Terrestrial water storage (TWS) includes all forms of water stored on and below the land surface, and is a key determinant of global water and energy budgets. However, TWS data from measurements by the Gravity Recovery and Climate Experiment (GRACE) satellite mission are only available from 2002, limiting global and regional investigation of the long-term trends and variabilities in the terrestrial water cycle under climate change. This study presents long-term (i.e., 1940-2022) and high-resolution (i.e., 0.25°) monthly time series of TWS anomalies over the global land surface. The reconstruction is achieved by using a set of machine learning models with a large number of predictors, including climatic and hydrological variables, land use/land cover data, and vegetation indicators (e.g., leaf area index). The outcome, machine learning-reconstructed TWS estimates (i.e., GTWS-MLrec), fits well with the GRACE/GRACE-FO measurements, showing high correlation coefficients and low biases in the GRACE era. We also evaluate GTWS-MLrec with other independent datasets such as the land-ocean mass budget, large-scale water balance in 341 large river basins, and streamflow measurements at 10,168 gauges. We find that the proposed approach performs overall as well as or is more reliable than previous TWS datasets. Moreover, our reconstructions successfully reproduce the impact of climate variability, such as strong El Niño events. GTWS-MLrec dataset consists of three reconstructions based on JPL, CSR and GSFC mascons, three detrended and de-seasonalized reconstructions, and six global average TWS series over land areas, both with and without Greenland and Antarctica. Along with its extensive attributes, GTWS_MLrec can support a broad range of applications such as better understanding the global water budget, constraining and evaluating hydrological models, climate-carbon coupling, and water resources management. Please cite the reference: Yin J, Slater L, Khouakhi A, et al. GTWS-MLrec: Global terrestrial water storage reconstruction by machine learning from 1940 to present. Earth System Science Data. 2023. For any inquiry about the dataset, welcome to contact Dr. Jiabo Yin (jboyn@whu.edu.cn).