An artificial intelligence (AI) tool trained to differentiate between grey and red squirrels could revolutionise conservation efforts, experts suggest.

Known as Squirrel Agent, the system has been developed using thousands of squirrel images, achieving a reported 97% accuracy in distinguishing the two species.

The tool can automatically regulate access to squirrel feeders: red squirrels gain entry to feeders with food, while grey squirrels are directed to feeders containing contraceptive paste. This innovative approach aims to control grey squirrel populations while bolstering red squirrel numbers.

“It’s a real showcase of what AI can do,” said Emma McClenaghan, co-founder of Genysys Engine, which developed the tool.

“It’s working in real time to do a task that we don’t have enough [human] volunteers to do.”

Its developer, Genysys Engine, envisions broader applications for the technology, including monitoring other species requiring precise digital identification.

Ian Glendinning, from Northern Red Squirrels—a conservation group participating in the trials—emphasised the urgency of technological intervention. He said that, for the animals he is trying to protect, help from technology was urgently needed.

“We are in the bar of the last chance saloon, and the landlord has just called last orders,” he said.

Grey squirrels, introduced to the UK about 200 years ago, are a major factor in the red squirrel population’s steep decline. Their high numbers and ability to carry a virus lethal to red squirrels but harmless to themselves have contributed to this trend.

“Red squirrels are hanging on in Scotland and Ireland, and there are some island populations like Anglesey and the Isle of Wight”, explained Mr Glendinning.

“But mainland England and Wales is in dire straits, and they will become extinct if we are unable to reverse this trend.”

Adding complexity, not all red squirrels are actually red. Other distinguishing traits, such as tail shape, ear size, and weight, also help differentiate the species, even when their coloration overlaps.

Identifying these subtle differences is labor-intensive for humans, but Squirrel Agent leverages AI to rapidly analyse such markers, enabling near-instant decisions with exceptional precision. The system supports conservation by either allowing red squirrels better access to food or guiding grey squirrels toward reproductive control.

The technology’s future developments include identifying individual animals by analysing their whiskers, which are unique to each squirrel.

Emma McClenaghan of Genysys Engine explains that AI will examine the shape, base, and length of whiskers to uniquely identify and monitor specific animals.

“Whiskers are like a human fingerprints,” she says.

This capability could significantly enhance population tracking and conservation strategies.

Beyond squirrels, AI has already proven invaluable for broader wildlife conservation. For instance, the World Wildlife Fund (WWF) employed AI to analyse millions of photos from areas of Australia devastated by bushfires, locating surviving animals. Such technology accelerates data processing, enabling timely interventions.

“Over time this data will build up, allowing scientists and researchers to start tracking family lines,” she says.

AI’s versatility extends to personal use as well. Last year, a British hobbyist shared how he created the “Furbinator 3000,” an AI tool to deter foxes and badgers from fouling his garden.

The Squirrel Agent project demonstrates how AI can address complex conservation challenges efficiently and creatively. By streamlining wildlife management and offering scalable solutions, it holds promise for protecting vulnerable species and restoring ecological balance.

 

——————————————————————————

At Natural World Fund, we are passionate about rewilding the UK to stop the decline in our wildlife.

Donate now and join in the solution!