WRc & United Utilities Showcase: Ofwat Innovation Challenge – Artificial Intelligence and Sewers
Do you want to find out more about how a collaborative project between seven water companies and WRc has produced the industry’s first open source dataset aiming to considerably improve the process of assessing sewer defects?
United Utilities, in partnership with Dŵr Cymru (Welsh Water), Scottish Water, Severn Trent Water, South West Water, Thames Water, Water Research Centre, and Yorkshire Water Services have succeeded in doing just that by creating an open dataset of more than 27,000 classified CCTV images of sewer features which can be used to train AI models as well as validate and evaluate existing AI models.
Join Spring and United Utilities on the 14th November from 10:00-12:00 for a knowledge showcase where you will learn more about collaboration in the water sector, the creating of an open-source dataset and how artificial intelligence can be used to identify features in sewers.
Although we rarely think about it, sewers are vital to today’s society. To maintain their performance, they must be regularly assessed and maintained. Historically, this condition assessment has been in the hands of skilled inspectors, who must perform a repetitive and time-consuming process, painstakingly identifying all features and defects in the pipes according to the WRc Manual of Sewer Condition Classification 5th Edition.
Artificial intelligence (AI) can be used to improve the accuracy of the classification and reduce the overall time required. AI is widely used for object/ facial recognition in many sectors, and is gradually being adopted within the water sector to boost efficiency. While AI recognition is already used for defect recognition in sewer networks, the accuracy of current software is restricted by the images available to train the algorithms. Obtaining the data for AI development in the area of sewer condition assessments has been a significant obstacle for adoption of this technology, especially given the required number of images of each defect type often does not exist within just one company.
The Ofwat Innovation Challenge – Artificial Intelligence and Sewers project aims to remove this obstacle by pooling resources across all partner companies, creating a single benchmark dataset and accessible repository of classified sewer CCTV images. In doing this, the project team has developed the first open-source training dataset of its kind, paving the way for future innovation and development across the water sector, and beyond.
If you, or someone in your organisation, would like to hear more about the project and the learnings acquired then register today to reserve your space for this exciting innovation event!
