Real-Time Water Quality Monitoring Trialled At Scalby Beck And Bridlington

Swimmers and river users will soon benefit from real-time water quality updates as a new artificial intelligence trial begins on the Yorkshire Coast.

Real-time water quality predictions will soon be available to swimmers and river users across the Yorkshire Coast.

A two-year artificial intelligence trial will transform how inland bathing waters are monitored, replacing historic laboratory testing with immediate insights.

Riverside sensors are currently taking readings every fifteen minutes at twenty bathing sites, including Scalby Beck in Scarborough and Springfield Avenue in Bridlington.

The new monitoring equipment continuously measures chemical levels such as dissolved oxygen, ammonia, and temperature.

This continuous data is combined with weekly manual samples to build an advanced predictive model, which will eventually give the public instant warnings about harmful bacteria before they enter the water.

Yorkshire Water's Manager of Strategic Partnerships, Miles Cameron, said:

"For bathing water, historically when it's measured, it's a bacterial measures as a lab test. Basically growing some in a petri dish. That takes 5 days. So when you get the results, it's too late. I've been swimming, so if it was bad, that's how the that's how the regulation, that's how it works. That's the nature of science.

There's a lot of work now in this space to understand how do you get what we call near or real time water quality monitoring. And we're doing a trial, and the exciting thing about it, we've actually got one of the monitors in Skegby Beck."

The data gathered during the trial will also support ongoing environmental investigations by the water company and the Environment Agency.

At Scalby Beck, water company officials confirmed a dedicated operational squad recently removed thirty-two tons of sand and silt from the sewer network near Whitby Road bridge to maximise capacity.

Specialist drainage contractors are also investigating up to twenty suspected plumbing misconnections at older properties and new housing estates in the area, according to the water provider.

Mr Cameron explained how the new monitoring equipment will assist these infrastructure operations:

"The idea is that you have a water quality instrument that measures what we call a standard water quality parameters, a look at ammonia, pH, temperature, conductivity. And in addition, we take four times a week bacteria samples. And over the next two years, we'll be using algorithm AI to weave those two sets of data together and it'll start to give a much more insight into water quality and be able to inform water users and bathers of water quality.

But what we are able to use is use that intelligence now, looking at Skull of Beck as an example, where there's any risk around ammonia because of the misconnections or our assets, we're using that intelligence and we're sharing that with the environment agency of part our investigations."

The monitoring project is funded by the water regulator Ofwat and is being delivered alongside artificial intelligence specialists UnifAI Technology, The Rivers Trust, and the British Standards Institution.

More than seven thousand data sets will be collected over the next twenty-four months to effectively train the predictive technology.

If the trial proves successful, a user-friendly web application will be launched, allowing residents and visitors to check near-live water conditions before making a decision to swim.

Coastal Delivery and Engagement Manager at Yorkshire Water, Faye Cossins, said:

"We know that people are passionate about their Yorkshire rivers and waterways, and they rightly want clearer, quicker information about water quality. This project has real potential to give communities near real‑time insights so they can make confident, informed decisions about taking a dip.

We're pleased to be leading this work with our partners and with funding from Ofwat's Breakthrough Challenge. It's an important step forward in innovation, transparency and preparing for future environmental monitoring requirements.

Using specialist monitoring sensors, on‑site sampling and UnifAI Technology machine‑learning, the 2-year project will gather over 7,800 samples from 20 varied inland bathing water sites. This data will be used to build a transferable, “site‑agnostic” AI model that can predict bacteria levels across different water types — from rivers to lidos to coastal inlets.

If proven, the technology has the potential to be deployed widely and at scale."