A machine learning method to estimate PM 2.5 concentrations across China with remote sensing, meteorological and land use information

Machine learning algorithms have very high predictive ability. However, no study has used machine learning to estimate historical concentrations of PM (particulate matter with aerodynamic diameter ≤ 2.5 μm) at daily time scale in China at a national level. To estimate daily concentrations of PM across China during 2005-2016. Daily ground-level PM data were obtained from 1479 stations across China during 2014-2016. Data on aerosol optical depth (AOD), meteorological conditions and other predictors were downloaded. A random forests model (non-parametric machine learning algorithms) and two traditional regression models were developed to estimate ground-level PM concentrations. The best-fit model was then utilized to estimate the daily concentrations of PM across China with a resolution of 0.1° (≈10 km) during 2005-2016. The daily random forests model showed much higher predictive accuracy than the other two traditional regression models, explaining the majority of spatial variability in daily PM [10-fold cross-validation (CV) R = 83%, root mean squared prediction error (RMSE) = 28.1 μg/m ]. At the monthly and annual time-scale, the explained variability of average PM increased up to 86% (RMSE = 10.7 μg/m and 6.9 μg/m , respectively). Taking advantage of a novel application of modeling framework and the most recent ground-level PM observations, the machine learning method showed higher predictive ability than previous studies. Random forests approach can be used to estimate historical exposure to PM in China with high accuracy.