Leakage detection in water distribution networks plays an instrumental role in effectively addressing water loss, yet the scarcity of annotated leak events limits the applicability of supervised classification methods. While hydraulic simulation-generated datasets are often considered as an alternative, their generation is hindered by incomplete network topology and sparse sensor coverage in real-world settings. Consequently, many real-world solutions rely on unsupervised anomaly detection approaches but frequently struggle to balance sensitivity and accuracy. This study proposes a regression-ensemble framework that learns the district metered area (DMA)-specific demand–supply dynamics to detect emerging leaks using smart meter data, without requiring real or simulated labeled leak datasets for training. Regression models—Random Forest, Support Vector Regression, XGBoost, and Multi-Layer Perceptron—are trained on DMA-level consumption and supply data that are preprocessed to preserve background leakage while correcting emerging leaks. Deviations between predicted and observed supply are quantified through Pearson correlation, Kendall’s tau, and Z-score, whose anomaly indications are combined at metric and model levels using weights derived from model prediction accuracy. A leak is identified once the ensemble anomaly score crosses a threshold. The system detects leaks within 8–12 h of onset, achieving 90% and 98% accuracy on simulated and real leak scenarios, respectively, at an anomaly-score threshold of 0.5. Recall rates of 85% and 95% are observed for simulated and real leaks, respectively, whereas 95% and 100% recall are observed for no-leak events in both leak scenarios, respectively. Our proposed framework demonstrates the potential of smart meter-driven ensemble analytics for rapid and robust leak detection.
Chatterjee et al. (Fri,) studied this question.