Public transit systems influence roadway safety through changes in travel behavior, congestion levels, and modal distribution, yet the specific mechanisms linking transit characteristics to safety outcomes are not well quantified. While prior studies suggest that higher transit use is associated with improved safety, agencies lack clear guidance on which system features contribute most to these effects. This project addresses that gap through large-scale data integration and predictive modeling.
The research will combine crash data, transit system attributes, roadway network characteristics, and demographic indicators from national and regional data sources. Machine learning models will be developed to predict crash rates as a function of transit network size, service intensity, demand, and multimodal shares. Explainable modeling techniques will be used to identify the most influential predictors of safety outcomes at both metropolitan and town levels. Results will provide actionable evidence to support data-driven transit planning and roadway safety strategies.