as leaf area index. In addition, our reconstruction has successfully reproduced the impact of climate variability, such as the strong El Ni ñ o phenomenon The GTWS-MLrec dataset includes three reconstructions based on JPL, CSR, and GSFC masks, three de trending and de seasoning reconstructions, and six global average TWS sequences for land regions (including Greenland and Antarctica). GTWS-MLrec has a wide range of properties and can support a wide range of applications, such as better understanding of global water budgets, constrained and evaluated hydrological models, climate carbon coupling, and water resource management