Despite considerable progress in scaling carbon fluxes from eddy covariance sites to globe, significant uncertainties still exist when estimating the global net ecosystem exchange (NEE). In this study, the site-level NEE was estimated from FLUXNET, a global network of eddy covariance towers, using a random forest (RF) model based on remote sensing products and precipitation data. The plant function type (PFT) had the highest relative explanatory power in predicting the global site-level NEE. However, within PFTs, water-related variables (i.e., the total precipitation, remotely sensed evapotranspiration, land surface water index, and the difference between daytime and nighttime land surface temperature) and soil respiration (<italic>R</italic><sub>s</sub>) were strong predictors of NEE variability. Cross-validation analyses revealed the good performance of RF in predicting the spatiotemporal variability of monthly NEE at 168 global FLUXNET sites, with <italic>R</italic><sup>2</sup> of 0.72 and RMSE of 0.96 g·C·m<sup>−2</sup>·day<sup>−1</sup>. The performance was also good when predicting across-site (<italic>R</italic><sup>2</sup> = 0.75) and seasonal patterns (<italic>R</italic><sup>2</sup> = 0.92) over the 58 sites with available data being longer than two years and the 12-month value being present for each year. The RF-estimated NEE showed better relationships with the tower-measured NEE than a global NEE product from FLUXCOM across all PFTs. The difference between the RF-estimated NEE and FLUXCOM NEE was likely linked to the different predictor sets, such as those with more water-related variables and <italic>R</italic><sub>s</sub>. This study indicates the importance of considering the influence of water-related variables and <italic>R</italic><sub>s</sub> in the estimation of NEE at the global scale.