Sign In

Communications of the ACM

ACM TechNews

How Big Data and Algorithms Are Slashing the Cost of Fixing Flint's Water Crisis

A big data analysis indicates the focus on service line replacement may only go so far at fixing Flint’s water issues.

Researchers at the University of Michigan are using data analytics to help resolve the water contamination in Flint, MI.

Credit: George Thomas/flickr

University of Michigan researchers are using data analytics methods similar to those employed by Facebook and Amazon to help solve the water contamination in Flint, MI.

A challenge for recovery has been a lack of useful information and understanding of locations most at risk for lead contamination. Only about 30% of homes in Flint have had their water tested, and city officials have had difficulty identifying which homes are at risk. By leveraging algorithmic and statistical tools, the Michigan team has been able to produce a more complete picture of the risks in Flint.

The researchers say data connected to the water crisis was compiled, including more than 20,000 water samples, records of home service lines, and information on land and water usage. Records of service line installations and the materials used for each home's pipes are incomplete, but machine-learning techniques were able to seek patterns in the existing records and predict the type of material in a home's service line with 80% accuracy. Data on individual homes, including the year of construction, location, value, and size, also were used to create risk profiles.

The researchers say they have made the risk assessments available to Flint officials and residents via a mobile application.

From The Conversation
View Full Article


Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA


No entries found

Read CACM in a free mobile app!
Access the latest issue, plus archived issues and more
ACM Logo
  • ACM CACM apps available for iPad, iPhone and iPod Touch, and Android platforms
  • ACM Digital Library apps available for iOS, Android, and Windows devices
  • Download an app and sign in to it with your ACM Web Account
Find the app for your mobile device