Predictive mapping of air pollution involving sparse spatial observations

A limited number of sample points greatly reduces the availability of appropriate spatial interpolation methods. This is a common problem when one attempts to accurately predict air pollution levels across a metropolitan area. Using ground-level ozone concentrations in the Tucson, Arizona, region as an example, this paper discusses the above problem and its solution, which involves the use of linear regression. A large range of temporal variability is used to compensate for sparse spatial observations (i.e. few ozone monitors). Gridded estimates of emissions of ozone precursor chemicals, which are developed, stored, and manipulated within a geographic information system, are the core predictor variables in multiple linear regression models. Cross-validation of the pooled models reveals an overall R2 of 0.90 and approximately 7% error. Composite ozone maps predict that the highest ozone concentrations occur in a monitor-less area on the eastern edge of Tucson. The maps also reveal the need for ozone monitors in industrialized areas and in rural, forested areas.