UK water company Severn Trent announced that it has started to utilise ‘machine learning’ to further develop the firm’s approach to leak detection.
According to a press release, the company has created an advanced leak detection model that uses data from its network to help identify, locate and manage leaks in its system.
“We’re really excited by this project, and it’s fantastic that we’re already seeing brilliant results,” said Rob Ryder, technology and lab data manager at Severn Trent.
“We’ve created the model by applying advanced analytics to data from our network of pipes collected through sensors, which gives us loads of valuable data which we can use to anticipate and manage leakage across our region. When using the model we’re getting the most out of our network data, giving us the upper-hand when it comes to locating and fixing leaks.”
The model is the result of a collaborative process between Severn Trent and France-based technology consultation company Capgemini. The model is already seeing ‘notable early results’ according to Severn Trent.
Sections of the network in which the model has been implemented, labelled as ‘pilot areas’, have reportedly seen a leakage decrease of over 16%.
“The amount of data we’re analysing is huge,” said Ryder.
“We’ve collected about five billion records of flow and pressure data that we’re able to use to help our teams on the ground while also ensuring we can understand our network better.
“This new advanced capability allows us to explore possible outcomes that were not previously available to us – so we’re in a position where we can tackle leakage more effectively and more quickly for our customers, and improve their experience with us.”
Severn Trent claims that it is now interested in utilising advanced analytics across other areas of the business as well.