Vacation photos of zebras and whales that tourists post on social media may have a benefit they didn’t expect: helping researchers track and gather information about endangered species.

Scientists are using artificial intelligence (AI) to analyze photos of zebras, sharks and other animals to identify and track individuals and offer new insights into their movements, as well as population trends .

“We have millions of images of endangered and threatened animals taken by scientists, camera traps, drones and even tourists,” said Tanya Berger-Loupdirector of the Translational Data Analytics Institute at Ohio State University.

“These images contain a wealth of data that we can extract and analyze to help protect animals and fight extinction.”

A new field called imageomics takes the use of wildlife images one step further by using AI to extract biological information about animals directly from their photos, said Berger-Wolf, professor of computer science and d Engineering, Electrical and Computer Engineering and Evolution, Ecology and Organismal Biology at Ohio State.

She discussed recent advances in using AI to analyze wildlife images and the foundation of imageomics in a presentation February 20 to annual meeting of the American Association for the Advancement of Science. She spoke at the scientific session “Participatory Science: Volunteers and Machine Learning Protect Nature for All.”

One of the biggest challenges facing conservationists is the lack of available data on many threatened and endangered species.

“We are losing biodiversity at an unprecedented rate and we don’t even know how much and what we are losing,” Berger-Wolf said.

Among the more than 142,000 species present on the IUCN Red List of Threatened Speciesthe status of more than half is not known because there are insufficient data or their population trend is uncertain.

“If we want to save African elephants from extinction, we need to know how many there are in the world, and where they are, and how fast they are declining,” Berger-Wolf said.

“We don’t have enough GPS collars and satellite tags to monitor all the elephants and answer these questions. But we can use AI techniques like machine learning to analyze images of elephants to provide much of the information we need.

Berger-Wolf and his colleagues created a system called wild book which uses computer vision algorithms to analyze photos taken by vacationing tourists and field researchers to identify not just animal species, but individuals.

“Our AI algorithms can identify individuals using anything that’s scratched, spotted, wrinkled or notched – even the shape of a whale’s fluke or a dolphin’s dorsal fin,” she said. .

For example, Wildbook contains over 2 million photos of approximately 60,000 uniquely identified whales and dolphins from around the world.

“It’s now one of the main sources of information scientists have about killer whales – they don’t lack data anymore,” she said.

In addition to sharks and whales, there are wildlife books for zebras, turtles, giraffes, African carnivores, and other species.

Berger-Wolf and his colleagues have developed an artificial intelligence agent that searches publicly shared social media posts for relevant species. This means vacation photos of sharks that many people have seen in the Caribbean, for example, end up being used in Wildbook for science and conservation, she said.

With information about when and where the images were taken, these photos can aid conservation by providing population counts, birth and death dynamics, species range, social interactions, and interactions with other species, including humans, she said.

This has been very helpful, but Berger-Wolf said researchers are looking to advance the field with imageomics.

“The ability to extract biological information from images is the foundation of imageomics,” she explained. “We teach machines to see things in images that humans may have missed or can’t see.”

For example, is the pattern of stripes on a zebra significantly similar to the pattern of its mother, and if so, can this give information about their genetic similarities? How do the skulls of bat species vary with environmental conditions, and what evolutionary adaptation drives this change? These questions and many more can be answered by machine learning analysis of photos.

The National Science Foundation awarded the State of Ohio $15 million in September to lead the creation of the Imageomics Institute, which will help guide scientists around the world in this new field. Berger-Wolf is the institute’s principal investigator.

As the use of AI in wildlife image analysis continues to grow, Berger-Wolf said, one of the keys will be to ensure that AI is used fairly and ethically.

On the one hand, researchers need to make sure it does no harm. For example, data must be protected so that it cannot be used by poachers to target endangered species.

But it must be more than that.

“We need to make sure it’s a human-machine partnership in which humans trust AI. AI should, by design, be participatory, connecting between people, between data and across geographic locations,” she said.