Wet NH4-N deposition plays a significant role in the ecosystem safety in China, and thus it is highly imperative to estimate the national wet NH4-N deposition flux accurately. In this study, a new methodology named space-time ensemble machine-learning model was first applied to constrain the high-resolution NH4-N deposition fluxes over China based on the satellite data, assimilated meteorology, and various geographical covariates. A small gap between site-based cross-validation (CV) R2 value (0. 73) and 10-fold CV R2 value (0.76), along with remarkable improvement in predictive accuracy (0.76) compared with previous studies (0.61), demonstrated the strong prediction capability of the space-time ensemble model in data mining. The higher wet NH4-N deposition fluxes mainly occurred in North China Plain (NCP), Sichuan Basin, Hunan, Jiangxi, and Guangdong provinces, whereas other regions retained the lower values. In addition, the wet NH4-N deposition fluxes, removing the precipitation effect in some major developed regions (e.g., Beijing and Shanghai) of China, displayed gradual increases from 2011 to 2014, while they suffered from dramatic decreases during 2014-2016, which was due to the strict implementation of the Action Plan for Air Pollution Prevention and Control (APPC-AP). The high-quality NH4-N deposition data sets are greatly useful to assess the potential ecological risks.