The Slow Leaks Nobody Detects

Current leak detection methods in water distribution networks — including graph-based multilayer approaches, ML anomaly detection, and IoT smart metering — suffer from two compounding failures: gradual-onset leaks that develop slowly over time evade detection for 700+ hours, while abrupt leaks can be caught in approximately 15 minutes; and ML-based anomaly detection produces high false positive rates that trigger costly unnecessary investigations and erode operator trust. Non-revenue water losses remain at approximately 30% of global supply (~126 billion m³/year, ~$14 billion annual economic loss).

Water utilities worldwide lose roughly one-third of treated water before it reaches consumers. In many developing-country utilities, losses exceed 50%. Gradual leaks — from corrosion, joint degradation, or pressure cycling — account for the majority of water loss volume because they persist undetected for weeks or months. Each hour of undetected leaking wastes water, undermines infrastructure integrity, and risks contamination through negative pressure events that draw untreated groundwater into pipes.

A benchmark study on a standard water distribution test network found: 73.9% true positive rate (17 of 23 test leaks detected), 17.4% completely missed, and 8.7% false positives. Gradual leaks required 700+ hours for detection versus 15 minutes for abrupt leaks. Localization accuracy ranged from 42 to 378 meters from the actual leak site. Leaks were only detected when flow reached ~3 L/s (1–2% of total network inlet flow) — smaller leaks went entirely unnoticed. Single-layer graph approaches fail because they cannot model the relationship between physical infrastructure and monitored data. Conventional z-score and IQR outlier detection increased detection time by 38 hours for the smallest leak, representing 140 m³ of unnecessary water loss. More than 40% of small water utilities cite high installation and maintenance costs as a barrier to IoT sensor deployment.

Multilayer network models that couple hydraulic state with infrastructure topology show promise but need validation on real (not benchmark) distribution systems. Physics-informed machine learning that encodes hydraulic constraints could reduce false positives while maintaining sensitivity. Low-cost acoustic sensors deployed at strategic network nodes — rather than comprehensive coverage — could provide cost-effective monitoring for smaller utilities. Transfer learning approaches could allow models trained on data-rich utilities to be deployed in data-poor ones.

A team could partner with a local water utility to deploy a small acoustic sensor array on a known leak-prone section of pipe, comparing detection latency between the sensor system and the utility's existing monitoring. An algorithmic team could develop and test a multilayer network detection model using publicly available benchmark datasets (such as BattLeDIM or LeakDB), specifically targeting gradual-onset leak scenarios. Relevant disciplines: civil/environmental engineering, signal processing, network science, machine learning.