Dissertation Grant - Project Description:

This dissertation explores the use of a knowledge graph (KG) framework to enhance systemic road safety analysis, contrasting with the traditional focus on high-crash locations which is often narrow, data-dependent, and reactive. The research advocates for a systemic safety analysis that evaluates risk factors across the entire road network, offering a more holistic approach to road safety. 

The study addresses several critical questions: How does integrating diverse road safety data into a knowledge graph enhance the understanding of systemic risk factors across the network? What role do advanced graph-based analytical techniques play in identifying high-risk areas that are not apparent through conventional methods? Can a systemic approach using a knowledge graph effectively allocate safety interventions to underrepresented rural or less-traveled roads, thereby reducing crash severity and frequency? 

Methodologically, the research involves aggregating a variety of data sources—crash databases, traffic management systems, weather data, and road network information—into a comprehensive knowledge graph. This integration supports advanced analysis techniques that help identify and mitigate potential safety issues system wide. The framework not only facilitates the identification of risky factors but also enhances the capability to implement targeted safety interventions where they are most needed, including in rural areas.

The anticipated contributions of this research are promising to shift the paradigm in traffic safety analysis from a reactive to a more proactive, equitable approach. It aims to ensure a fair distribution of road safety resources, improving safety across all road types and conditions.