Project Summary
Freight truck traffic, essential for commerce, generates significant air and noise pollution, disproportionately burdening low-income communities and communities of color. Traditional data methods lack the granularity to fully capture truck activity and quantify these environmental justice (EJ) impacts. This research proposes a new data fusion and modeling framework by leveraging agent-based simulation and machine learning algorithms with enhanced data collection methods, including GPS, probe and sensor data, to create a high-resolution understanding of truck patterns, flows, and their localized effects. By linking this activity data with spatiotemporally dynamic exposure estimates and socio-demographic information, the research team will quantitatively assess exposure disparities in EJ communities. Focusing on California, the study will also evaluate the potential of truck electrification, driven by state regulations, to mitigate these environmental and health impacts, particularly for overburdened populations. This research will provide critical data and methodologies for government agencies, planners, and community advocates seeking to address the complex challenges at the intersection of freight transportation, environmental quality, and social equity.
