Coalition Announced to Quantify, Locate Lead Pipes


At the end of September, Google announced that it was awarding $3 million in grants to the BlueConduit Charitable Fund, the Natural Resources Defense Council and the We Act for Environmental Justice organization to build an open-source tool for locating lead pipes.

The open-source tool is slated to help communities quantify and locate dangerous lead service lines for replacement.

“The massive uncertainty around fundamental questions like, ‘How many lead service lines do we have across our community?’ is both costly and dangerous,” said Eric Schwartz, BlueConduit Co-Founder and Associate Professor of marketing at the University of Michigan Ross School of Business.

“By providing these free tools and services and bringing together these partners, we aim to empower communities and water systems nationwide to efficiently replace these pipes, reduce the time that people are living with lead and generate more equitable outcomes for communities across the country.”   

About BlueConduit

Launched as a start-up company by the University of Michigan, BlueConduit is a water infrastructure analytics company that uses data and machine learning to help cities do service line inventories and replacement.

The technology was developed as the city of Flint, Michigan was working to replace lead service lines after mismanagement of the city’s water system caused pipeline corrosion and lead in the drinking water to spike to dangerous levels. While the water issue was eventually mitigated, locating lead lines throughout the city proved to also be challenging.

“The records are poor, and many of them have just been handwritten over decades,” said Schwartz. “Sometimes we were looking at records that had been manually entered in a spreadsheet after reading an atlas of hand-drawn maps, or index cards that have been in file cabinets in the basements of City Halls for decades. Even if you do your best to digitize those, they’re old and incomplete.”

Due to these issues, cities are often forced to spend thousands of dollars to dig and confirm whether a pipeline is made of lead or copper. In an effort to save time and money on the issue, Schwartz, along with other University of Michigan researchers, worked to develop a machine-learning tool that could better predict where lead pipes were most likely to be.

According to reports, the software works by collecting data about the ages of homes, the ages of neighborhoods, whether any records exist about the service line or others nearby and the size of the property, among other factors. From the collected data, the tool then uses machine learning to estimate the likelihood that the service line on the property is made from lead.

When BlueConduit first began testing the tool in Flint from 2016-2017, it was reported to successfully locate lead pipes roughly 80% of the time. In 2018, the city temporarily stopped using the algorithm, causing the hit rate to drop by 15%. After a 2019 court order, the software was reinstated.

“If there were enough resources to inspect every service line and replace the hazardous ones tomorrow, or next month, or even next year, then that would be fantastic,” says Schwartz. “No need to worry about optimizing. But in reality, there isn’t going to be enough funding or available labor to do that everywhere. Some needs to go first, so the order matters. The best a city can do is use its best information available, like the probability each home has lead, to aim to cut down the total time all residents are living with lead.”

Awarded Grants, Next Steps

Just as the Biden administration announced its initiative to remove lead pipes on a national scale, Google announced its coalition with We Act and NRDC, in addition to the award of $3 million to BlueConduit for the development of machine learning tools to map lead service lines and inform communities of the associated risks.

In a survey conducted by the NRDC, it is estimated that lead service lines carry drinking water to 9 to 12 million homes in the United States.

The new open-source tool is slated to help other cities to better understand the scope of their lead pipe problem and help municipalities estimate the cost of replacing potentially harmful water infrastructure. Additionally, the tool is also expected to allow water utilities to create public-facing maps that aim to strengthen public communication and help meet upcoming U.S. EPA Revised Lead and Copper Rule requirements.

“Lead service lines are a scourge that threaten families’ health in every state,” said Erik D. Olson, Senior Strategic Director for Health and Food at NRDC. This project will help residents learn the scope of the problem in their community and advocate for an equitable program to replace these lead pipes. No one should have to worry that the water flowing from their kitchen faucet could be contaminating their kids with lead.”

For the development of the toll, BlueConduit will be working closely with the We Act organization and NRDC. The funding will also be used to support collaboration between We Act and the NRDC to fund local community groups in three to-be-selected cities to facilitate increased outreach and education around service line replacement.

Specifically, the funding will be used to provide guidance and training to local organizations to support community engagement, education, and identifying and remediating risks of lead in water in their communities.

BlueConduit estimates that initial versions of the software will be available by the first half of 2022.


Tagged categories: Colleges and Universities; Environmental Controls; Good Technical Practice; Health & Safety; Health and safety; Infrastructure; Lead; Lead Renovation, Repair and Painting Rule (LRRP); NA; North America; Pipeline; Pipelines; Program/Project Management; Water/Wastewater

Join the Conversation:

Sign in to our community to add your comments.