Impact of Data Preparation on the Performance of Pipe Break Status Prediction Models
Bibliographic record
Abstract
Water distribution pipes convey clean drinking water to billions of end users around the globe. Unexpected pipe breaks can lead to several challenges, including reduced fire-fighting capability and contamination. Recent studies have developed machine learning models to predict pipe break status. Because the number of pipes that have never experienced breaks generally outnumbers broken pipes, pipe break data sets are inherently imbalanced. For this reason, different approaches for data preparation might yield different model performances. This study explored the impact of different data preparation strategies on the performance of pipe break status prediction for a case study water distribution system. The system had 55,561 pipes and 28,815 breaks recorded between 1970 and 2019. Because ANN, decision trees, XGBoost, and logistic regression were shown to perform well for similar models they were applied to all model variations. Four areas of variation were explored: (1) break type, (2) break period, (3) data splitting, and (4) data sampling. Firstly, data sets with first breaks and all breaks were compared. Secondly, break status was aggregated into one-year or five-year periods. Thirdly, random split of data and split by time period were compared. Fourthly, no sampling and undersampling of non-broken pipes was compared. In all cases, the last 10 years of data was excluded from training to ensure comparability of test results. All models were evaluated with F1 scores and AUC. Findings indicated that random data sampling and undersampling lead to skewed results. Future studies should consistently evaluate models based on selected time periods to better reflect real model performance.
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".