A collaborative project involving the University of Sheffield, Yorkshire Water and Siemens is using a cloud-based artificial intelligence (AI) system designed to detect blockages in sewers. The system has shown an almost 90 per cent accuracy rate in a recent trial.

Early identification of sewer blockages is essential to reduce pollution incidents affecting our rivers. AI algorithms can analyse vast datasets in real-time, enhancing our ability to predict and manage flood events more effectively. By employing smart sensors and monitoring systems powered by AI, we can detect and respond to pollution incidents swiftly, implementing targeted interventions to safeguard water quality. Using AI in water management strategies is already delivering a proactive and dynamic approach. It contributes to sustainable practices and allows us to be more resilient against the challenges of flooding and river pollution.

The project is a collaboration between the University of Sheffield, Yorkshire Water, and tech company Siemens, and is a part of the ‘Pollution Incident Reduction Plan’ which focuses on early intervention to reduce pollution incidents by 50 per cent by 2025.

Sewers have ‘combined sewer overflows’ (CSOs) which let excess water spill out into a nearby water body when the pipes are full due to heavy rainfall, preventing downstream flooding. These spillages can also be caused by unexpected restrictions in the pipe, such as blockages, resulting in unnecessary pollution of our rivers and watercourses.

Sensors monitor water depth in the CSOs, and other parts of the sewer network, allowing real time understanding of performance. The quantity of sensors makes manual analysis infeasible, hence an automated system is needed.

The technique was originally developed by the University of Sheffield and Yorkshire Water to improve on their previous analytics technique. This project with Siemens has further developed the tool into a commercial, cloud-based solution – the Siemens Water (SIWA) Blockage Predictor.

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.

The AI based solution predicts water depths using rainfall data and compares these to the measured depth using a Fuzzy Logic (FL) algorithm. The FL alerts the water utility of any unexpectedly high depths which could lead to a pollution incident. The aim is to identify developing blockages so that they can be removed before pollution occurs.

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.

A new peer reviewed journal article presents an assessment of the SIWA Blockage Predictor for 50 CSOs over a two year ‘historic’ period and a six month ‘live’ period. The article also compares performance to the previous analytics solution. Across the full dataset, 88.4 per cent of confirmed issues were correctly identified, compared to 26.6 per cent for the previous solution.

Dr Will Shepherd, Principal Investigator from the University of Sheffield’s Department of Civil and Structural Engineering, said: “Our sewer networks were not designed to convey heavy rainfall to treatment, CSOs provide an essential relief valve when rain would otherwise cause flooding further down the network.  Our focus here is on making them as environmentally friendly as possible by identifying blockages which would cause premature spills and hence pollution of rivers and watercourses.”

Professor Joby Boxall, Professor of Water Infrastructure Engineering in the University of Sheffield’s Department Civil and Structural Engineering, said: “The synergies of the collaborative partnership approach to this research was vital to success. It was important that the different needs and ambitions of each partner was mutually recognised and respected from the outset and that we built and maintained a high level of trust.”

This success story was first published in NCUB’s ‘Drops of innovation: Navigating the waters of collaboration‘ showcasing report.