Top Factors Leading to Water Main Failures—An Analysis of 12 Canadian Cities
Bibliographic record
Abstract
Water main deterioration is a global challenge which can jeopardize the ability of water systems to deliver clean water safely. A variety of factors can affect pipe breakage, yet previous research has focused on different subsets of data. The key objective of this study is to identify the most important factors in predicting water main failure across multiple Canadian cities. The study included data organizing, data cleaning, and dimensionality reduction analyses. Two approaches were applied to analyze the importance of factors affecting water main rate of failure, factor analysis of mixed data (FAMD) and random forest. Data from 12 water utilities across Canada were analyzed, containing information on pipe physical characteristics, historical information, protection activities, environmental factors, and operational condition. Available attributes were different for each city. Overall, the two methods rated failure month and protection as the most important factors. While random forest consistently found age to be the most important attribute, FAMD results indicated that either failure month or material was the most important factor. Random forest results were observed to be biased as they consistently rated numerical attributes as more important than categorical. Thus, FAMD results are expected to be more reliable. Future data collection should focus on pipe characteristics and protection activities. Next steps of the project will include conducting other dimension reduction approaches and running correlation analyses. Findings will support the development of a framework for pipe and break data collection. This will help water utilities develop cost-effective and accurate water main deterioration models, enabling more reliable renewal strategies for water distribution systems.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.009 |
| Science and technology studies | 0.004 | 0.001 |
| Scholarly communication | 0.002 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".