New advanced technology developed for computer games and artificial intelligence might be used to detect leaking pipes, according to a team of researchers at Exeter University.

The team from university's Centre for Water Systems is working on new software that will be capable of detecting problems in a water distribution network. To develop the software, the team is trying to understand how to identify false alarms.

The team is also relying on powerful computer processors that are designed for supporting complex 3D graphics, for developing models that determine how rainfall or building work might affect the probability of flooding in an area much faster than existing systems.

Prof Dragan Savic, director of the Centre for Water Systems told The Engineer said, `It is important for a water company to get information [about leaking pipes] as soon as possible because then they can intervene before the loss of pressure is felt by the customer.'

Existing mechanism in water distribution involves the use of thousands of pressure and flow sensors that send information to a control centre every 30 minutes to allow the software to detect anomalies in the water flow. However, about four in five of these are false alarms caused by sensor issues, the signal transmission or flooding due to heavy rain.

This mechanism relies on human intervention on knowing which abnormality is real. The new system learns how to do this without human intervention after jus about an hour of detecting water leaks.

The three-year research project is funded by the Engineering and Physical Sciences Research Council and 12 industrial partners. The finished program will be released in open source allowing any organization to use the software.