PUB's Anomaly Leak Finder — Singapore's AI Digital-Twin System for Underground Water-Pipe Leak Detection

PUB, Singapore's national water agency, developed the Anomaly Leak Finder (ALF), a cloud-hosted system built on Bentley Systems' iTwin and OpenFlows software that combines a data-driven prediction (DDP) model with a physics-based simulation (PBS) model. Hydraulic models are recalibrated daily against live monitoring data from over 90 smart sensors to create a high-fidelity digital twin of more than 1,000km of pipelines across four major distribution networks, run 24/7.
Since January 2024, ALF has detected and localised two significant underground leaks to within roughly one kilometre, alerting PUB's leak-detection crews before the leaks became disruptive. The tool also flags related anomalies such as sensor failures and pressure shifts from changing demand, which earlier acoustic-only sensor deployments (120 sensors trialled from 2017, expanded to 1,500 permanent leak-detection sensors network-wide) could not distinguish from genuine leaks on their own.
ALF sits within a longer-running PUB leak-management programme: more than 330km of pipes have been renewed since 2016, and in 2024 PUB repaired 267 pipe leaks (about 4.5 leaks per 100km of the 6,000km network per year). PUB has not yet published network-wide non-revenue-water savings attributable specifically to ALF, and the two confirmed leaks so far represent an early-stage result rather than a mature performance track record.

Read the full analysis: https://yii.bentley.com/project/high-fidelity-digital-twin-enabled-anomaly-detection-and-localization-in-singapore/