Delaware Taps Artificial Intelligence To Evacuate Crowded Beaches When Floods Hit

Delaware’s low elevation, combined with crowded coastlines and limited access, make the state particularly vulnerable to major flooding, but officials hope an influx of federal infrastructure money will spur future evacuation plans.

The Biden administration is set to announce a total of $53 million in grants to Delaware and seven other states aimed at high-tech solutions to traffic congestion problems. Although the money is from the infrastructure bill the president signed in 2021, many of the programs — including $5 million for flood response efforts in Biden’s country — have since evolved.

“What’s new is predictive analytics; Delaware’s former transportation secretary, US Federal Highway Administrator Shailene Bhatt, said in an interview with The Associated Press. Because we now have access to all this information, it is difficult for us as humans to know what is data and what is actionable data.

Delaware officials do away with evacuation-style procedures every week during the tourist season, when long lines of cars head to the beaches on weekend mornings and evenings. But flooding presents a unique problem – including standing water on roads that makes the most direct routes out of town more treacherous than simply sheltering in place.

“What you don’t want to do is make the decision too late and then have vehicles impounded,” said Gene Donaldson, operations manager for the state’s 24-hour Transportation Management Center.

The Delaware Department of Transportation, which controls more than 90% of the roads in the state with the lowest average elevation in the country, is tasked with implementing evacuation plans during high water — a bureaucratic nightmare given how quickly conditions can change.

That’s where AI comes in. Instead of sending crews to the scene to block a static road, the system uses sensors to detect weather threats — and can even predict them. It then sends the information directly to drivers via mobile phone alerts, simultaneously broadcasting on electronic highway signs.

The amount of information is growing as more automated cars are able to not only inform their drivers of the danger ahead, but feed the system to warn others.

Researchers at the Missouri University of Science and Technology tested an earlier version of the Mississippi River flood forecast system between 2019-22. Steve Korns, associate professor of engineering management and systems engineering, who co-authored the study, said the system was able to separate what would take hours in minutes.

But now, Korns said, the capabilities are more advanced and useful — if they’re funded enough to keep the technology from becoming obsolete.

The previous law provided more than $300 million in congestion relief aid, and Bhatt said the agency received $385 million for a $52.8 million application under the Infrastructure Act. “It shows a huge appetite” for new solutions to traffic problems, he said.

Other payments in this grant round include $14 million for machine learning traffic forecasting and signal timing in Maryland, and $12.7 million in Ann Arbor, Michigan, which could become a national model for retrofitting the traffic system with cellular technology. It also includes $11.6 million to expand microtransit service in Grand Rapids, Minnesota.

The Weather Company’s core journalistic mission is to report on breaking weather news, the environment and the importance of science to our lives. This story does not necessarily represent the position of our parent company, IBM.