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.