Vacation Photos Of Zebras & Whales Captured By Tourists Can Combat Extinction Of Endangered Animals: Researchers

Vacation photographs of zebras and whales posted by tourists on social media can have unexpected benefits, researchers have found.

New Delhi: Vacation photographs of zebras and whales posted by tourists on social media can have unexpected benefits. The pictures can help researchers track and gather information on endangered species, researchers have found.

Scientists from The Ohio State University in the United States are using artificial intelligence (AI) to analyse photos of zebras, sharks and other animals to identify and track individuals. The photos offer new insights into the movements of the animals, as well as population trends, according to a statement issued by The Ohio State University. 

Tanya Berger-Wolf, director of the Translational Data Analytics Institute at The Ohio State University, said in the statement that there are millions of images of endangered and threatened animals taken by scientists, camera traps, drones, and even tourists. Berger-Wolf said that those images contain a wealth of data that one can extract and analyse to help protect animals and combat extinction. 

Using ‘Imageomics’ To Extract Biological Information On Animals

Researchers are using a new field called imageomics to extract biological information on animals directly from their pictures. Berger-Wolf said that imageomics is taking the use of wildlife images a step further by using AI for this purpose. 

The researcher discussed recent advances in using AI to analyse wildlife images and the founding of imageomics in a presentation on February 20, at the annual meeting of the American Association for the Advancement of Science, the statement said.

The lack of data available on many threatened and endangered species is one of the biggest challenges that environmentalists face. Berger-Wolf said that the world is losing biodiversity at an unprecedented rate, and "we don't even know how much and what we're losing".

As many as 1,42,000 species are named on the International Union for Conservation of Nature (IUCN) Red List of Threatened Species. The status of more than half of these species are not known because there is not enough data, or their population trend is uncertain. 

According to Berger-Wolf, people must know how many African elephants there are in the world, and where they are, and how fast they are declining, in order to save the animals from extinction.

She said that there are not enough GPS collars and satellite tags to monitor all the elephants and answer those questions. She proposed the use of AI techniques such as machine learning to analyse images of elephants to provide much of the information needed. 

A System Called ‘Wildbook’

The statement said that Berger-Wolf and her colleagues created a system called Wildbook, which uses computer vision algorithms to analyse photos taken by tourists on vacation and researchers in the field to identify not only species of animals, but individuals. 

She said that the researchers' AI algorithms can identify individuals using anything striped, spotted, wrinkled or notched. The algorithms can even identify the shape of a whale's fluke or the dorsal fin of a dolphin, she said.

Wildbook contains over 2 million pictures of about 60,000 uniquely identified whales and dolphins from around the world, the statement said.

Berger-Wolf said that this is now one of the primary sources of information scientists have on killer whales. She said that they are "data deficient no longer".

Apart from sharks and whales, there are ‘wildbooks’ for zebras, turtles, giraffes, African carnivores, and other species.

How The AI Helps In Conservation

The researchers have developed an AI agent which searches publicly shared social media posts for relevant species, the statement said. Berger-Wolf said this implies that many vacation pictures of sharks captured by tourists end up being used in Wildbook for science and conservation. 

The pictures, together with information about when and where they were taken, can aid in conservation. Berger-Wolf said that the photos do so by providing population counts, birth and death dynamics, species range, social interactions and interactions with other species, including humans.

Though this has been useful, researchers are looking to move the field forward with imageomics, Berger-Wolf said. 

She explained that the ability to extract biological information from images is the foundation of imageomics. "We're teaching machines to see things in images that humans may have missed or can't see," she further said.

A question arises whether the pattern of stripes on a zebra are similar in some meaningful way to its mother's pattern, according to the statement. Also, if the pattern of stripes on the zebra is similar in some meaningful way to its mother's pattern, can it provide information about their genetic similarities? 

Other questions include how the skulls of bat species vary with environmental conditions, and what evolutionary adaptation drives that change. 

The statement said that these and many other questions may be answered by machine learning analysis of photos. 

Why AI Should Be Used Ethically

Berger-Wolf said that one must make sure the AI is used equitably and ethically, according to the statement. 

Researchers must make sure that the AI does no harm. For instance, data must be protected so that it cannot be used by poachers to target endangered species, the statement said.

Berger-Wolf said one must ensure that it is a human-machine partnership in which humans trust the AI, according to the statement.

She explained that the AI should, by design, be participatory, connecting among the people, among the data, and among the geographical locations.