An artificial intelligence (AI) tool that was trained to tell the difference between gray and red squirrels could be a “complete game changer”, conservationists say.

The system, called Squirrel Agent, was trained on thousands of images of animals, allowing it to distinguish them with 97% accuracy, its developer claims.

It can then be used to automatically control access to squirrel feeders – only reds allowed in those containing food, and only grays in those where the food has been replaced with contraceptive paste.

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

“It’s about working in real time to accomplish a task for which we don’t have enough (human) volunteers.”

Squirrel Agent is currently being trialled at sites across the UK in collaboration with five wildlife charities.

Genysys Engine hopes it will eventually be used much more widely, not only with squirrels, but also with other species that would benefit from sophisticated digital monitoring.

Ian Glendinning, of Northern Red Squirrels – one of the conservation groups involved in the trial – told the BBC that, for the animals he is trying to protect, help from technology was urgently needed.

“We’re at the Last Chance Lounge bar, and the owner just called in last orders,” he said.

Gray squirrels are largely responsible for the sharp decline in red squirrel numbers.

This is partly due to their large numbers, but also because they can carry a virus to which they are immune, but which is fatal to red squirrels. They arrived in the UK around 200 years ago.

“Red squirrels persist in Scotland and Ireland, and there are some island populations such as Anglesey and the Isle of Wight,” Mr Glendinning said.

“But mainland England and Wales are in dire straits, and they will disappear if we fail to reverse this trend.”

Efforts to preserve red squirrels are further complicated by the fact that, despite their name, not all red squirrels are red.

There are other markers, including their tail, ears, size and weight, that can also distinguish them from gray squirrels – the largely dominant population – even if they are the same color.

The detection process is time-consuming for human observers, but Squirrel Agent uses the power of AI to quickly analyze all of these markers and decide with an extremely high level of accuracy which is which.

It can then automatically decide whether to increase their chances of survival by allowing them to eat more or reduce their chances of reproducing by directing them to contraceptives.

Genysys Engine says the next step in the technology’s evolution is to go beyond simply distinguishing between types of squirrels and identify individual animals.

This will be done, explains Emma McClenaghan, by focusing on their whiskers, which are unique to each animal.

“Whiskers are like human fingerprints,” she says.

By distinguishing the tips of each creature’s whiskers, as well as their base and length, she hopes AI will allow wildlife experts to track and monitor individual members of the population.

“Over time, this data will accumulate, allowing scientists and researchers to begin tracking family lineages,” she says.

There are already other examples of AI’s ability to process huge amounts of data very quickly, useful to conservationists.

For example, the World Wide Fund for Nature (WWF) has used this technology to analyze millions of photographs of a large part of Australia destroyed by bushfires, in order to find the places where animals had survived.

It has also been taken up by amateurs, with a Briton telling BBC News last year how he had designed a tool – called Furbinator 3000 – to stop foxes and badgers from messing up your Surrey garden.