• With such a wealth of information here at SWAN, we want to make it easier for you to find the knowledge you seek as quickly as possible.

  • Lighthouse uses some of the most advanced AI language models to understand your questions and sifts through SWAN's entire knowledge base to find an answer. We have carefully trained it to present relevant information in a consolidated way.

  • As you navigate an ocean of information, let Lighthouse be your beacon.

  • Disclaimer: We cannot always guarantee complete or accurate responses, given that AI-powered dialogue is still an emerging technology. Lighthouse will always accompany answers with the most relevant references, which we encourage you to check out. We highly value your feedback to ensure that Lighthouse meets the highest standards of quality and reliability. If you notice something off, please contact us at:

  • Ready to join us?

    SWAN Members enjoy full access to Lighthouse (unlimited searches and gated content) along with global membership benefits.

Looking for classic search?

Case Study

Leveraging AI for Sewer Network Management in the UK

StormHarvester and Severn Trent complete successful proof-of-concept project for blockage detection, leading to a full network rollout of the solution.


Related Topics

Sewer Blockage Detection

AI/Machine Learning

Severn Trent Water is one of the largest of the 11 regulated water and sewerage companies in England and Wales. It provides high quality water and waste services to more than 4.5 million homes and businesses in the Midlands, from the outskirts of Bristol to the southern suburbs of Sheffield.


Severn Trent wanted to strengthen their ability to respond to sewer network alerts. This would mean being able to prevent sewer blockages before they occur and reduce pollution and flooding leading to better protection for customers, communities and the environment. In February 2023, Severn Trent began working with StormHarvester on a proof-of-concept (PoC) for blockage detection on the wastewater catchment of South Derbyshire.


Severn Trent Water provided sewer level data for 393 sites, which StormHarvester ingested and cleaned the sewer level data matching it with the corresponding hyperlocal rainfall data from the same locale. Focusing on a single catchment allowed Severn Trent to focus on the quality of alerts over a small area to ascertain the accuracy of StormHarvester predictions. During the trial, the nature and timing of the alerts allowed the Operations Team to move from reactive to proactive control by adjusting to a new way of working.


The highly accurate machine learning model meant that Operations Team at Severn Trent Water were alerted to potential blockages and pollutions ahead of time and were able to mobilise the appropriate response to the right place at the right time to return “full flow.” This meant there was no detriment to customers or the environment.

During the 5-month trial:

  • 11 pollution incidents were avoided.
  • 93 sites had remedial works completed and are now operating in an improved and steady managed state.
  • 46 restrictions/partial blockages were found and fixed.
  • 0 pollution events were missed by the StormHarvester system.

Following the success of the POC, Severn Trent Water have instigated a full network roll out of the StormHarvester solution.

Within the first few months the difference in performance was clear to see not only in the accuracy and timeliness of alerts, but also crucially during storm events the reduction in volume of alerts was very impressive. This gave us confidence to go ahead and roll out across our entire network. 

– Jason Dearlove, Waste Smart Networks Lead, Severn Trent Water
Featured SWAN Members: