River deep mountain AI

A collaborative Ofwat Innovation Fund project that developed open-source, scalable digital solutions that support effective action to reduce pollution in UK waterbodies. 

Developed

eight open-source AI and remote sensing proof-of-concept models, supported by comprehensive datasets, handbooks, and practical guidance for water sector stakeholders.

Demonstrated

how advanced analytics and AI can significantly enhance understanding of waterbody health and pollution.

Enabled

open access to water quality data through integration with platforms such as Stream, improving transparency and usability across the sector.

Project partners

ADAS, Anglian Water, Cognizant, Dŵr Cymru Welsh Water, Northern Ireland Water, Northumbrian Water, South West Water, Stream, The Rivers Trust, Uisce Éireann, Water Research Centre Limited, Wessex Water, Xylem Inc.

As part of River Deep Mountain AI, the open-source proof-of-concept models and guidance are available on GitHub.



The Challenge

Under the Water Framework Directive, 86% of UK rivers fail to meet ‘good’ ecological status, with evidence suggesting that three in four rivers may pose a potential risk to human health.

The water industry continues to invest heavily in catchment management to improve water quality at source while addressing the growing pressures of population growth and climate change. Although monitoring capabilities have expanded, the sector faces a critical challenge:

  • Managing and analysing increasingly large volumes of data
  • Identifying cost-effective approaches to extract actionable insights
  • Turning complex datasets into informed, timely decision-making

The Solution

Through the River Deep Mountain AI project, a suite of open-source, scalable digital models was developed to support proactive water quality management across the sector.

Funded by the Ofwat Innovation Fund and led by Northumbrian Water, the collaboration harnessed expertise from across the industry including UK water companies, consultants, non-governmental organisations and regulators.

WRc played a key role by contributing scientific knowledge and domain expertise on river water quality, catchment management and data science, ensuring that each model is, scientifically robust, operationally relevant aligned with real-world catchment management challenges.

These models leverage AI and remote sensing technologies to provide new insights into pollution sources, behaviours, and risks.

The Outcome 

By making all project outputs freely available as open-source resources, River Deep Mountain AI is helping to accelerate sector-wide progress in improving the health of UK waterbodies. The application of AI and remote sensing enables stakeholders to better understand the complex and interconnected factors driving pollution, supporting more targeted interventions and ultimately contributing to healthier rivers and reduced risks to both ecosystems and public health.

Crucially, the project unlocks the full potential of existing data by transforming it into actionable insight. By identifying patterns, trends, and emerging risks at scale, the models provide the base for stronger evidence for decision-making, enabling water companies, regulators, and partners to respond more effectively and efficiently to water quality challenges, while laying the groundwork for continued innovation across the sector.

Related items

Related case studies 

Created by potrace 1.16, written by Peter Selinger 2001-2019

Start a conversation

Full name
Email address
Company name
How can we help?

Can we stay in touch?

Your details will be stored within our CRM to allow us to handle your enquiry. We'd love to keep in touch and send you our newsletters and other notifications we think may be of interest to you. Please let us know if we have your permission for this.