AI helps tell snow leopards apart, improving population counts for these majestic mountain predators
Snow leopards are known as the 'ghosts of the mountains' for a reason. Imagine waiting for months in the harsh, rugged mountains of Asia, hoping to catch even a glimpse of one. These elusive big cats move silently across rocky slopes, their pale coats blending so seamlessly with snow and stone that even the most seasoned biologists seldom spot them in the wild.
Travel writer Peter Matthiessen spent two months in 1973 searching the Tibetan plateau for them and wrote a 300-page book about the effort. He never saw one. Forty years later, Peter's son Alex retraced his father's steps – and didn't see one either.
Researchers have struggled to come up with a figure for the global population. In 2017, the International Union for Conservation of Nature reclassified the snow leopard from endangered to vulnerable, citing estimates of between 2,500 and 10,000 adults in the wild. However, the group also warned that numbers continue to decline in many areas due to habitat loss, poaching and human-wildlife conflict. Those who study these animals want to help protect the species and their habitat – if only we can determine exactly where they live and how many there are.
Traditional tracking methods – searching for footprints, droppings and other signs – have their limits. Instead of waiting for a lucky face-to-face encounter, conservationists from the Wildlife Conservation Society, led by experts including Stéphane Ostrowski and Sorosh Poya Faryabi, began deploying automated camera traps in Afghanistan. These devices snap photos whenever movement is detected, capturing thousands of images over months, all in hopes of obtaining a rare glimpse of a snow leopard.
But capturing images is only half the battle. The next, even harder task is telling one snow leopard apart from another.
At first glance, it might sound simple: Each snow leopard has a unique pattern of black rosettes on its coat, like a fingerprint or a face in a crowd. Yet in practice, identifying individuals by these patterns is slow, subjective and prone to error. Photos may be taken at odd angles, under poor lighting, or with parts of the animal obscured – making matches tricky.
A common mistake happens when photos from different cameras are marked as depicting different animals when they actually show the same individual, inflating population estimates. Worse, camera trap images can get mixed up or misfiled, splitting encounters of one cat across multiple batches and identities.
I am a data analyst working with Wildlife Conservation Society and other partners at Wild Me. My work and others' has found that even trained experts can misidentify animals, failing to recognize repeat visitors at locations monitored by motion-sensing cameras and counting the same animal more than once. One study found that the snow leopard population was overestimated by more than 30% because of these human errors.
To avoid these pitfalls, researchers follow camera sorting guidelines: At least three clear pattern differences or similarities must be confirmed between two images to declare them the same or different cats. Images too blurry, too dark or taken from difficult angles may have to be discarded. Identification efforts range from easy cases with clear, full-body shots to ambiguous ones needing collaboration and debate. Despite these efforts, variability remains, and more experienced observers tend to be more accurate.
Now people trying to count snow leopards are getting help from artificial intelligence systems, in two ways.
Modern AI tools are revolutionizing how we process these large photo libraries. First, AI can rapidly sort through thousands of images, flagging those that contain snow leopards and ignoring irrelevant ones such as those that depict blue sheep, gray-and-white mountain terrain, or shadows.
AI can identify individual snow leopards by analyzing their unique rosette patterns, even when poses or lighting vary. Each snow leopard encounter is compared with a catalog of previously identified photos and assigned a known ID if there is a match, or entered as a new individual if not.
In a recent study, several colleagues and I evaluated two AI algorithms, both separately and in tandem.
The first algorithm, called HotSpotter, identifies individual snow leopards by comparing key visual features such as coat patterns, highlighting distinctive 'hot spots' with a yellow marker.
The second is a newer method called pose invariant embeddings, which operates similar to facial recognition technology: It recognizes layers of abstract features in the data, identifying the same animal regardless of how it is positioned in the photo or what kind of lighting there may be.
We trained these systems using a curated dataset of photos of snow leopards from zoos in the U.S., Europe and Tajikistan, and with images from the wild, including in Afghanistan.
Alone, each model worked about 74% of the time, correctly identifying the cat from a large photo library. But when combined, the two systems together were correct 85% of the time.
These algorithms were integrated into Wildbook, an open-source, web-based software platform developed by the nonprofit organization Wild Me and now adopted by ConservationX. We deployed the combined system on a free website, Whiskerbook.org, where researchers can upload images, seek matches using the algorithms, and confirm those matches with side-by-side comparisons. This site is among a growing family of AI-powered wildlife platforms that are helping conservation biologists work more efficiently and more effectively at protecting species and their habitats.
These AI systems aren't error-proof. AI quickly narrows down candidates and flags likely matches, but expert validation ensures accuracy, especially with tricky or ambiguous photos.
