Mobile Computing

U Michigan, Google Partner on Flint Water Tools

• By Leila Meyer
• 05/04/16

Students at the University of Michigan's Flint and Ann Arbor campuses are collaborating with Google to develop an Android app and web-based tools to help Flint residents determine whether their home water supply is at risk of lead contamination and locate resources to cope with the problem.

According to information from the university, students in UM-Flint Computer Science's community-based learning program have already developed a prototype of the Android app. The team is now collaborating with Google and students from U-M Ann Arbor's Michigan Data Science Team to integrate mapping features using predictive analytics developed by the U-M Ann Arbor students, and they are working with Google to improve the user interface of the app. The completed app is slated for release this summer.

The app uses predictive algorithms and machine learning techniques to analyze data from Google, the State of Michigan and the City of Flint to help determine which homes and neighborhoods are at greatest risk of contamination. "There's a lot of data on the water crisis, but it's scattered over many different agencies and places," said Jacob Abernethy, an assistant professor of computer science and engineering at U-M Ann Arbor and faculty advisor to the Michigan Data Science Team, in a news release. "By organizing it in one place and analyzing it, we can predict which areas are likely to be at risk."

Google and the University of Michigan are also planning a separate project to develop web-based tools for researchers and government representatives with the goal of helping them plan repairs and deploy resources. Those tools will include "extensive mapping and predictive analytics, with details on waterline type and location and other infrastructure data," according to the news release.

"We can help planners determine which infrastructure repairs will benefit the most residents, and how to allocate resources like bottled water most efficiently" said Abernethy.

The project is funded by a $150,000 grant from Google. The tech company has also contributed remote and on-site development assistance, as well as data resources such as mapping, satellite imagery and geo-location data.