US to spend millions on AI for flood detection and traffic problems

An influx of federal infrastructure money "shows huge appetite" for innovative solutions to tackle traffic problems, says Shailen Bhatt.
Amal Jos Chacko
Water crashing over bridge
Water crashing over bridge

Eric Overton/iStock 

The state of Delaware is set to introduce Artificial Intelligence to keep citizens safe from possible weather threats by predicting them early and broadcasting alerts.

Home to some of the most beautiful beaches on the East Coast, Delaware recovered from a COVID slump to attract a record number of 28.3 million visitors in 2021, expected to be surpassed by 2022 figures to be released later this year.

However, these numbers, combined with limited exit routes and low elevation, make the state susceptible to massive flooding.

Delaware’s transportation department controls over 90% of roads in the state and is responsible for evacuations during high water. Although evacuation-type procedures stemming from floods have become a common sight during the tourism season, standing water on roads renders most direct routes out of town more dangerous than sheltering in place.

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

The state aims to reduce these situations by leveraging artificial intelligence to trigger future evacuation plans automatically.

“For humans to monitor thousands of detectors or data sources is overwhelming, “ said George Zhao, director of transportation at BlueHalo, a technology company that worked with the state to develop the software.

“What’s new is the predictive analysis; the machine learning. Because now we have access to all this data, it’s hard for us as humans to figure out what is data and what is actionable information,” U.S. Federal Highway Administrator Shailen Bhatt, Delaware’s former transportation secretary, told The Associated Press.

The new system will detect and predict threats by analyzing sensor data and sending appropriate information to drivers through cell phone alerts and electronic highway signs.

More money, fewer problems

An earlier version of a flood prediction analysis system tested on the Mississippi River between 2019-22 cut down detection time from hours to minutes. Steve Corns, co-author of that study and an associate professor of engineering management and systems engineering, said that current capabilities were even more advanced and useful.

The Biden administration is set to announce $53 million in grants from the infrastructure law signed in 2021 to eight states to combat traffic congestion problems with high-tech solutions.

Apart from Delaware, Maryland will receive $14 million for machine learning traffic prediction, and Michigan $12.7 million to retrofit its current traffic system with cellular technology that could be adopted on a national level.

This article was written and edited by a human, with the assistance of Generative AI tools. Find out more about our policy on AI-powered writing here.

Add Interesting Engineering to your Google News feed.
Add Interesting Engineering to your Google News feed.
message circleSHOW COMMENT (1)chevron
Job Board