Airborne fine particulate matter exhibits spatiotemporal variability at multiple scales, which presents challenges to estimating exposures for health effects assessment. Here we created an model to predict ambient particulate matter less than 2.5 microns in aerodynamic diameter (PM2.5) across the contiguous United States to be applied to health effects modeling. We developed a hybrid approach combining a land use regression model (LUR) selected with a machine learning method, and Bayesian Maximum Entropy (BME) interpolation of the LUR space-time residuals. The PM2.5 dataset included 104,172 monthly observations at 1,464 monitoring locations with approximately 10% of locations reserved for cross-validation. LUR models were based on remote sensing estimates of PM2.5, land use and traffic indicators. Normalized cross-validated R2 values for LUR were 0.63 and 0.11 with and without remote sensing, respectively, suggesting remote sensing is a strong predictor of ground-level concentrations. In the models including the BME interpolation of the residuals, cross-validated R2 were 0.79 for both configurations; the model without remotely sensed data described more fine-scale variation than the model including remote sensing. Our results suggest that our modeling framework can predict ground-level concentrations of PM2.5 at multiple scales over the contiguous U.S.
展开▼
