High contents of reactive nitrogen components aggravate air pollution and could also impact ecosystem structure and function across the terrestrial-aquatic-marine continuum. However, the long-term historical trends and future prediction of reactive nitrogen components at the global scale still remains high uncertainties. In our study, the field observations, satellite products, model output, and many other covariates were integrated into the multi-stage machine-learning model to capture the global patterns of reactive nitrogen components during 2000-2019. In order to decrease the estimate uncertainties in the future scenarios, the constructed reactive nitrogen component dataset during the historical period was then utilized as the constraint to calibrate the CMIP6 dataset in four scenarios. The results suggested the cross-validation (CV) R² values of four species showed satisfied performance (R² > 0.55). The concentrations of estimated reactive nitrogen components in China experienced persistent increases during 2000-2013, while they suffered from drastic decreases since 2013 except NH₃. It might be associated with the impact of clean air policy. However, these compounds in Europe and the United States remained relatively stable since 2000. In the future scenarios, SSP3-7.0 (traditional energy scenario) and SSP1-2.6 (carbon neutrality scenario) showed the highest and lowest reactive nitrogen component concentrations, respectively. Although the reactive nitrogen concentrations in some heavy-pollution scenarios (SSP3-7.0) also experienced decreases during 2020-2100, SSP1-2.6 and SSP2-4.5 (middle emission scenario) still kept more rapid decreasing trends. Our results emphasize the need for carbon-neutrality pathway to reduce global atmospheric N pollution.