Another study we conducted pitted AI-assisted groups of experts and novices against each other. Each was given a set of three to 10 images of 34 known captive snow leopards and asked to use the Whiskerbook platform to identify them. They were also asked to estimate how many individual animals were in the set of photos.
The experts accurately matched about 90% of the images and delivered population estimates within about 3% of the true number. In contrast, the novices identified only 73% of the cats and underestimated the total number, sometimes by 25% or more, incorrectly merging two individuals into one.
Both sets of results were better than when experts or novices did not use any software.
The takeaway is clear: Human expertise remains important, and combining it with AI support leads to the most accurate results. My colleagues and I hope that by using tools like Whiskerbook and the AI systems embedded in them, researchers will be able to more quickly and more confidently study these elusive animals.
With AI tools like Whiskerbook illuminating the mysteries of these mountain ghosts, we have another way to safeguard snow leopards – but success depends on continued commitment to protecting their fragile mountain homes.
This article is republished from The Conversation, a nonprofit, independent news organization bringing you facts and trustworthy analysis to help you make sense of our complex world. It was written by: Eve Bohnett, University of Florida
Read more:
In protecting land for wildlife, size matters – here's what it takes to conserve very large areas
Grizzly bear conservation is as much about human relationships as it is the animals
I run 'facial recognition' on buildings to unlock architectural secrets
Eve Bohnett receives funding from San Diego State Research Foundation and Wildlife Conservation Society. She is affiliated with University of Florida.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Yahoo
2 days ago
- Yahoo
AI helps tell snow leopards apart, improving population counts for these majestic mountain predators
Snow leopards are known as the 'ghosts of the mountains' for a reason. Imagine waiting for months in the harsh, rugged mountains of Asia, hoping to catch even a glimpse of one. These elusive big cats move silently across rocky slopes, their pale coats blending so seamlessly with snow and stone that even the most seasoned biologists seldom spot them in the wild. Travel writer Peter Matthiessen spent two months in 1973 searching the Tibetan plateau for them and wrote a 300-page book about the effort. He never saw one. Forty years later, Peter's son Alex retraced his father's steps – and didn't see one either. Researchers have struggled to come up with a figure for the global population. In 2017, the International Union for Conservation of Nature reclassified the snow leopard from endangered to vulnerable, citing estimates of between 2,500 and 10,000 adults in the wild. However, the group also warned that numbers continue to decline in many areas due to habitat loss, poaching and human-wildlife conflict. Those who study these animals want to help protect the species and their habitat – if only we can determine exactly where they live and how many there are. Traditional tracking methods – searching for footprints, droppings and other signs – have their limits. Instead of waiting for a lucky face-to-face encounter, conservationists from the Wildlife Conservation Society, led by experts including Stéphane Ostrowski and Sorosh Poya Faryabi, began deploying automated camera traps in Afghanistan. These devices snap photos whenever movement is detected, capturing thousands of images over months, all in hopes of obtaining a rare glimpse of a snow leopard. But capturing images is only half the battle. The next, even harder task is telling one snow leopard apart from another. At first glance, it might sound simple: Each snow leopard has a unique pattern of black rosettes on its coat, like a fingerprint or a face in a crowd. Yet in practice, identifying individuals by these patterns is slow, subjective and prone to error. Photos may be taken at odd angles, under poor lighting, or with parts of the animal obscured – making matches tricky. A common mistake happens when photos from different cameras are marked as depicting different animals when they actually show the same individual, inflating population estimates. Worse, camera trap images can get mixed up or misfiled, splitting encounters of one cat across multiple batches and identities. I am a data analyst working with Wildlife Conservation Society and other partners at Wild Me. My work and others' has found that even trained experts can misidentify animals, failing to recognize repeat visitors at locations monitored by motion-sensing cameras and counting the same animal more than once. One study found that the snow leopard population was overestimated by more than 30% because of these human errors. To avoid these pitfalls, researchers follow camera sorting guidelines: At least three clear pattern differences or similarities must be confirmed between two images to declare them the same or different cats. Images too blurry, too dark or taken from difficult angles may have to be discarded. Identification efforts range from easy cases with clear, full-body shots to ambiguous ones needing collaboration and debate. Despite these efforts, variability remains, and more experienced observers tend to be more accurate. Now people trying to count snow leopards are getting help from artificial intelligence systems, in two ways. Modern AI tools are revolutionizing how we process these large photo libraries. First, AI can rapidly sort through thousands of images, flagging those that contain snow leopards and ignoring irrelevant ones such as those that depict blue sheep, gray-and-white mountain terrain, or shadows. AI can identify individual snow leopards by analyzing their unique rosette patterns, even when poses or lighting vary. Each