Texas AI study links disparate data sets to identify dangerous road segments

In a study funded by the Texas Department of Transportation, a University of Houston professor combined multiple data sources such as pavement conditions and roadway geometry to identify the city's most dangerous roadway segments. 

As Nick Ross explains in an article for SMBtech, "At the core of the research is the use of large language model-based crash narrative analysis to identify and quantify pavement-related crash risk. The LLM component converts unstructured police crash narratives into structured, mechanism-specific labels – such as hydroplaning or curve-related loss of control."

The research differs from others in that it combines these vast datasets to add depth to crash research that is often missing key risk factors. "These details tend to be embedded in free-text narratives, making large-scale extraction difficult through manual review or simple keyword rules."