Compared with the limited capability of ground-level monitoring, remote sensing provides useful image data at a moderate or high spatial or temporal resolution with global coverage for monitoring of air pollutants, e.g., aerosol optical depth (AOD) observations from the MODIS for fine particulate matter (PM_2.5) and Ozone Monitoring Instrument (OMI) nitrogen dioxide (NO₂) vertical columns for ground-level NO₂ concentration. However, the extensive nonrandom missingness of OMI-NO₂ data (e.g., an approximate per-pixel missing proportion of 59% for mainland China in 2015) due to cloud contamination or high reflectance limits applicability of these data in estimation of ground-level NO₂. This paper proposes the use of a full residual deep learning method to impute missing satellite-borne NO₂ data (OMI-NO₂) and to estimate (map) ground-level NO₂ with uncertainty (coefficient of variation) at a high spatial (1 × 1 km²) and temporal (daily) resolution. For the large study region (mainland China except Hainan Province), the presented method achieved robust performance with a stable learning efficiency (mean test R²: 0.98 with a small standard deviation of 0.01; mean test RMSE: 0.42 × 10¹⁵ molecules/cm²) for imputation of OMI-NO₂. In the model, the coordinates and elevation were used to capture the spatial variability of the OMI-NO₂ columns, and fused meteorological grid data and planetary boundary layer height and ozone data from GEOS-FP were used to capture spatiotemporal variability of OMI-NO₂. The evaluation with ground in situ NO₂ measurements showed considerable contribution of the complete (raw observed and imputed) OMI-NO₂ columns, meteorology and traffic variables to inference of ground-level NO₂ (test R²: 0.82; test RMSE: 8.80 μg/m³). The complete grids of OMI-NO₂ columns showed natural and smooth spatial transitions between the raw observed and imputed values. The surfaces of predicted NO₂ concentration not only showed consistent distributions with OMI-NO₂ at a regional and temporal scale, but also presented local spatial gradients of ground-level NO₂. OMI-NO₂ can be downscaled and imputed to be used as an important predictor to improve the estimation of high-resolution ground-level NO₂. The reliable estimates of ground-level NO₂ concentration with uncertainty can reduce the bias in estimates of NO₂ exposure and subsequently evaluations of its health effects.