snow leopard encounter is compared with a catalog of previously identified photos and assigned a known ID if there is a match, or entered as a new individual if not. In a recent study, several colleagues and I evaluated two AI algorithms, both separately and in tandem. The first algorithm, called HotSpotter, identifies individual snow leopards by comparing key visual features such as coat patterns, highlighting distinctive 'hot spots' with a yellow marker. The second is a newer method called pose invariant embeddings, which operates similar to facial recognition technology: It recognizes layers of abstract features in the data, identifying the same animal regardless of how it is positioned in the photo or what kind of lighting there may be. We trained these systems using a curated dataset of photos of snow leopards from zoos in the U.S., Europe and Tajikistan, and with images from the wild, including in Afghanistan. Alone, each model worked about 74% of the time, correctly identifying the cat from a large photo library. But when combined, the two systems together were correct 85% of the time. These algorithms were integrated into Wildbook, an open-source, web-based software platform developed by the nonprofit organization Wild Me and now adopted by ConservationX. We deployed the combined system on a free website, where researchers can upload images, seek matches using the algorithms, and confirm those matches with side-by-side comparisons. This site is among a growing family of AI-powered wildlife platforms that are helping conservation biologists work more efficiently and more effectively at protecting species and their habitats. These AI systems aren't error-proof. AI quickly narrows down candidates and flags likely matches, but expert validation ensures accuracy, especially with tricky or ambiguous photos. Another study we conducted pitted AI-assisted groups of experts and novices against each other. Each was given a set of three to 10 images of 34 known captive snow leopards and asked to use the Whiskerbook platform to identify them. They were also asked to estimate how many individual animals were in the set of photos. The experts accurately matched about 90% of the images and delivered population estimates within about 3% of the true number. In contrast, the novices identified only 73% of the cats and underestimated the total number, sometimes by 25% or more, incorrectly merging two individuals into one. Both sets of results were better than when experts or novices did not use any software. The takeaway is clear: Human expertise remains important, and combining it with AI support leads to the most accurate results. My colleagues and I hope that by using tools like Whiskerbook and the AI systems embedded in them, researchers will be able to more quickly and more confidently study these elusive animals. With AI tools like Whiskerbook illuminating the mysteries of these mountain ghosts, we have another way to safeguard snow leopards – but success depends on continued commitment to protecting their fragile mountain homes. This article is republished from The Conversation, a nonprofit, independent news organization bringing you facts and trustworthy analysis to help you make sense of our complex world. It was written by: Eve Bohnett, University of Florida Read more: In protecting land for wildlife, size matters – here's what it takes to conserve very large areas Grizzly bear conservation is as much about human relationships as it is the animals I run 'facial recognition' on buildings to unlock architectural secrets Eve Bohnett receives funding from San Diego State Research Foundation and Wildlife Conservation Society. She is affiliated with University of Florida.
Miami Herald
4 days ago
- Miami Herald
Creature with ‘horned' eyelids discovered on China mountain. It's a new species
Researchers on an expedition to survey amphibians in southern China encountered several unfamiliar frogs with 'horned' eyelids on a mountain peak. Five males and three females were collected for analysis and later revealed to be members of a new species, according to a study published June 13 in the peer-reviewed journal Herpetozoa. Boulenophrys yezhongensis, also called the Yezhong horned toad, was discovered in Yezhong Nature Reserve and can only be found on 'a single peak within the Wumeng Mountain Range,' according to researchers. The new species is described as having a 'shield-like' snout that sticks out beyond its lower jaw, 'horn-like' growths on the upper eyelids, slender limbs, rough wart-covered skin and 'copper-brown' irises, according to the study. The existence of the Yezhong horned toad is likely the result of isolation-driven speciation, according to the study. This process can happen when members of one species are geographically separated and isolated from the rest of the group and develop into a new species. The Yezhong horned toad is separated from the nearest related populations by just over 7 miles of 'valleys crossed by the deeply incised Beipan River,' researchers said. No populations of the new species were found in 'adjacent low-elevation regions,' researchers said. According to the study, the Yezhong horned toad lives roughly 2,600 feet higher in elevation than the nearest related species. This elevation difference also brings an average temperature difference of about 40 degrees. The Yezhong horned toad has adapted to survive at high elevations in a narrow range of cold temperatures, which researchers said is an 'extinction risk' in tropical mountain ecosystems that may be impacted by climate change. Researchers recommended the new species be listed as vulnerable on the International Union for Conservation of Nature's Red List considering its extremely limited distribution and single known location. Yezhong Nature Reserve is in Shuicheng County in China's Guizhou Province. The research team included Jing Liu, Chao-Bo Feng, Tuo Shen, Shi-Ze Li, Yanlin Cheng, Gang Wei, Bin Wang and Haijun Su.
