Scientists Repurpose Stargazing Tools to Protect Endangered Species

An infrared image of elephants captured as part of a collaboration between astrophysicists and ecologists at Liverpool John Moores University. (Photo: Endangered Wildlife Trust/LJMU)

In an effort to curb the rate of poaching and protect endangered species, conservationists are utilizing technology previously created to discover stars and galaxies.

The unusual collaboration, between ecologists at Liverpool John Moores University (LJMU) and the Royal Astronomical Society, came about from a problem created by new technology. Serge Wich, a conservationist at LJMU, was finding great success at counting endangered species in the wild using an infrared camera mounted to a drone. The process, however, was both time consuming and occasionally perplexing. Because of the distance of the drone from its subjects, it wasn't always easy to determine the species of animal based on the heat signature Wich and his team were looking at.

The serendipitous solution occurred while Wich was casually chatting over a fence with his neighbor, Dr. Steve Longmore, an astronomer also at LJMU. Longmore said he knew of a software app used by astrophysicists that could identify the size and age of stars and galaxies based on their heat signatures. Utilizing machine-learning algorithms, the technology could in essence also be applied to identify the heat signatures of various species in the wild.

Claire Burke, an astrophysicist at LJMU who ended up leading the project, says the application of the star-hunting tech has so far paid off big for conservation.

"Since animals and humans in thermal footage 'glow' in the same way as stars and galaxies in space, we have been able to combine the technical expertise of astronomers with the conservation knowledge of ecologists to develop a system to find the animals or poachers automatically," she said in a statement.

Looking at animal health

In addition to species identification, the software can also provide an overview of health. Speaking with the BBC, Burke said that diseased or injured animals give off a different heat profile than their healthy counterparts.

"The real advantage this gives you is that if you know how many animals you have and where they are and what kind of health they are in, then you can you can formulate a good conservation strategy for looking after them," she said.

To train the software on a wide variety of heat signatures from different species, the team of researchers spent time collecting infrared imagery of animals at Knowsley Safari and Chester Zoo in England. Their first field trial in South Africa to detect Riverine rabbits, one of the most endangered mammals in the world (with only 500 living adults left in the wild), was a complete success.

"The rabbits are very small, so we flew the drone quite low to the ground at a height of 20 meters (65 feet). Although this limited the area we could cover with the drone, we managed five sightings," said Burke. "Given that there have only been about 1,000 sightings of Riverine rabbits by anyone in total, it was a real success."

With their proof of concept complete, the team is now refining the software to account for vegetation that blocks body heat, as well as other factors such as high humidity and extremely warm ground temperatures. Once these issues are further ironed out, Burke believes the system will immediately prove to be yet another high-tech tool at the disposal of conservationists.

"Our aim is to make a system that is easy for conservationists and game wardens to use anywhere in the world, which will allow endangered animals to be tracked, found and monitored easily and poaching to be stopped before it happens," she said.