Multivariate time series modelling for urban air quality

We introduce a spatio-temporal model to represent development of atmospheric pollution in an urban area. An important element this is that recorded measurements are often incomplete which undermines time-series approaches. identify the multiple imputation by chained equation (MICE) method as effective complete data sequences synthetically. Following on from this, we develop vector autoregressive moving average (VARMA) for areas. This was fitted hourly four pollutants (NO, NO 2 , x and PM 10 ) whole calendar year 2017 at 30 stations across London, completed MICE required. show cross-validation VARMA more than other formulations, including Kriging spatial interpolation, seasonal ARMA models individual with either daily or weekly trends. The resulting can be used prediction air quality different periods basis assessment policy interventions such increasing vehicle emission standards, traffic management control policies low ultra-low zones. • Developing London. Proposing synthesise sequences. Cross validating stations.