[Animals] How the photos of our vacations can help the conservation of animals

[#Wittels-]

A new field, called imageomics, uses artificial intelligence to extract biological information about animals directly from photos.

 

You go on vacation to Kenya, take a picture of a zebra and post it on a social network so that your friends can enjoy it and hit the 'like' button. But, beyond your own enjoyment and that of your contacts, these photos can have a benefit that you would never have imagined: helping researchers to track and collect information on endangered species.

 

Scientists are using artificial intelligence (AI) to analyze photos of zebras, sharks, and other animals to identify and track individuals. This data offers new insights into their movements as well as po[CENSORED]tion trends.

"We have millions of images of threatened and endangered animals taken by scientists, camera traps, drones, and even tourists," explains Tanya Berger-Wolf, director of the Translational Data Analytics Institute at The Ohio State University. "Those images contain a wealth of data that we can mine and analyze to help protect animals and fight extinction."

This new field called imageomics is taking the use of wildlife images a step further by using AI to extract biological information about animals directly from their photos.

 

One of the biggest challenges facing environmentalists is the lack of available data on many threatened and endangered species. In fact, of the more than 142,000 species on the IUCN Red List of Threatened Species, the status of more than half is unknown due to insufficient data or uncertain po[CENSORED]tion trends.

“We are losing biodiversity at an unprecedented rate and we don't even know how much and what we are losing. 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," says Berger-Wolf.

 

Scientists do not have enough GPS collars and satellite tags to monitor all the elephants and answer these questions. Therefore, using artificial intelligence techniques opens new effective ways to learn more about animal po[CENSORED]tions.

 

Berger-Wolf and her colleagues created a system called Wildbook that uses computer vision algorithms to analyze photos taken by vacationing tourists and researchers in the field to identify not just animal species, but individuals as well.

"Our AI algorithms can identify people wearing anything with stripes, spots, wrinkles or indentations, even the shape of a whale's caudal fin or a dolphin's dorsal fin," explains Berger-Wolf.

 

Wildbook is a kind of social network, mainly dedicated to animal life, containing more than 2 million photos of around 60,000 uniquely identified whales and dolphins around the world. But, in addition to sharks or marine mammals, there are thousands of photographs of land animals such as zebras, turtles, giraffes, African carnivores and other species.

"This is now one of the main sources of information scientists have about killer whales: it's not bad data anymore," says Berger-Wolf.

 

Berger-Wolf's team has developed an artificial intelligence agent that searches for relevant species in publicly shared social media posts. "That means many people's vacation photos of sharks they sighted in the Caribbean, for example, ended up being used in Wildbook for science and conservation," explains Berger-Wolf.

 

 

Link: https://www.lavanguardia.com/natural/20220221/8072316/fotos-animales-inteligencia-artificial-conservacion-imageomica.html#foto-1