Spatiotemporal continuous estimates of PM2.5 concentrations in China, 2000–2016: A machine learning method with inputs from satellites, chemical transport model, and ground observations

作者：Tao Xue, Yixuan Zheng, Dan Tong, Bo Zheng, Xin Li, Tong Zhu, Qiang Zhang · 发表于：Environment International · 年份：2018 · DOI：10.1016/j.envint.2018.11.075 · 被引用次数：325 · 研究领域：Air Quality and Health Impacts、Air Quality Monitoring and Forecasting、Atmospheric chemistry and aerosols

Ambient exposure to fine particulate matter (PM 2.5 ) 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 PM 2.5 concentrations nationwide, while the lack of surface monitoring data before 2013 have created difficulties in historical PM 2.5 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 PM 2.5 and AOD as a nonlinear function of space and time covariates (e.g., planetary boundary layer height and relative humidity). In this way, the PM 2.5 -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 mod...