A new study using AI, traffic data, and Google Street View reveals that greenery, sidewalks, and streetlights can significantly reduce traffic fatalities.
Most people use Google Street View to find their way. But researchers at the University of Maryland (UMD) School of Public Health recently used it to locate spots where your journey might abruptly end. Their study, published this month in the British Medical Journal (BMJ) of Injury Prevention, leveraged AI tools to identify key environmental elements impacting car-related collisions, as well as cyclist-related and pedestrian-related accidents.
"Car crashes are the leading cause of death for young people between 5 and 29 years old. So it's crucial to understand how the physical environment can increase or lessen fatal collisions and which communities are most affected by this," explains Dr. Quynh Nguyen, an epidemiologist and statistician at UMD whose work involves combining technology and big data sources to address health disparities.
Nguyen and her team used Google Street View (GSV), which offers 360-degree views of streets, to determine the relationship between car accidents and the built environment in locations where crashes occur. Using virtual mapping, they examined specific road features, like streetlights or greenery, on a nationwide scale.
"Because we could crunch such a large amount of GSV data from across the country, we got precise results on which built elements influence car crashes," says Nguyen. "It was clear that places with higher levels of greenery, streetlights, single-lane roads, and sidewalks were associated with fewer fatal car crashes."
Sidewalks had the greatest impact on reducing crashes. Places with more sidewalks had 70% fewer traffic accidents, while places with one single-lane road – frequently found in rural areas – had 50% fewer accidents.
For pedestrians and cyclists, streetlights and stop signs offered more safety – they were associated with fewer car accidents involving either group. Conversely, areas with road construction had an adverse effect, with more collisions.
"Many of the public health issues communities face are often solvable," said Xiaohe Yue, a data analyst at UMD School of Public Health and study co‑author. "Emerging technologies and access to extensive data sources have been helpful in finding solutions to some of the public health issues that plague populations."
The researchers hope their findings will inform transport and infrastructure policy by offering proven, practical options for decision-makers to improve road safety for drivers, pedestrians, and cyclists.
"We hope that our work will lead urban planners and developers to consider the built environment more carefully and so design safer streets and communities," said co‑author Heran Mane, data analyst working with Yue.
Nguyen sees a whole new research pathway emerging: "We are seeing a rise in leveraging data science and AI to enable larger, more efficient and more timely studies like this one," she said. "This research is one demonstration of how we can use AI to improve public health, and we know there's so much more to come."
Nguyen and colleagues are now looking to expand the types of built environment indicators examined across the United States, as well as exploring these features in other countries.
By FutureTimeLine