Yahoo
4 days ago
- Yahoo
High IQ people may think something is wrong with them
Teachers gave special attention to the intellectually gifted Mel Jäger ever since the first grade - without making the young student "stand out." "There was no outing: the IQ test didn't change anything in my life," says Jäger, now 34, and a board member of the German chapter of the Mensa association for the highly gifted. To be accepted to the group you need an IQ of at least 130. However not every Mensa member gets such good support. Quite a few feel held back or that they rub people the wrong way, and have been bullied. Sometimes those with a high IQ think they are the problem, Mensa members said in a meeting of the group in Mainz in western Germany. Some only come to realize during psychotherapy that their problems are related to their giftedness. Mensa has many gifted people recognized later in life "All my life I thought I had a screw loose," says an engineer from the Ruhr area, who wants to remain anonymous except for his first name, Peter. After taking the IQ test at the age of 54, he only then understood "why I was always an intellectual outsider and lonely." At work, he usually had to take a back seat. "I did everything on the side to get ahead. That was 30 years of hard work," says Peter, 59. "Late bloomers make up a huge part of our community," says Sybille Beyer, spokeswoman for Mensa Germany. That feeling of relief after finding out they have a high IQ happens often, she says. It's the feeling that "I'm not wrong, I'm just different." She says it's similar to Hans Christian Andersen's fairy tale of the ugly duckling that wanders around, feeling like he doesn't fit in - until he stumbles upon a flock of swans and realizes he's not a duck but a beautiful swan. Beyer, 61, knows what they are talking about. In primary school, she taught herself to read, was top of the class for years, but was held back. "Nah, I'm not taking you on now, you always know everything anyway," she says, describing her experience with teachers. Later, she often had the feeling that, as a person, she was "always running into a brick wall." A book about highly gifted people that she got from her hairdresser was the turning point for Beyer. She was already 53 years old at the time. "As I read, I thought, someone is writing about my life," she says. And her relief: "You can throw off all the guilt about not being able to fit in." Expert: Highly intelligent people on average more satisfied "On average, highly intelligent people get through school, college and training better, are more successful in their careers, and are healthier and happier in life than non-highly gifted people," says Detlef H Rost, an emeritus psychology professor at the University of Marburg. "So giftedness is more of a protective factor than a risk factor for development and coping with life," he says. "It is not giftedness itself that leads to problems for a person, but the behaviour displayed" – and that of their important caregivers, Rost says. Good standardized tests are "very meaningful" in Rost's view. They are even among the best diagnostic tools in psychology. Highly gifted people have an IQ of at least 130 Of the roughly 70 million adults living in Germany, around 1.4 million are highly gifted, says Rost. According to its own figures, the Mensa association, founded in 1979, now has more than 18,000 members, making it the largest network for highly intelligent people in Germany. That means the vast majority are not organized in an association. "Here you can develop acquaintances you can work with immediately - within five minutes or after two sentences," says Peter from the Ruhr area. The realization that she is highly gifted has changed her private life, reports Beyer. Mensa helped her find her way out of loneliness. The average age of Mensa members in Germany is around 38, says Jäger, who prefers plural pronouns. Around two-thirds are men and one-third women, with the proportion of diverse people growing. The professional field is diverse, and the number of members is increasing significantly, partly because autism and ADHD are being tested more frequently and the IQ is often determined from those tests, says Jäger. "You meet interesting people here and learn unexpected things that you would never come across otherwise," says Annette, 54, who does not want to give her last name. She's learned about tax returns, elementary physics, archaeology and artificialintelligence from the group, she says. "You get very interesting ideas here," says another Mensa member named Peter, from Cologne, talking about a 62-kilometre route in Nepal to Mount Everest Basecamp. The computer scientist is now studying physics so that he won't get bored after retirement. There are many facets to giftedness, says Beyer. The Mensa association's activities are therefore very diverse. Both the regulars' tables and the German meetings, such as the one in Mainz, welcome non-members. "It's not as if you're a completely different person with an IQ of 130 or more." Global links too Mensa members say a few preferences and behaviours are often found among the highly gifted: fast speech, an aversion to "meaningless small talk" but a tendency to jump quickly from topic to topic in conversations – and a penchant for tricky games. "Loud noises, harsh light, too many people, a mad rush – that's something that many of us find very difficult to take," reports Beyer. And younger people in particular usually seek contact with older people. Annette, a pharmacist, has daughters who are also highly gifted. She can't say whether this makes family life easier. "At any rate, we've put up a 'nerd sanctuary' sign at home." "Mensa is my chosen family," says Jäger from Münster. "You come into contact with people you wouldn't otherwise have known." This applies worldwide, as the umbrella organization has 150,000 members. "With the Couchsurfing programme, for example, you can find a place to stay anywhere at any time," says Jäger. They have already planned their entire holiday with Mensa members from around the world.
