Ride on through
Sean Qian receives NSF award to combine big data and transportation system modeling to improve traffic flow and the way we create and operate transportation systems.
Almost everyone knows–and dreads–the feeling of getting stuck in traffic. Annually Americans spend billions of hours idling in egregious congestion, yet this doesn’t necessarily have to be the case. The Department of Civil and Environmental Engineering’s (CEE) Sean Qian is working with big data and transportation system modeling to develop a mathematical framework to improve the flow of traffic, and to improve the way we design, plan, and operate transportation systems. For his work, the National Science Foundation (NSF) has awarded him the Faculty Early Career Development Program (CAREER) Award, complete with $500,000 in funding for the next five years.
The NSF gives the CAREER Award to early-career faculty members who are expanding their field, demonstrating an ability to conduct groundbreaking research and also educate the next generation of innovators. Qian’s work uses massive amounts of data that’s available from various sources to better understand and predict the function of multi-modal transportation systems (combinations of multiple transportation systems, such as highways, urban streets, public transit, parking, bikes, connected automated vehicles, etc.).
The data Qian uses is already available; however, it is siloed, meaning it’s split between multiple transportation agencies. This makes it practically impossible to analyze or draw inferences about the operation of the overarching multi-modal system. Qian’s project will bring together disparate data sets, fusing the information to create a clearer picture of how each system functions and affects the next. This will better reflect how individuals move through and between systems toward their destinations.
The information gleaned from Qian’s work will help transportation agencies manage their respective systems. To enable this, he’ll look at changes in vehicular and passenger flow from one day to the next, or the day-to-day variance. His project will examine unique factors that distinguish each day to predict how individuals will move through the system.
He will also examine how likely the vehicle/passenger flow exceeds a threshold at any location in the transportation network, rather than an average. This can be learned from massive data collected over many years. This would allow more informative and reliable decision-making on infrastructure design and operation.
“If we know that there will be higher demand, we can allocate more resources and workers to manage this,” says Qian. “If there’s an incident, we can do the same, or possibly redesign the road to reduce the possibility or effect of future incidents.”
For Qian, an incident isn’t just a traffic accident or a natural disaster; an incident can be any major event that disrupts traffic, be it a sporting event, road closure, or an unplanned work zone. With the way data is siloed, we are unable to gain a clear picture of how these events affect the larger multi-modal system. If we can help travelers understand when and where people are traveling, they can better plan or be guided to avoid congestion. This reduces the overall strain on the system, ensuring better, more consistent transit times.
“The idea is that we can develop a kind of decision-making tool for travelers and provide agencies with easy, more effective ways to manage traffic and reduce congestion and emissions. It’s a win-win for both sides,” Qian says.
Many of those who will use his framework will be engineers who are currently still in school. Qian believes that now is the time to prepare them for the challenges ahead. With the lessons learned through this project, he will develop graduate and undergraduate infrastructure management courses that place greater emphasis on data analysis.
“It’s very important to teach the next generation of engineers how to design a bridge, a mobility service, and infrastructure, and also how to manage, monitor, and operate them by leveraging existing data and resources,” says Qian.
Some of the sources for Qian’s data include the Pennsylvania Department of Transportation, the City of Pittsburgh, the Port Authority of Allegheny County, the Pittsburgh Parking Authority, and the Pennsylvanian municipalities of McKees Rocks and Cranberry.