News

Severn Trent creates machine learning to help tackle leakage by filtering five billion data points

Tuesday 4th December 2018

Midlands-based water company Severn Trent has started to use machine learning to help transform the way it approaches leaks.

The FTSE 100 company has created an advanced leakage detection model that uses data from its network to help identify, locate and manage leaks. 

The model forms part of an innovative programme of work that Severn Trent is undertaking to help reduce leakage, and it’s already seeing impressive early results.

Rob Ryder, Technology and Lab Data Manager, said: “We’re really excited by this project, and it’s fantastic that we’re already seeing brilliant results. 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.”

Severn Trent teamed up with Capgemini, a global leader in consulting, technology services and digital services in the UK, to create the complex machine learning model which is already seeing notable early results.

The company says that, in the areas the model has been used, time to find leaks has reduced by over half, engineers are able to pinpoint leaks more accurately, and overall the network in those pilot areas seen a reduction in leakage of over 16%.

“The amount of data we’re analysing is huge,” adds Rob. “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.”

Amit Ghosh, Group Account Executive Energy and Utilities at Capgemini’s UK Business Unit, said: “The success of leakage detection programme demonstrates strong partnership ethos between Severn Trent and Capgemini. We brought our deep expertise in data science and analytics, and our pre-built analytical models, which combined with Severn Trent’s subject matter expertise in leakage operations enabled them to fast track the roll out of the solution. Severn Trent is a true innovator who believes in the power of data and we are taking our relationship to next level by helping them build a strong internal capability to deliver a truly insight driven business.”

Severn Trent is now looking to use advanced analytics across other areas of its business, to help solve some of the company’s other key challenges.