We present a novel typology of 349 metropolitan statistical areas in the United States and demonstrate its implication for understanding and mitigating per-capita mobile greenhouse gas emissions (PMGEs). Via factor analysis of 55 indicators across seven categories, we identified eight key drivers of mobile emissions. Based on these, we clustered the metro areas via Gaussian mixture modeling to obtain seven metro types. We used an extreme gradient boosting regression model to predict PMGEs based on all the indicators, excluding population. Using SHapley Additive exPlanations values, we identified the most relevant indicators. The model reveals that density and transit mitigate PMGEs, while car use and climate exacerbate it. The typology provides further insights into how these effects vary across network, mode share and development patterns. Ultimately, the typology can serve as a framework to identify relevant indicators and thereby guide the selection of strategies for effective, type-specific emissions mitigation.

Read original article

Read original article