Air pollution has altered the Earth’s radiation balance, disturbed the ecosystem, and increased human morbidity and mortality. Accordingly, a full-coverage high-resolution air pollutant data set with timely updates and historical long-term records is essential to support both research and environmental management. Here, for the first time, we develop a near real-time air pollutant database known as Tracking Air Pollution in China (TAP, http://tapdata.org.cn/) that combines information from multiple data sources, including ground observations, satellite aerosol optical depth (AOD), operational chemical transport model simulations, and other ancillary data such as meteorological fields, land use data, population, and elevation. Daily full-coverage PM_2.5 data at a spatial resolution of 10 km is our first near real-time product. The TAP PM_2.5 is estimated based on a two-stage machine learning model coupled with the synthetic minority oversampling technique and a tree-based gap-filling method. Our model has an averaged out-of-bag cross-validation R² of 0.83 for different years, which is comparable to those of other studies, but improves its performance at high pollution levels and fills the gaps in missing AOD on daily scale. The full coverage and near real-time updates of the daily PM_2.5 data allow us to track the day-to-day variations in PM_2.5 concentrations over China in a timely manner. The long-term records of PM_2.5 data since 2000 will also support policy assessments and health impact studies. The TAP PM_2.5 data are publicly available through our website for sharing with the research and policy communities.

Based on the exposure data sets from the Tracking Air Pollution in China (TAP, http://tapdata.org.cn/), we characterized the spatiotemporal variations in PM_2.5 and O₃ exposures and quantified the long- and short-term exposure related premature deaths during 2013–2020 with respect to the two-stage clean air actions (2013–2017 and 2018–2020). We find a 48% decrease in national PM_2.5 exposure during 2013–2020, although the decrease rate has slowed after 2017. At the same time, O₃ pollution worsened, with the average April–September O₃ exposure increased by 17%. The improved air quality led to 308 thousand and 16 thousand avoided long- and short-term exposure related deaths, respectively, in 2020 compared to the 2013 level, which was majorly attributed to the reduction in ambient PM_2.5 concentration. It is also noticed that with smaller PM_2.5 reduction, the avoided long-term exposure associated deaths in 2017–2020 (13%) was greater than that in 2013–2017 (9%), because the exposure–response curve is nonlinear. As a result of the efforts in reducing PM_2.5-polluted days with the daily average PM_2.5 higher than 75 μg/m³ and the considerable increase in O₃-polluted days with the daily maximum 8 h average O₃ higher than 160 μg/m³, deaths attributable to the short-term O₃ exposure were greater than those due to PM_2.5 exposure since 2018. Future air quality improvement strategies for the coordinated control of PM_2.5 and O₃ are urgently needed.

Ambient exposure to fine particulate matter (PM2.5) is known to harm public health in China. Satellite remote sensing measurements of aerosol optical depth (AOD) were statistically associated with in-situ observations after 2013 to predict PM2.5 concentrations nationwide, while the lack of surface monitoring data before 2013 have created difficulties in historical PM2.5 exposure estimates. Hindcast approaches using statistical models or chemical transport models (CTMs) were developed to overcome this limitation, while those approaches still suffer from incomplete daily coverage due to missing AOD data or limited accuracy due to uncertainties of CTMs. Here we developed a new machine learning (ML) model with high-dimensional expansion (HD-expansion) of numerous predictors (including AOD and other satellite covariates, meteorological variables and CTM simulations). Through comprehensive characterization of the nonlinear effects of, and interactions among different predictors, the HD-expansion parameterized the association between PM2.5 and AOD as a nonlinear function of space and time covariates (e.g., planetary boundary layer height and relative humidity). In this way, the PM2.5-AOD association can vary spatiotemporally. We trained the model with data from 2013 to 2016 and evaluated its performance using annually-iterated cross-validation, which iteratively held out the in-situ observations for a whole calendar year (as testing data) to examine the predictions from a model trained by the rest of the observations. Our estimates were found to be in good agreement with in-situ observations, with correlation coefficients (R2) of 0.61, 0.68, and 0.75 for daily, monthly and annual averages, respectively. To interpolate the missing predictions due to incomplete AOD data, we incorporated a generalized additive model into the ML model. The two-stage estimates of PM2.5 sacrificed the prediction accuracy on a daily timescale (R2 = 0.55), but achieved complete spatiotemporal coverage and improved the accuracy of monthly (R2 = 0.71) and annual (R2 = 0.77) averages. The model was then used to predict daily PM2.5 concentrations during 2000-2016 across China and estimate long-term trends in PM2.5 for the period. We found that population-weighted concentrations of PM2.5 significantly increased, by 2.10 (95% confidence interval (CI): 1.74, 2.46) μg/m3/year during 2000-2007, and rapidly decreased by 4.51 (3.12, 5.90) μg/m3/year during 2013-2016. In this study, we produced AOD-based estimates of historical PM2.5 with complete spatiotemporal coverage, which were evidenced as accurate, particularly in middle and long term. The products could support large-scale epidemiological studies and risk assessments of ambient PM2.5 in China and can be accessed via the website (http://www.meicmodel.org/dataset-phd.html).