Researchers at Exeter University have claimed that they have found a new way to use computer game technology and artificial intelligence to detect leaking pipes and predict floods.

A team of researchers from Centre for Water Systems of Exeter University said that they used computer processors intended for supporting complex 3D graphics to create models and developed software that is much better in detecting anomalies in a water distribution network.

Powerful graphics processing units support the current 3D graphics which feature life-like effects. University of Exeter researchers have used this technology to visualize and detect leaks and flood risks.

Currently, water firms have to use hundreds of pressure and flow sensors to detect leaking pipes, but they often give false, or 'ghost' alarms. This prompted researchers to develop the new approach, based on technology developed in the field of artificial intelligence, which is deployed as a piece of software installed on a computer in the control room of a water company.

The software constantly takes delivery of data and processes it and then searches for problems indicating the presence of a leak. After identifying the potential problem, an alarm notifies the control room operator. It also provides information on the possible location of the leak and suggests immediate actions to tackle the problem.

Centre for Water Systems’ director, Professor Dragan Savic, 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.”

As per an estimate, water industry collects, treats, and distributes more than 17 billion liters of water across 335,000 km of mains across the UK.