Preparing for the Replacement Era: Understanding North America's Aging Water Distribution Systems
Bibliographic record
Abstract
Water utilities throughout North America are facing a major infrastructure crisis. The large number of watermains installed during the urban expansion that occurred at the beginning of the 20th century and during the Baby-Boom are exceeding their design life and pipe breaks are increasing. Utilities are now faced with the difficult task of replacing watermains while still ensuring reliable delivery of drinking water to their customers. This thesis assists utilities in solving the aging watermain infrastructure crisis by improving pipe break prediction models, which are a critical tool in scheduling pipe replacement. First, this thesis improves the understanding of various pipe break prediction models. This research identifies machine learning models that are very accurate for ranking which pipes are likely to fail next. However, most machine learning models developed for pipe break prediction do not incorporate right censored data which results in the model being biased towards early pipe failure and thus aggressive pipe replacement schedules. This thesis improves prediction modelling by developing the first Random Survival Forest watermain failure model. The results indicate that incorporating the machine learning model into a survival analysis framework, the machine learning model is no longer biased towards early failure prediction. Therefore, utilities wishing to develop long-term pipe replacement strategies should adopt a machine learning survival analysis model. Lastly, this thesis examines the long-term trends of Canadian pipe breaks. The findings from this research identify that break rates for major water utilities in Canada have not increased substantially since the 1990s. Furthermore, this research quantifies the impact pipe rehabilitation has played in lowering break rates over the last three decades. Overall, this thesis advances the research into pipe break prediction models by identifying the impact of limited datasets on various prediction models, developing an advanced machine learning survival analysis model that accurately predicts time-to next failure, and quantifying the impact of pipe rehabilitation techniques on long-term break trends in Canada. This information is significant to many utilities throughout Canada and much of the developed world as they begin to face an aging watermain infrastructure crisis that threatens the supply of clean drinking water.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".