Mixed deterministic statistical modelling of regional ozone air pollution
Article first published online: 17 MAR 2011
Copyright © 2011 John Wiley & Sons, Ltd.
Volume 22, Issue 4, pages 572–586, June 2011
How to Cite
Kalenderski, S. and Steyn, D.G. (2011), Mixed deterministic statistical modelling of regional ozone air pollution. Environmetrics, 22: 572–586. doi: 10.1002/env.1088
- Issue published online: 5 MAY 2011
- Article first published online: 17 MAR 2011
- Manuscript Accepted: 15 OCT 2010
- Manuscript Revised: 19 JUL 2010
- Manuscript Received: 7 APR 2010
- advection equation;
- Bayesian hierarchical modelling;
- Gibbs sampling;
- spatiotemporal processes
We develop a physically motivated statistical model for regional ozone air pollution by separating the ground-level pollutant concentration field into three components, namely: transport, local production and large-scale mean trend mostly dominated by emission rates. The model is novel in the field of environmental spatial statistics in that it is a combined deterministic-statistical model, which gives a new perspective to the modelling of air pollution. The model is presented in a Bayesian hierarchical formalism, and explicitly accounts for advection of pollutants, using the advection equation.
We apply the model to a specific case of regional ozone pollution—the Lower Fraser valley of British Columbia, Canada. As a predictive tool, we demonstrate that the model vastly outperforms existing, simpler modelling approaches. Our study highlights the importance of simultaneously considering different aspects of an air pollution problem as well as taking into account the physical bases that govern the processes of interest. Copyright © 2011 John Wiley & Sons, Ltd.