Moderate evidence
Published recordScienceProblem Space
More
Effectiveness of Different Ground Truths at Detecting Lead Service Pipes Using Machine Learning
- Truvace record
- TRV-2026-2887raw data (JSON)
- Version
- v1Published
- First published
- Evidence type
- Controlled or validated comparison
- Sources
- 1 sourcePeer-reviewed
- sha256
- 6935ca95ad07…check it
Replacing all existing lead service pipes (SPs) is an important strategic goal for the water industry because lead SPs represent a clear health risk. For example, the UK water industry has been instructed by the Drinking Water Inspectorate to be lead-free by 2050, and the USEPA has assigned $3 billion to tackle lead. The first key challenge in achieving this goal is determining whether a property’s service pipes are made of lead. Previous research into the application of machine learning (ML) to this problem has…
The problem
A study using a large real-world UK water company dataset found that machine learning models trained on lead concentration sampling or asset records performed no better than random chance at identifying properties with lead service pipes.
What this doesn’t fix
The evaluation used data from one UK water company, so how the results hold for other networks is not established by the study.
Sources
1 on file- Journal of Water Resources Planning and Managementdoi:10.1061/jwrmd5.wreng-7717
Cite this record
v1Truvace Impact Record TRV-2026-2887, v1: “Effectiveness of Different Ground Truths at Detecting Lead Service Pipes Using Machine Learning.” Truvace, 2026-11-13. /record/TRV-2026-2887 (accessed on the day you copy it). sha256 6935ca95ad07d0c1…
Change history
1 versionEvery change made to this record since it was first published, and why. Nothing has changed since it went up.
Certified into the record
Check this record hasn’t been altered
How to check it yourself, without trusting this page
Download any version from /api/record/TRV-2026-2887 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.
ace