An innovative solution by Yorkshire Water and partners that uses AI models to provide continuous river water quality monitoring at multiple inland bathing water sites has been awarded £1.93 million in Ofwat’s £42 million+ Water Breakthrough Challenge competition.

Scarborough Beach

The AI-Water Quality Monitoring Project - a collaboration between Yorkshire Water and UnifAI Technology along with, The Rivers Trust, British Standards Institution (BSI), supported by Surfers Against Sewage (SAS) will develop AI-based models to monitor water quality at 20 inland bathing sites. The partners are contributing a further £215,000 to take the project total to £2.15 million.

Faye Cossins, coastal delivery and engagement manager, Yorkshire Water, said:

“We’re grateful for this important funding from the Ofwat Water Breakthrough Challenge as it allows us to fast-track this research project that significantly reduces the time and cost of expanding large-scale continuous bacteria monitoring at 20 inland bathing water sites.

“This solution aligns with national priorities for public health and environmental protection and enables water users to access real time information on water quality so they can safely and confidently enjoy our rivers and bathing sites.

“It is an emotive subject, and we know one that matters to our customers and to our stakeholders. We are really pleased that campaign group Surfers Against Sewage (SAS) are supportive of the research project. Together with our collaborators, British Standards Institution, The Rivers Trust and other utilities, we are collectively working towards the common goal of improving bathing water quality.”

Currently, water quality monitoring at bathing sites relies on periodic sampling and laboratory testing, which are both slow and costly, and often provide delayed results.

The project aims to address both challenges by deploying water quality sensors and carrying out an intensive programme of bacteriological sampling at 20 sites across Yorkshire in order to develop a site-agnostic, scalable solution and accelerate adoption across Yorkshire and the UK.

Developing Generalised AI Models across diverse water bodies will remove the need for training localised, site-specific models that will significantly reduce the time and cost of wider roll-out of near real-time bacteria monitoring in the future.

Phil Hughes, CEO of UnifAI, explained:

“UnifAI Technology is delighted to be working with Yorkshire Water and partners to develop an AI model for river water quality by monitoring and sampling across 20 locations. This project builds on our proven success using AI and virtual sensors to monitor harmful bacteria in rivers and will provide near real-time information for water-users and stakeholders.

“By developing scalable, site-agnostic AI models that work 'out of the box' at diverse locations, we'll significantly enhance public safety, support environmental stewardship and enable water companies to rapidly respond to pollution events.

“This project will make it easier and faster to roll-out the solution. It will enable us to create AI models that can be deployed across multiple sites with varying water conditions that remove the need for site-specific customisation and provide real-time information about water quality. Current monitoring methods rely on periodic sampling and laboratory testing, which are both slow and costly. This project addresses these challenges by implementing a hardware-agnostic, scalable system that leverages Generalised AI Models for real-time monitoring and predictive analytics.”