Uni of Sheffield develops AI system to detect sewer blockages and reduce river pollution

In a recent trial, a cloud-based artificial intelligence AI system designed by engineers from the University of Sheffield in collaboration with Yorkshire Water and Siemens, for sewer blockage detection has demonstrated an impressive accuracy rate of almost 90 per cent. The early detection of sewer blockages is important in mitigating pollution incidents that have a negative impact on UK-wide rivers.

This pioneering initiative forms an integral part of the ‘Pollution Incident Reduction Plan,’ which seeks to curtail pollution incidents by 50 per cent by the year 2025 through a proactive approach. Sewer systems incorporate ‘combined sewer overflows’ (CSOs), designed to release excess water into nearby water bodies during heavy rainfall, thereby preventing downstream flooding. However, these overflows can also occur due to unforeseen obstructions within the pipes, leading to unwanted pollution of rivers and waterways.

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.”

An array of sensors continuously monitors water levels within the CSOs and various segments of the sewer network, providing real-time insights into their performance. Given the sheer volume of sensors involved, manual analysis becomes impractical, necessitating the implementation of an automated system.

Originally conceived by the University of Sheffield and Yorkshire Water to enhance their previous analytical methods, this collaborative effort with Siemens has transformed the tool into a commercial cloud-based solution known as the Siemens Water (SIWA) Blockage Predictor.

This AI-driven solution forecasts water levels by analyzing rainfall data and comparing it with actual measurements through a sophisticated Fuzzy Logic (FL) algorithm. The FL algorithm promptly alerts water utility authorities to any unexpected surges in water levels that could potentially lead to pollution incidents. The primary objective is to identify impending blockages so that they can be proactively addressed before pollution ensues.

Professor Joby Boxall, Professor of Water Infrastructure Engineering in the University of Sheffield’s Department Civil and Structural Engineering, concluded: “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.”