<p><strong>Abstract.</strong> Fine particulate matter with aerodynamic diameters &#8804;&#8201;2.5&#8201;&#956;m (PM<sub>2.5</sub>) shows adverse effects on human health and atmospheric environment. Satellite-derived aerosol products have been intensively adopted in estimating surface PM<sub>2.5</sub> concentrations, but most previous studies failed to monitor air pollution over small-scale areas limited by coarse spatial-resolution (3&#8211;50&#8201;km) and low data-quality aerosol optical depth (AOD) products. Therefore, a new space-time extremely randomized trees (STET) model is developed that integrates spatiotemporal information to improve PM<sub>2.5</sub> estimates at both spatial resolution and overall accuracy across China. To this end, the newly released MODIS MAIAC AOD product, meteorological and other auxiliary data are inputs to the STET model. Daily 1-km PM<sub>2.5</sub> maps in 2018 across mainland China are produced. The STET model performs well with a high out-of-sample (out-of-station) cross-validation coefficient of 0.89 (0.88), a low root-mean-square error of 10.35 (10.97)&#8201;&#956;g/m<sup>3</sup>, a small mean absolute error of 6.71 (7.17)&#8201;&#956;g/m<sup>3</sup>, and a small mean relative error of 21.37&#8201;% (23.77&#8201;%), respectively. Particularly, it can well capture the PM<sub>2.5</sub> concentrations at both regional and individual site scales. In addition, it posed a strong predictive power (e.g., monthly-R<sup>2</sup>&#8201;=&#8201;0.80) and can be used to predict the historical PM<sub>2.5</sub> records. The North China Plain, the Sichuan Basin, and Xinjiang Province always are featured with high PM<sub>2.5</sub> pollution, especially in winter. The STET model outperforms most models presented in previous related studies. More importantly, our study provides a new approach to obtain high-quality PM<sub>2.5</sub> estimates, which is important for air pollution studies over urban areas.</p>