To Save Endangered Species, Scientists Point Stargazing Software Back to Earth

Attendees at the European Week of Astronomy and Space Science (EWASS), hosted in Liverpool, UK from April 3 to 6, had the chance to hear a surprising presentation.

Dr. Claire Burke, an astrophysicist at Liverpool John Moores University (LJMU), explained how software used to identify galaxies is being used closer to Earth—to resolve problems involved with the tracking of endangered species.

“With thermal infrared cameras, we can easily see animals as a result of their body heat, day or night, and even when they are camouflaged in their natural environment,” Burke explained in an LJMU press release.

“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.

The project uses machine-learning algorithms developed for astronomy to train software to recognize different animals in varying landscapes based on infrared images. It is an important technique because it can identify animals at night, when most poaching occurs.

The story of how the system developed, as reported by BBC News April 3, is almost as fascinating as the technology itself.

LJMU conservationist Serge Wich developed a system to track endangered animals using infrared cameras mounted on drones. Monitoring the populations of endangered species has traditionally been done by physically counting animals or the signs they left behind, but such methods are time-consuming and inaccurate, since scientists can’t always follow where different populations move.

Wich’s tests with drones at Chester Zoo and Knowsley Safari Park showed promise. Wich could detect the animals’ presence, but he couldn’t always tell which animal was which.

He lamented his problem to his neighbor in a conversation over a shared fence. Fortunately, his neighbor was Dr. Steve Longmore, an astronomer also working at LJMU, who told him about Burke’s work identifying galaxies from the patterns of light they emitted.

“I collaborated with quite a few people during my career but astrophysicists were not on my list of potential collaborators,” Wich told BBC News.

“But here we are. It shows how the serendipity of how science works.”

LJMU reported that the team tested the software in the field in September 2017 by tracking Riverine rabbits, one of the most endangered mammals in the world. They sighted five of the highly elusive creatures.

“Given that there have only been about 1,000 sightings of Riverine rabbits by anyone in total, it was a real success,” Burke said in the LJMU release.

Their next tests will involve tracking orangutans in Malaysia and spider monkeys in Mexico in May and monitoring Brazilian river dolphins in June, LJMU reported.

Longmore explained to BBC News why the new technique is such a breakthrough for protecting vulnerable species.

“Conservation is not only about the numbers of animals but also about political will and local community supporting conservation. But better data always helps to move good arguments forward. Solid data on what is happening to animal populations is the foundation of all conservation efforts,” he said.