- University of Sheffield researchers have developed and helped to deliver game-changing artificial intelligence (AI) that can predict blockages in sewers
- Blockage predictor tool can help to prevent sewers from backing up during heavy rainfall, which can flood homes, gardens and rivers with wastewater
- Tool has been developed as part of a collaboration between the University of Sheffield, Siemens and Yorkshire Water
- Yorkshire Water is rolling out the new AI to its network of more than 2,000 combined sewer overflows (CSOs) in a bid to reduce pollution risks in the region
Game-changing artificial intelligence that can predict blockages in sewers to help cut pollution incidents and improve the health of rivers has been developed as part of a collaboration between the University of Sheffield, Siemens and Yorkshire Water.
The new digital technology, initially developed by researchers in the University’s Department of Civil and Structural Engineering, commercialised by Siemens and then successfully piloted by Yorkshire Water, is set to be rolled out to Yorkshire Water’s network of more than 2,000 combined sewer overflows (CSOs) in a bid to reduce pollution risks in the region.
Combined sewers carry both foul water from homes and businesses, as well as rainwater which falls onto impermeable areas such as pavements, roofs and highways. As the weather can be unpredictable, CSOs reduce the pressure on sewers during heavy rainfall events and stop the system from backing up and flooding homes and gardens by allowing heavily diluted wastewater to be discharged into watercourses.
The integrated sensing, communication, analytics and reporting solution works by using sensors to feed water level data into the SIWA Blockage Predictor, an application on Siemens’ cloud-based, open Internet of Things (IoT) operating system, MindSphere.
The performance of the sewer network is analysed in real time and predicts problems like network blockages before they happen - enabling Yorkshire Water to quickly investigate the predicted blockage and prevent it developing into sewage pollution in the environment.
Analysis of 21,300 days of data by researchers at the University of Sheffield found the blockage predictor can provide up to two weeks’ notice of problems within the sewer network and identify nine out of 10 potential issues - three times more successful than existing pollution prediction processes, while reducing the number of false positive alerts by 50 per cent.
Heather Sheffield, Integrated Planning and Central Control Manager at Yorkshire Water, said: “Much of our network in Yorkshire is combined, taking both waste from toilets and sinks in home and surface water from rainfall. Periods of prolonged or intense rainfall can significantly increase the flows in our network and there is a risk of sewage flooding in homes, the environment, and the potential for damage at wastewater treatment works.
“This challenge is compounded by population growth, climate change and consumer behaviour which puts non-flushable items like wipes into sewers, causing or accelerating blockages.
“Reducing intermittent discharges from CSOs is a key priority for us and our partnership with Siemens and the University of Sheffield illustrates Yorkshire Water’s commitment to investing in cutting-edge technology to reduce pollution incidents by 50 per cent, a key goal of our Pollution Incident Reduction Plan 2020-2025.
“Our customers expect us to use the latest technologies. This solution, developed in partnership with Siemens and the University of Sheffield, will change our visibility of the sewer network and improve how we identify and tackle blockages.
“Rolling out the solution to 2,000 assets across the entire county will have a significant role in reducing the number of pollution incidents, which can have a negative impact on the environment, as well as increasing our efficiency and providing improved value to our customers.”
The collaboration builds on previous research by PhD students and research staff in the University of Sheffield’s Department of Civil and Structural Engineering - one of the most renowned centres of excellence for urban water engineering in the UK. A tool was developed, with funding from Yorkshire Water, which allowed sewers with degrading performance to be identified.
Siemens harnessed the research tool and developed it into a commercial product. At the University of Sheffield, researchers worked with Siemens through their development process and validated the results from the commercialised tool against the original tool.
The University’s researchers also analysed data from Yorkshire Water to assess the efficiency of the tool in predicting blockages downstream of CSOs, which have the potential to cause flooding and river pollution. A key benefit of the tool is that it can learn how a sewer usually responds to rainfall and detect any changes - this gives it the ability to identify sewers that are deteriorating in performance before any adverse impacts can occur.
Professor Joby Boxall, Professor of Water Infrastructure Engineering in the University of Sheffield’s Department Civil and Structural Engineering, said: "Key to the technical advance we made was combining our depth of expertise in both artificial Intelligence and water engineering. The long term collaborative partnerships we have with Yorkshire Water and Siemens are essential to moving beyond concept and enabling translation into a reliable service that is delivering benefits at scale."
Adam Cartwright, Head of IoT Application Delivery at Siemens, said: “SIWA Blockage Predictor is a step change in how water companies can avoid pollution incidents. The AI can work on existing or new sensors in the network. Integrated reporting of spills and overflow events will support water companies as they rise to the challenge set by the Storm Overflows Taskforce for greater transparency and open data.”
Dr Will Shepherd, Principal Investigator from the University of Sheffield’s Department of Civil and Structural Engineering, said: “This project with Siemens and Yorkshire Water has been a great example of commercialising university research to provide a tool which will reduce environmental impacts from our sewer networks by rapidly identifying blockages and enabling targeted maintenance.”
Contact:
For further information please contact:
