Nonstationary POT modelling of air pollution concentrations: Statistical analysis of the traffic and meteorological impact

TL;DR

This study develops advanced non-stationary extreme value models to analyze how traffic and weather influence high air pollution levels, improving prediction accuracy for environmental health assessments.

Contribution

The paper introduces a novel GPD parameterization that ensures threshold stability, enhancing the modeling of non-stationary air pollution extremes.

Findings

Model II outperforms Model I in estimation accuracy.

Traffic and meteorological factors significantly affect extreme pollution levels.

The new model provides better forecasting of high pollution events.

Abstract

Predicting the occurrence, level and duration of high air pollution concentrations exceeding a given critical level enables researchers to study the health impact of road traffic on local air quality and to inform public policy action. Precise estimates of the probabilities of occurrence and level of extreme concentrations are formidable due to the combination of complex physical and chemical processes involved. This underpins the need for developing sophisticated extreme value models, in particular allowing for non-stationarity of environmental time series. In this paper, extremes of nitrogen oxide (NO), nitrogen dioxide (NO$_2$) and ozone (O$_3$) concentrations are investigated using two models. Model I is based on an extended peaks-over-threshold (POT) approach developed by A. C. Davison and R. L. Smith, whereby the parameters of the underlying generalized Pareto distribution (GPD) are treated as functions of covariates (i.e., traffic and meteorological factors). The new Model II resolves the lack of threshold stability in the Davison--Smith model by constructing a special functional form for the GPD parameters. For each of the models, the effects of trafic and meteorological factors on the frequency and size of extreme values are estimated using Markov chain Monte Carlo methods. Finally, appropriate goodness-of-fit tests and model selection criteria confirm that Model II significantly outperforms Model I in estimation and forecasting of extremes.