Journal of Earth Sciences and Geotechnical Engineering

How Selection Techniques on Traffic Data Sets Can Help in Estimating Network Vehicle Emissions

• [ Download ]
• Times downloaded: 9703

• Abstract

   

  Road traffic is a major source of air pollution in urban areas. Policy makers are pushing for different solutions including new traffic management strategies that can directly lower pollutants emissions. To assess the performances of such strategies, the calculation of pollution emission should take into account traffic dynamics. The use of traditional on-road sensors (e.g. inductive loops) for collecting real-time data is necessary but not sufficient because of their expensive cost of implementation. It is also a disadvantage that such technologies, for practical reasons, only provide local information. Some methods should then be applied to expand this local information to large spatial extent. These methods currently suffer from the following limitations: (i) the relationship between missing data mechanisms/patterns and the estimation accuracy, both cannot be easily determined and (ii) the calculations on large area is computationally expensive. Given a dynamic traffic simulation, we take a novel approach to this problem by applying selection techniques that can identify the most relevant locations to estimate the network vehicle emissions. This paper explores the use of a statistical method, i.e. the Lasso regularized generalized linear models, as powerful tool for selecting the most relevant traffic information on a network to determine the total pollution emission.