Trial to track damaging invasive species of plant

Artificial intelligence is being enlisted in the fight against invasive plants, as experts try to design a system that makes problem species easier to track.

Scientists from the UK Centre for Ecology and Hydrology (UKCEH) and Birmingham-based company Keen AI are developing a new AI system to quickly survey areas such as roadsides for invasive species of plant.

Plants such as Japanese knotweed can cause damage in the UK, but finding and tracking their spread can be expensive and time-consuming, the experts said.

The new scheme will use a high-speed camera on top of a vehicle to survey up to 120 miles of roadside vegetation a day.

The images will be tagged with their GPS location and uploaded on to an online platform, where UKCEH ecologists will identify the plants in the photographs.

Then the team aims to teach the AI how to correctly identify invasive species such as Japanese knotweed, rhododendrons,

Himalayan balsam and cherry laurel.

They will also teach the system to spot ash trees, which are native to the UK but at risk of a devastating disease, ash dieback.

It is hoped that once it has learned to identify certain species, the AI – which can rapidly analyse large numbers of images – will make surveying for invasive and potentiallydamaging plants quicker and cost-effective.

A 10-month pilot project, funded by government innovation agency Innovate UK, will survey roads in north Wales and Birmingham, the team said.

Dr Tom August, from UKCEH, said: “There’s a huge opportunity for AI to help us learn more about the natural world. We’re interested to see if we can develop a cost-effective, rapid way to identify UK invasive plant species.”

“There’s a huge opportunity for AI to help us learn more”

Invasive Japanese knotweed poses a risk in the UK