Have you ever felt a surge of adrenaline while navigating a particular intersection or highway during your daily commute? Perhaps it’s a short on-ramp that leaves you vulnerable or an intersection where drivers ignore red lights. These precarious spots represent more than mere moments of anxiety; they highlight flaws in urban planning that overlook human behavior. Understanding these risky areas is crucial, particularly given that Connecticut recorded nearly 100,000 car crashes in 2025, including 215 fatal incidents.
According to urban geographer Congcong Miao, these hazardous locations are not isolated incidents—they emerge from the shortcomings in urban planning methodologies. Fortunately, with robust data and targeted research, it is possible not only to identify these dangerous areas but also to implement effective solutions and preventative measures. By focusing on research-informed interventions, urban planners can mitigate the risks associated with hazardous environments.
Miao’s interest in this field blossomed during her time as a research assistant at the Connecticut Transportation Institute (CTI) at the University of Connecticut. “The first project I worked on at CTI involved visualizing traffic crash data across Connecticut dating back to 2015,” she recalls. Her initial surprise at the traffic crash statistics opened her eyes to the reality that, despite her perception of safety while driving, a significant number of accidents occur annually. While many are minor, the aggregate figures were far above what she had anticipated.
Intrigued by these statistics, Miao questioned whether certain areas had disproportionately high crash rates and sought to uncover the common characteristics of these locations.
This inquiry led to Miao’s first published paper as a doctoral student, where she developed a spatial-temporal statistical methodology to explore these questions. Her work introduced a novel approach that not only tracks areas with elevated crash rates but also considers the timing of these incidents and their severity.
In her subsequent research, Miao discovered a surprising human dimension to road safety: not only do physical characteristics of environments impact safety, but so do people’s perceptions of these conditions. “My research is grounded in a simple idea: the environment can influence human safety both directly and indirectly,” Miao states. “Physical factors like road surface and glare can directly affect the likelihood of crashes, but the emotional context of how individuals experience their surroundings is equally significant.”
Healthy Habitats
Beyond her work on traffic incidents, Miao is committed to improving urban planning methodologies that intersect with public health. Earlier this year, she was honored with the Peter Gould Paper Award from the American Association of Geographers (AAG) Health and Medical Geography Specialty Group for her efforts using mobility data to understand food access and its effects on health.
Moreover, she has published research addressing healthcare access, particularly for specific providers like pediatric dermatologists. Her findings pinpoint access issues and offer policy recommendations to improve these challenges.
Miao describes her broader goal: “I aim to leverage large-scale geospatial data to analyze human behavior and to inform policies that are both effective and equitable.” Throughout her doctoral journey at UConn, she collaborated with professors Xiang “Peter” Chen, Chuanrong “Cindy” Zhang, and Suining “Henry” He, who share her passion for spatial analytics and health geography.
Tools of the Trade
Miao’s research employs sophisticated software tools, especially geospatial artificial intelligence (GeoAI). She explains how AI assists in various layers of her research. For instance, GeoAI can analyze urban environment images, such as those from Google Street View, to derive their physical characteristics.
“Using AI tools, we can extract detailed characteristics from images that reflect the environmental conditions of our cities,” Miao explains. “This method allows us to methodically examine the features associated with high-risk areas or potentially hazardous environments.”
AI also aids researchers like Miao in deciphering human behavior patterns, which is vital for navigating the vast, complex datasets geographers often encounter.
Furthermore, this technology has opened a new front for Miao’s research: refining AI tools for better reliability and practicality in geographic analysis. “Many of the AI tools we use may generate maps but can also produce errors due to a lack of basic geographic literacy,” she clarifies. “I am particularly interested in how to design AI systems that can understand geographic concepts more effectively, thus developing a more sophisticated geographic intelligence.”
Miao will continue to explore these questions as she embarks on the next chapter of her career, having accepted an assistant professorship in spatial data science and GeoAI at Binghamton University, where she will begin her teaching and research this fall.
