Predicting Air Quality by Integrating a Mesoscopic Traffic Simulation Model and Simplified Air Pollutant Estimation Models

摘要

Continuous growth in traffic demand has led to a decrease in the air quality in various urban areas. More than ever, localauthorities for environmental protection and urban planners are interested in performing detailed investigations using trafficand air pollution simulations for testing various urban scenarios and raising citizen awareness where necessary. This article isfocused on the traffic and air pollution in the eco-neighbourhood Bnancy Grand Coeur^, located in a medium-size city from northeasternFrance. The main objective of this work is to build an integrated simulation model which would predict and visualizevarious environmental changes inside the neighbourhood such as: air pollution, traffic flow or meteorological information.Firstly, we conduct a data profiling analysis on the received data sets together with a discussion on the daily and hourly trafficpatterns, average nitrogen dioxide concentrations and the regional background concentrations recorded in the eco-neighbourhoodfor the study period. Secondly, we build the 3D mesoscopic traffic simulation model using real data sets from the local trafficmanagement centre. Thirdly, by using reliable data sets from the local air-quality management centre, we build a regressionmodel to predict the evolution of nitrogen dioxide concentrations, as a function of the simulated traffic flow and meteorologicaldata. We then validate the estimated results through comparisons with real data sets, with the purpose of supporting the trafficengineering decision-making and the smart city sustainability. The last section of the paper is reserved for further regressionstudies applied to other air pollutants monitored in the eco-neighbourhood, such as sulphur dioxide and particulate matter and adetailed discussion on benefit and challenges to conduct such studies.