Macroscopic Emission Modeling of Urban Traffic Using Probe Vehicle Data: A Machine Learning Approach

The recent study on macroscopic emission modeling of urban traffic represents a significant advancement in understanding and managing urban congestion, which is a major contributor to greenhouse gas emissions and air pollution. By leveraging machine learning techniques and large-scale probe vehicle data, the research establishes a predictive relationship between traffic and network-wide emission rates in U.S. urban areas. This innovative approach addresses the historical limitations of empirical eMFD models, which have been sparse due to a lack of comprehensive data. The findings not only enhance the understanding of how emissions vary with different urban characteristics but also empower transportation authorities to implement data-driven strategies for measuring and managing carbon emissions. As cities continue to grapple with traffic-related challenges, this study provides a crucial tool for optimizing traffic flow and reducing environmental impacts, ultimately contributing to more …