From AI to electric snowplows, WVU researchers are exploring ways to modernize

Motivated by extreme weather events like the 2021 winter storm in Texas, a West Virginia University researcher is looking for new technologies to re-imagine how state and city agencies maintain roads and other transportation networks.

Kakan Dey’s expansive research will investigate the many ways a data-driven approach can improve road maintenance operations — from modernizing maintenance vehicle fleets and rethinking the placement of operational centers to leveraging artificial intelligence that analyzes real-time information collected by sensors on consumers’ cars or at train stations. roadside observation.

With funding from the prestigious and highly competitive National Science Foundation CAREER award worth $540,000, Dey, an associate professor at WVU’s Benjamin M. Statler College of Engineering and Mineral Resources, will consider how to transition to an all-electric maintenance fleet and how to tackle maintenance. operations in scenarios where real-time data is flowing from sources such as “connected vehicles”, or cars that can transmit data about road conditions.

Like a smartphone on wheels, connected vehicles capture and upload data about speed, road conditions, temperature, road friction and a host of factors that tell artificial intelligence systems which parts of the transportation network need immediate attention. Such information can allow emergency operations and maintenance to prioritize highways where real-time data indicates major problems and minimize time and resources spent on roads that are less affected.

October marks the official launch date for Dey’s five-year project, Maintenance of the Transport Network under Climate Change, Resource Uncertainty, and Connectivity.

Dey will also transform case studies from research into educational activities for K-12 and higher education students and provide continuing education opportunities for transport network maintenance professionals, with special attention to engaging underrepresented groups.

Explore data

Dey said his main focus was on winter weather conditions, although his research could also be applied to roads affected by problems such as potholes or flooding – two other transport-related problems that are causing an increase in climate change.

By the time winter hits, he explained, every state transportation department has a weather response plan. Units know where to go first if a storm comes. Depending on several criteria, they knew how many plows to send and which route to take. Certain limited adjustments may be made to the plan, based on information from existing data sources such as the National Weather Service or permanent observation stations.

Dey envisions an alternative, where data comes from sources such as portable weather observation stations and “connected vehicles”.

Places with the highest risk for weather-related traffic problems should still have permanent observation stations, he explained. But data from portable weather observation stations and connected vehicles can provide real-time insight into low-priority locations and areas where permanent observation stations are not economical, enabling agencies to use AI to analyze that data and adjust operations quickly.

“The US surface transportation system is in dire shape, with bridges and roads no longer able to support the growing demand for freight and passenger transportation in many areas,” Dey said. “Winter storms and other severe weather conditions triggered by climate change will place an enormous burden. This research lays the foundation for transforming traditional and static transport network maintenance operations into next-generation dynamic programs.”

Invest in modernization

Dey said he believes agencies like state DOT should make a gradual transition to electric fleets to minimize the environmental impact of maintaining the transport network, which means not only replacing existing fleets but also building charging station infrastructure.

That would require a large upfront investment, and fortunately, Dey acknowledged, that the research was done against the backdrop of the $108 billion earmarked for transport in the 2022 Bipartisan Infrastructure Act.

But Dey says a responsive approach to transport network maintenance means economic savings after the initial investment. He estimates a reduction in winter maintenance costs and time when operational decision making takes into account real-time data from multiple sources.

And he argues that the cost is worth it.

“Twenty-one percent of traffic accidents occur during bad winter weather conditions,” said Dey. “Weather-related traffic delays cost the US freight transportation industry $2.2 to $3.5 billion annually. And transportation agencies spend over $2.3 billion annually on winter road maintenance in the U.S. Among all types of transportation network maintenance, winter road maintenance is the most complex and resource intensive.”

Research that drives education

Because a skilled transportation workforce is critical to the future of high-tech transport, Dey said, he will engage K-12 students and WVU engineering students with hands-on classes and activities based on his research. For K-12 classrooms, he will create simplified case studies, while WVU’s new undergraduate and graduate program in civil engineering asset management will teach students to develop and deploy technological solutions to manage transportation systems.

She said, “It is critical that we start building the future STEM workforce by raising awareness about STEM careers in K-12 students, preparing the next generation of engineers through multidisciplinary research opportunities and engaging underrepresented groups in engineering, such as women, minorities , and the first generation. class student. It’s also important for us to engage with professional organizations and train the current workforce on new technologies and advanced analytics.”

Anurag Srivastava, chair of the Lane Department of Computer Science and Electrical Engineering will lend his expertise to the project, who will consult on the grid implications of switching to an all-electric fleet; Associate Professor Omar Abdul-Aziz, who will contribute to predicting the effects of climate change on weather patterns; and Assistant Professor Abhik Roy, program evaluation specialist from the College of Applied Human Sciences.