A systematic review of urban road traffic CO<sub>2</sub> emission models
Chenglong Yu, Xiaoguang Yang, Jiantao Mu, Sijin Liu
Abstract
With rapid urbanization and increasing mobility demand, urban traffic systems face intensifying congestion, resulting in elevated CO2 emissions. This paper provides a systematic review of the current status of models estimating CO2 emissions from urban road traffic, considering their applicability across various traffic management scenarios. Urban road traffic CO2 emission models can generally be categorized into two main types. Traditional models typically estimate emissions based on average speed, traffic conditions, or vehicle operation modes, whereas data-driven models leverage techniques such as machine learning and deep learning to capture complex emission patterns. The review proposes a set of model selection criteria, namely data availability, computational complexity, interpretability, and transferability. Based on a comparative evaluation of these criteria, the study finds that there is no one-size-fits-all model so far. Instead, model suitability depends heavily on local data infrastructure and specific application needs. Therefore, future work needs to enhance model localization and personalization to improve estimation accuracy, while the integration of spatiotemporal data-driven modeling approaches is likely to become a research hotspot in upcoming studies.