Sign In

Communications of the ACM

ACM TechNews

Flint Water Crisis: How AI Is Finding Thousands of Hazardous Pipes

View as: Print Mobile App Share:
Replacing water pipes in Flint, MI.

An artificially intelligent algorithm is helping to target lead water pipes for replacement in Flint, MI.

Credit: Jim West/ZUMA Wire/REX/Shutterstock

Georgia Institute of Technology (Georgia Tech) researchers have developed an artificial intelligence (AI) algorithm that can determine the location of dangerous lead pipes in Flint, MI.

A team led by Georgia Tech's Jacob Abernethy designed the AI algorithm to predict which residences are connected to lead pipes by analyzing old city plans and about 140,000 handwritten records of building work rendered digitally.

The AI catalogs 71 pieces of information for every property in Flint, including the age, value, and site of the home.

The algorithm trained itself on properties where lead levels had been measured, to anticipate other homes that were likely to have lead pipes. The AI system can list properties with lead pipes with a 97% success rate, which is expected to save $10 million and make an additional 2,000 homes safe.

Prior to Georgia Tech's algorithm, homes were selected for pipe replacement based on educated guesses, with 20% of pipes dug up turning out not to be lead.

The researchers gave their data to Flint's cleanup crew, and they say the model can be applied to other cities.

From New Scientist
View Full Article


Abstracts Copyright © 2018 Information Inc., Bethesda, Maryland, USA


No entries found