Mathematicians in Chicago Stopping Water Leaks in Syracuse

Published on by in Technology

Mathematicians in Chicago Stopping Water Leaks in Syracuse

Using an algorithm developed by a team at the University of Chicago, Syracuse, NY, can fix mains before they break. 

On average, water lines in Syracuse were breaking 332 times a year, nearly once every day.

Mayor Stephanie Miner couldn’t get the state to help foot the bill for the onerous costs of updating the city’s underground infrastructure. Then she turned to big data.

To get to the bottom of the problem of catastrophic water main breaks, Syracuse first had to understand what was happening underground and where. 

Using an algorithm developed by a team at the University of Chicago, the city put reams of information, scattered among various departments, to work. With a predictive system that can point to the hotspots along its 550 miles of pipes, the city hopes to save millions of dollars a year by fixing mains  before  they break. 

zI2PcAu.jpg
A Syracuse Water Department contractor attaches a blue sleeve connector to a broken water main. | AP Images 
Image source: Politico Magazine

Syracuse is one of only two cities in the state—the other is New York City—that has such a clean water supply that it does not need a filtration plant.

however, Syracuse is an aging industrial city with a dwindling population, a crime problem, and bitter cold winters typical of upstate New York. It averages nearly one water main break a day, which is not unusual for an older northern city but which costs the city $1 million a year for repairs and replacement. Its water main system has parts that are more than 100 years old. 

Miner’s logic was simple: “Why would we spend millions of dollars on economic development above a system and then not pay any attention below and a month later have a road blow up because we didn’t replace the water mains?”

The bigger question was, what would be the smartest way to spend the city’s limited resources? The search for an answer was helped along in 2015 by a three-year grant of $1.35 million from Bloomberg Philanthropies to create the City of Syracuse’s i-team, which is focused on infrastructure improvement.

Using the know-how of a team from the University of Chicago’s Eric and Wendy Schmidt Data Science for Social Good program, Syracuse began a laborious project to first gather and enter the data into a digital form, and then create an algorithm that would predict just where those mains were most likely to break.

This machine-learning system, an application of artificial intelligence, homed in on 50 (out of 5,263) of the city’s most break-prone blocks and pointed to 32 blocks that were most likely to break in the next three years. 

To get to that formula, researchers applied a series of factors—age of pipes, construction material, previous breaks and pipe dimensions—to breaks that happened in the past as a way to “predict the past,” or test whether the formula, working blind, could accurately guess which mains would break.

Rayid Ghani, director of the University of Chicago’s Data Science for Social Good summer fellowship, says, “If you have 10 years of data, you take nine years and hide the tenth year from the system. So you pretend it’s 2015 and you try to predict what would have happened.”

One surprise in the findings, notes Ghani, was that pipes that had broken recently tended to be more likely to break again, possibly because of some intrinsic flaw that hadn’t been corrected with a repair. Keep in mind that the city expects to see 500 to 600 breaks over the next few years, says data officer Edelstein. When the city does replace some mains in the 32 hotspots, “we’d be pretty sure we are replacing the ones most likely to break,” he says.

Source: Politico Magazine

Media

Taxonomy