Review of model-based and data-driven approaches for leak detection and location in water distribution systems

TLDR

Leak detection and location in water distribution systems is crucial for reducing water loss, yet it remains a major challenge for utilities; researchers have proposed many methods, with model‑based and data‑driven approaches widely used, though model‑based methods require highly calibrated hydraulic models and are sensitive to uncertainties, while data‑driven methods avoid deep system understanding but often yield high false positives and cannot handle anomalous variations from unexpected water demands. The paper reviews both model‑based and data‑driven leak detection approaches and classifies the techniques they employ. The authors conduct a systematic review and classification of leak detection methods used in these approaches.

Abstract

Abstract Leak detection and location in water distribution systems (WDSs) is of utmost importance for reducing water loss, which is, however, a major challenge for water utility companies. To this end, researchers have proposed a multitude of methods to detect such leaks in WDSs. Model-based and data-driven approaches, in particular, have found widespread uses in this area. In this paper, we reviewed both these approaches and classified the techniques used by them according to their leak detection methods. It is seen that model-based approaches require highly calibrated hydraulic models, and their accuracies are sensitive to modeling and measurement uncertainties. On the contrary, data-driven approaches do not require an in-depth understanding of the WDS. However, they tend to result in high false positive rates. Furthermore, neither of these approaches can handle anomalous variations caused by unexpected water demands.