A Complex Analysis Employing ARIMA Model and Statistical Methods on Air Pollutants Recorded in Ploiesti, Romania

Abstract

Air pollution is an everyday issue, very relevant to public authorities, requiring control and monitoring to provide data for decision-making policies. The objective of this study was to evaluate the air quality in Ploiesti city, Romania and to observe the advantages and limitations of the some statistical methods used in forecasting air quality. Data for six air quality parameters collected at monitoring stations in Ploiesti during the 2013 year were statistically analyzed. Principal component analysis (PCA) was used to provide a relevant description in factors that can be explained in terms of different sources of air pollution. The measured pollutants data were statistically analyzed using the auto-regressive integrated moving average (ARIMA) method in order to assess the efficiency of using this method in forecasting the environmental air quality. The results revealed that ARIMA method has some limitations and do not produce satisfactory results for certain air pollutants such as PM10 and CO, even the forecasted period is short. By comparison, the ARIMA model obtained for NOx , NO2 , or O3 time series, provides good results, with relative errors around 5%.