You are here:
A Bivariate Space-time Downscaler Under Space and Time Misalignment
Citation:
Berrocal, V. J., A. E. Gelfand, AND D. M. HOLLAND. A Bivariate Space-time Downscaler Under Space and Time Misalignment. Applied Statistics. Carfax Publishing Limited, Basingstoke, Uk, 4:1942-1975, (2011).
Impact/Purpose:
Ozone and particulate matter, PM,2:5 have long been associated with increased public health risks, e.g., of respiratory diseases (Schwartz 1996; Dominici et al. 2006; Braga et al. 2001), cardiovascular diseases (Dominici et al. 2006; Braga et al. 2001), and mortality and morbidity in general (Dominici et al. 2000; Smith et al. 2000). In order to protect human health, the US Environmental Protection Agency (EPA) is required by the Clean Air Act to set, review and enforce air quality standards. To do so, the EPA utilizes information coming from monitoring devices sparsely located across the United States. A second source of information on the concentration of air pollutants is provided by output from complex numerical models that integrate several components, accounting, respectively, for meteorology, the emissions injected in the atmosphere and the chemical and physical interactions among the different gases in the atmosphere.
Description:
Ozone and particulate matter PM2:5 are co-pollutants that have long been associated with increased public health risks. Information on concentration levels for both pollutants come from two sources: monitoring sites and output from complex numerical models that produce concentration surfaces over large spatial regions. In this paper, we offer a fully-model based approach for fusing these two sources of information for the pair of co-pollutants which is computationally feasible over large spatial regions and long periods of time. Due to the association between concentration levels of the two environmental contaminants, it is expected that information regarding one will help to improve prediction of the other. Misalignment is an obvious issue since the monitoring networks for the two contaminants only partly intersect and because the collection rate for PM2:5 is typically less frequent than that for ozone. Extending previous work in Berrocal et al. (2009), we introduce a bivariate downscaler that provides a exible class of bivariate space-time assimilation models. We discuss computational issues for model fitting and analyze a dataset for ozone and PM2:5 for the ozone season during year 2002. We show a modest improvement in predictive performance, not surprising in a setting where we can anticipate only a small gain.