Paper Information

Ambient fine particulate matter (PM2.5) is linked to numerous adverse health outcomes. Accurate large-scale PM2.5 prediction and uncertainty quantification at fine spatial resolution are crucial for health analyses. We introduce a scalable Bayesian spatial-temporal geostatistical regression model (GRM) that performs bias-correction of gridded Chemical Transport Model (CTM) outputs or satellite-retrieved Aerosol Optical Depth (AOD) and additional spatiotemporal covariates to improve PM2.5 predictions. This model employs nearest neighbor Gaussian process (NNGP) spatial random effects to efficiently exploit spatial correlation when analyzing large numbers of PM2.5 monitors (7.64 times faster than a regular Gaussian process), and when predicting over large spatial grids (43.7 times faster than a regular Gaussian process). We apply the model to two case studies: an analysis using 12-km CTM outputs over the contiguous United States, and an analysis using 1-km AOD data over the state of California. For the U.S. 12-km case study, we demonstrate the spatial predictive performance and accurate uncertainty quantification of the model with several cross-validation experiments. For the California 1-km case study, in addition to the above, we also assess Random Forest (RF) and GRM-RF hybrid models which include a RF mean term in the GRM. Under the California 1-km case study the GRM-RF provides higher predictive accuracy (RMSE 7.325 μg/m3) than both the stand-alone RF (RMSE 7.732 μg/m3) and GRM (RMSE 8.557 μg/m3) while maintaining accurate predictive uncertainty (95% credible interval coverage 0.957). Finally, we provide open-source R software for researchers to implement the models.