AI-powered CCTV spots blockages to prevent floods

The ‘AI on the River’ platform was designed primarily for use on culverts, man-made channels that allow rivers and streams to pass under roads and other urban infrastructure. Numbering over one million in the UK, culverts generally have metal trash screens at their entrances to stop large debris passing through. However, if enough debris builds up, culverts can become blocked, creating a significant flood risk. 

The Bath team developed AI on the River at a culvert site in Cardiff, using machine learning to train a camera system to automatically spot potential obstructions. Described in The Journal of Flood Risk Management, the system identified likely blockages with close to 90 per cent accuracy.

“We’ve been able to develop an efficient model that can capture and identify blockages before they become a problem – it’s proactive, so doesn’t wait for a flood to happen before raising the alarm,” said Dr Andrew Barnes, a lecturer in Bath’s Department of Computer Science and a member of the Centre for Climate Adaptation & Environment Research.

“We’ve developed the system to be flexible and scalable – it could be applied almost anywhere, giving it huge potential in countries where flooding is an issue but where the resources to develop similar tools locally may be scarce.”

According to the Bath team, its machine learning process has attracted attention from flood prevention organisations in countries including South Africa, where monitoring equipment is available, but data that could be used to train an AI is scarce or not collected.

“Climate change means the risk of flooding is growing all around the world,” said Dr Thomas Kjeldsen, a reader in Bath’s Department of Architecture & Civil Engineering and a member of the Centre for Regenerative Design and Engineering for a Net Positive World (RENEW).

“This work opens the potential for the development of new, lightweight and cost-efficient flood management systems in urbanised areas, enabling authorities around the globe to adapt to the changing climate. This study is a first step toward a sustainable solution to flood forecasting.”