One key component of non-revenue water is physical water loss, specifically leaks within the water distribution system. This refers to water that is simply lost en route to consumers. According to the Spanish daily El País, in some localities losses exceed 60% supply.
Servicios de Txingudi, the public utility responsible for the water supply in the northern Spanish municipalities of Irun and Hondarribia, is leveraging the SIWA Leak Finder app to address water loss.
SIWA Leak Finder is a software solution for detecting and pre-locating leaks in water transport and distribution networks by using artificial intelligence to analyze real-time flow data. The tool lets operators detect and repair leaks quickly while minimizing false alarms.
Furthermore, thanks to AI, the system is capable of recognizing seasonal patterns influenced by tourism and weather conditions.
In less than a month, SIWA Leak Finder was implemented across the entire network covering 285 km of pipes and trained on a three-week dataset.
The fast track was possible because sensors were already in place — Servicios de Txingudi was one of the first utilities in Spain to install smart water meters. The tool processes data from flow meters, pressure sensors, chlorine sensors, and more — including daily customer water meter readings. Thus, it possible to identify leaks quickly based on KPIs from each distribution management area.
Since SIWA Leak Finder entered operations in January 2017, over 10,000 events have been detected and solved, including leaks, pressure issues, chlorine anomalies, sensor failures, data transmission problems and theft.
The system also manages seasonal changes in consumption patterns, allowing for dynamic changes as a result of increased population in the summer.