PM 2.5 is hazardous to human health, and high-quality data are thus needed on a routine basis. An attempt is made here to improve the accuracy of near-surface PM 2.5 estimates using the newly released aerosol product derived from the Visible Infrared Imaging Radiometer Suite (VIIRS) satellite with the Deep Blue retrieval algorithm. A high-quality PM 2.5 data set is generated at a spatial resolution of 6 km from 2013 to 2018 by applying the space-time extremely randomized trees (STET) model, which also aims to extend the Earth Observing System (EOS) long-term PM 2.5 data records in China. The PM 2.5 estimates are highly consistent with ground-based measurements, with an out-of-sample cross-validation coefficient of determination (CV-R 2 ) of 0.88, a root-mean-square error (RMSE) of <inline-formula> <tex-math notation="LaTeX">16.52~\mu \text{g}/\text{m}^{3} </tex-math></inline-formula>, and a mean absolute error of <inline-formula> <tex-math notation="LaTeX">10~\mu \text{g}/\text{m}^{3} </tex-math></inline-formula> at the national scale. Spatiotemporal PM 2.5 variations at monthly scales are also well captured (e.g., <inline-formula> <tex-math notation="LaTeX">R^{2} =0.91 </tex-math></inline-formula>-0.94, RMSE = 5.8-<inline-formula> <tex-math notation="LaTeX">11.6~\mu \text{g}/\text{m}^{3}) </tex-math></inline-formula>. PM 2.5 varied greatly at regional and seasonal scales across China. Benefiting from emission reduction and air pollution controls, PM 2.5 pollution has reduced dramatically in China with an average of <inline-formula> <tex-math notation="LaTeX">- 5.6~\mu \text{g}/\text{m}^{3} </tex-math></inline-formula>/yr −1 during 2013-2018. Significant regional reductions are also seen, in particular, in the Beijing-Tianjin-Hebei region (<inline-formula> <tex-math notation="LaTeX">- 6.6~\mu \text{g}/\text{m}^{3} </tex-math></inline-formula>/yr −1 , <inline-formula> <tex-math notation="LaTeX">p < 0.001 </tex-math></inline-formula>), and the Deltas of Yangtze River (<inline-formula> <tex-math notation="LaTeX">- 6.3~\mu \text{g}/\text{m}^{3} </tex-math></inline-formula>/yr −1 , <inline-formula> <tex-math notation="LaTeX">p < 0.001 </tex-math></inline-formula>) and Pearl River Delta (<inline-formula> <tex-math notation="LaTeX">- 4.5~\mu \text{g}/\text{m}^{3} </tex-math></inline-formula>/yr −1 , <inline-formula> <tex-math notation="LaTeX">p < 0.001 </tex-math></inline-formula>). Our study improved the accuracy of near-surface PM 2.5 estimates in terms of their spatiotemporal variations at a relatively long-term record, which is important for future air pollution and health studies in China.