Artificial intelligence can help track down invasive plants such as Japanese knotweed before they take over verges and cause expensive damage to roads
- The UK Centre for Ecology and Hydrology and Keen AI are working on the AI
- Once trained, it will rapidly scan images of roadsides to highlight invasive plants
- This will reduce the costs of plant surveys and increase their potential scale
- Images could be captured by a camera mounted on a vehicle driving around
- A 10-month pilot project will survey roadsides in Birmingham and north Wales
Artificial intelligence may soon help track down invasive plants such as Japanese knotweed before they take over verges and cause expensive damage to roads.
The UK Centre for Ecology and Hydrology and Birmingham-based firm Keen AI are building the system to quickly survey areas like roadsides for invasive plant species.
Plants such as Japanese knotweed can be managed to minimise the damage they cause — but finding and tracking their spread is expensive and time-consuming.
Artificial intelligence may soon help track down invasive plants such as Japanese knotweed, pictured, before they take over verges and cause expensive damage to roads
The new scheme will use a high speed cameras mounted atop a vehicle to survey up to 120 miles (193 kilometres) of roadside vegetation a day.
The images will be tagged with their GPS location and uploaded onto an online platform, where ecologists will be able to identify the plants in the photographs.
However, the team aims to teach an AI how to correctly identify such invasive species 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 are at risk from ash dieback, a devastating disease.
It is hoped that once the software has learned to identify such species, its ability to rapidly analyse large numbers of images will make surveying for invasive and potentially-damaging plants both quicker and more cost-effective.
A 10-month pilot project — funded by the Government agency Innovate UK — will survey roads in Birmingham and north Wales, the team said.
‘There’s a huge opportunity for AI to help us learn more about the natural world,’ said computational ecologist Tom August of the UK Centre for Ecology and Hydrology.
‘We’re interested to see if we can develop a cost-effective, rapid way to identify invasive plant species in the UK.’
These species, he explained, ‘tend to grow in corridors — which is why we’re focused on roadside surveys.’
‘If the pilot is successful, this could be scaled up in other countries, or for other species of plants, trees or even insects and animals.’
The UK Centre for Ecology and Hydrology and Birmingham-based firm Keen AI are building the system to quickly survey areas like roadsides for invasive plant species like knotweed, pictured
Plants such as Japanese knotweed, pictured, can be managed to minimise the damage they cause — but finding and tracking their spread is expensive and time-consuming
‘Using AI to rapidly analyse vast amounts of images will mean safety and cost benefits to highways agencies, landowners and decision-makers,’ said Amjad Karim, Keen-AI founder.
‘Currently this work requires temporary closure of roads to ensure the safety of surveyors.’
According to Mr Karim, the AI setup would ‘significantly reduce’ the cost of ecological surveys while simultaneously allowing them to take place at a scale that is not currently possible.
‘If we are successful, we’ll be able to survey the entire UK very cost-effectively, giving a much better understanding of the extent of invasive species,” he added.