Photos of zebras and whales from vacations that tourists post on social media can bring benefits they never expected: helping researchers track and collect information on endangered species.

Scientists use artificial intelligence (AI) to analyze photographs 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 endangered and endangered images of animals taken by scientists, photo traps, drones and even tourists,” said Tanya Berger-Wolf, director of the Institute of Translational Data Analysis 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 imaging makes the use of wildlife images a step further, using artificial intelligence to extract biological information about animals directly from their photographs, said Berger-Wolf, professor of computer science and technology, electrical engineering and computer engineering and evolution. , Ecology and Biology of Organisms in Ohio.

She discussed the latest advances in the use of AI to analyze wildlife images and the establishment of imagery in a presentation February 20 at Art the annual meeting of the American Science Development Association. She spoke at a scientific session “Science with Crowdsourcing: Volunteers and Machine Learning Protect Nature for All.”

One of the biggest problems facing environmentalists is the lack of available data on many threats 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.

With more than 142 thousand species on IUCN Red List of Endangered Speciesthe status of more than half is unknown because there is not enough 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 where they are and how fast they are declining,” Berger-Wolf said.

“We don’t have enough GPS collars and satellite labels to track all the elephants and answer those questions. But we can use AI techniques like machine learning analyze images of elephants to give most of the information we need. ”

Berger-Wolf and her colleagues created a system called Wildbook which uses computer vision algorithms to analyze photographs taken by tourists on vacation, and researchers in the field to identify not only animal species but also individuals.

“Our artificial intelligence algorithms can identify people using anything striped, spotted, wrinkled or notched – even the shape of a whale’s bivalve or the dorsal fin of a dolphin,” she said.

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

“Now this is one of the main sources of information for scientists about killer whales – they no longer have enough data,” she said.

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

Berger-Wolf and her colleagues have developed an AI agent that opens up a common search social networks messages for relevant species. That means photos of many people from shark vacations they saw in the Caribbean, for example, ended up being used in the Wildbook for science and conservation, she said.

Along with information on when and where the pictures were taken, these photos can help preserve, providing population counts, birth and death dynamics, species range, social interactions and interactions with other species, including humans, she said.

It was very helpful, but Berger-Wolf said the researchers are looking to push the field forward with the help of imagery.

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

For example, is the image of the stripes on the zebra in some significant way similar to that of her mother, and if so, can this provide information about their genetic similarity? How do skulls of bat species change depending on environmental conditions and what evolutionary adaptation causes these changes? These and many other questions can be answered by analyzing photographs using machine learning.

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

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

First, researchers need to make sure it doesn’t cause harm. For example, data should be protected so that poachers cannot use it to target endangered species.

But it has to be more than simple.

“We need to make sure this is a human-machine partnership in which people trust AI. According to its plan, AI should participate, connect people, data and geographical places, ”she said.

Photos of zebras and whales from vacations that tourists post on social media can bring benefits they never expected: helping researchers track and collect information on endangered species.

Scientists use artificial intelligence (AI) to analyze photographs 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 endangered and endangered images of animals taken by scientists, photo traps, drones and even tourists,” said Tanya Berger-Wolf, director of the Institute of Translational Data Analysis 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 imaging makes the use of wildlife images a step further, using artificial intelligence to extract biological information about animals directly from their photographs, said Berger-Wolf, professor of computer science and technology, electrical engineering and computer engineering and evolution. , Ecology and Biology of Organisms in Ohio.

She discussed the latest advances in the use of AI to analyze wildlife images and the establishment of imagery in a presentation February 20 at Art the annual meeting of the American Science Development Association. She spoke at a scientific session “Science with Crowdsourcing: Volunteers and Machine Learning Protect Nature for All.”

One of the biggest problems facing environmentalists is the lack of available data on many threats 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.

With more than 142 thousand species on IUCN Red List of Endangered Speciesthe status of more than half is unknown because there is not enough 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 where they are and how fast they are declining,” Berger-Wolf said.

“We don’t have enough GPS collars and satellite labels to track all the elephants and answer those questions. But we can use AI techniques like machine learning analyze images of elephants to give most of the information we need. ”

Berger-Wolf and her colleagues created a system called Wildbook which uses computer vision algorithms to analyze photographs taken by tourists on vacation, and researchers in the field to identify not only animal species but also individuals.

“Our artificial intelligence algorithms can identify people using anything striped, spotted, wrinkled or notched – even the shape of a whale’s bivalve or the dorsal fin of a dolphin,” she said.

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

“Now this is one of the main sources of information for scientists about killer whales – they no longer have enough data,” she said.

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

Berger-Wolf and her colleagues have developed an AI agent that opens up a common search social networks messages for relevant species. That means photos of many people from shark vacations they saw in the Caribbean, for example, ended up being used in the Wildbook for science and conservation, she said.

Along with information on when and where the pictures were taken, these photos can help preserve, providing population counts, birth and death dynamics, species range, social interactions and interactions with other species, including humans, she said.

It was very helpful, but Berger-Wolf said the researchers are looking to push the field forward with the help of imagery.

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

For example, is the image of the stripes on the zebra in some significant way similar to that of her mother, and if so, can this provide information about their genetic similarity? How do skulls of bat species change depending on environmental conditions and what evolutionary adaptation causes these changes? These and many other questions can be answered by analyzing photographs using machine learning.

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

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

First, researchers need to make sure it doesn’t cause harm. For example, data should be protected so that poachers cannot use it to target endangered species.

But it has to be more than simple.

“We need to make sure this is a human-machine partnership in which people trust AI. According to its plan, AI should participate, connect people, data and geographical places, ”she said.