A model for external drift kriging with uncertain covariates applied to air quality measurements and dispersion model output

We present a method that combines uncertain air quality measurements with uncertain secondary information from an atmospheric dispersion model. The method combines external drift kriging and a measurement error (ME) model, and uses Bayesian techniques for inference. An illustration with simulated data shows what can theoretically be expected. The method is flexible for assigning different error variances to both the primary information and secondary information at each location. Next, we address actual NO2 data collected at an urban and a rural site in the Netherlands. Uncertainty assessments in terms of exceeding air quality standards are given. The study shows that biased uncertain secondary information can be used successfully in a spatial interpolation study at the national scale