Criteria-based critical review of artificial intelligence applications in water-leak management
Bibliographic record
Abstract
Leakages in water distribution networks (WDNs) cause economic losses and environmental hazards. It is, therefore, unsurprising that water-leak management has been a focus of research over the last couple of decades, but leaks in WDNs still occur frequently. Thus, this domain is experiencing a transformation from traditional signal processing and statistical-based models to artificial intelligence (AI) based models for recognizing complex leak patterns, handling large datasets, and establishing accurate leak-management models, especially in leak detection and localization. However, a comprehensive review of the application of AI in water-leak management is largely missing from the literature. To bridge this gap, this review presents a criteria-based critical review to systematically investigate the existing literature on the application of AI in four sub-domains of leak management including leak detection, localization, prediction, and sizing. The first criterion (research attributes) established the (1) research trends, (2) links between influential countries and sources, and (3) popular keywords using scientometric analysis. The systematic analysis of the second criterion (research technicality) and the third criterion (research focus) revealed the (1) AI-techniques adopted, (2) equipment used for collecting data, (3) data features used in the models, (4) objectives of different models adopted, (5) type of experiments conducted to collect the data, and (6) types of pipes for which models were developed. The study highlighted research gaps, future research directions, and proposed a leak management framework for upcoming AI studies in this domain. This review is intended to serve early researchers by enhancing their understanding of existing research in AI-based leak management as well as seasoned researchers by providing a platform for future research.
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 | 0.010 | 0.031 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.002 |
| Bibliometrics | 0.020 | 0.019 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.004 | 0.004 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
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".