Researchers at the University of Bath have developed an AI enabled detection software to spot blockages in urban waterways.
Named AI on The River, it can be integrated into existing CCTV systems to detect natural debris, litter or waste blocking trash screens mounted in culverts, and provide an early warning of likely flooding.
Culverts, which number over one million in the UK, allow streams and rivers to flow under roads, railway embankments and housing developments. Trash screens, usually a set of bars, are mounted at culvert entrances to stop debris from passing through.
The university team used machine learning to train a camera system at a culvert site in Cardiff to automatically spot potential obstructions, and have reported that it has been able to identify likely blockages with close to 90% accuracy.
They said that using AI and machine learning to create early warning systems would allow local authorities in charge of keeping waterways flowing to focus resources where they are needed and respond to potential blockages quickly and in a focused way.
In most case, culverts are monitored manually over CCTV by council staff watching a bank of screens.
Safety benefits
The team added that the proactive nature of the system also offers major safety benefits to response teams, as they can attend sites immediately rather than having to work in dangerous flooded conditions.
Dr Andrew Barnes, a lecturer in the university’s Department of Computer Science and member of the Centre for Climate Adaptation and Environment Research, said: “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.
“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.”
A paper on the project has been published in The Journal of Flood Risk Management.
The research was supported by a grant from the Engineering and Physical Sciences Research Council under the Reclaiming Forgotten Cities programme.
