Spatiotemporal prediction of fine particulate matter using high-resolution satellite images in the Southeastern US 2003-2011.

Numerous studies have demonstrated that fine particulate matter (PM2.5, particles smaller than 2.5 μm in aerodynamic diameter) is associated with adverse health outcomes. The use of ground monitoring stations of PM2.5 to assess personal exposure, however, induces measurement error. Land-use regression provides spatially resolved predictions but land-use terms do not vary temporally. Meanwhile, the advent of satellite-retrieved aerosol optical depth (AOD) products have made possible to predict the spatial and temporal patterns of PM2.5 exposures. In this paper, we used AOD data with other PM2.5 variables, such as meteorological variables, land-use regression, and spatial smoothing to predict daily concentrations of PM2.5 at a 1-km(2) resolution of the Southeastern United States including the seven states of Georgia, North Carolina, South Carolina, Alabama, Tennessee, Mississippi, and Florida for the years from 2003 to 2011. We divided the study area into three regions and applied separate mixed-effect models to calibrate AOD using ground PM2.5 measurements and other spatiotemporal predictors. Using 10-fold cross-validation, we obtained out of sample R(2) values of 0.77, 0.81, and 0.70 with the square root of the mean squared prediction errors of 2.89, 2.51, and 2.82 μg/m(3) for regions 1, 2, and 3, respectively. The slopes of the relationships between predicted PM2.5 and held out measurements were approximately 1 indicating no bias between the observed and modeled PM2.5 concentrations. Predictions can be used in epidemiological studies investigating the effects of both acute and chronic exposures to PM2.5. Our model results will also extend the existing studies on PM2.5 which have mostly focused on urban areas because of the paucity of monitors in rural areas.