Latest news with #CaTRAT
New Indian Express
4 days ago
- Science
- New Indian Express
Code Green
It was burning bright. For three months, a four-year-old tiger roamed across 12 villages in Lucknow's Rehmankheda area, killing 25 animals and keeping residents on edge in the forest of the night. Daily life slowed as people stayed indoors, wary of the elusive predator that was a ghost with stripes. To track it down, forest officials took a blended approach—mixing traditional tracking methods with modern technology. They installed AI-powered thermal cameras at five key points and deployed three thermal drones to scan the forest canopy. On the ground, trained elephants Diana and Sulochana moved through dense undergrowth where vehicles couldn't go. Meanwhile, a wildlife expert in Bengaluru monitored live camera feeds, studying the tiger's patterns to anticipate its movements. In March, came the breakthrough. AI cameras captured the tiger returning to a fresh kill. A ranger team was dispatched. A tranquiliser dart was fired, but the tiger fled, covering 500 metres before disappearing into thick foliage. Drones followed it from above, helping rangers close in for a second shot. Within 15 minutes, the animal was safely sedated. The 230 kg beast was then caged and transported to the Bakshi Ka Talab range office. The entire operation ended without a single human injury, thanks to the combined effort of AI surveillance, aerial tracking, and coordinated fieldwork. In the past, conserving wildlife in India often meant navigating dense jungles with binoculars, spending months waiting for elusive animals to appear, or diving into the sea with nothing more than a net. Today, conservationists are adding something new to their toolkit: algorithms, thermal cameras, drones, and even genetic samplers. From the cold, high-altitude deserts of Ladakh to the lush mangroves of the Sundarbans, across coral reefs, tiger corridors, and railway tracks, a quiet revolution is unfolding. Technology is changing not only how we protect wildlife, but how we understand it. In Ladakh, where the air is thin and snow leopards are more myth than mammal to most, a team of researchers set out to count the uncountable. 'Tough terrain and a lack of transport facilities were major challenges,' recalls Pankaj Raina from the Department of Wildlife Protection, Leh. 'We carried rations and equipment on ponies and set up temporary camps at subzero temperatures. Some places can only be accessed in winter, when the streams freeze. So, we'd place cameras one winter and return the next to collect them.' Over two years, they trekked more than 6,000 km and installed 956 camera traps across India's largest snow leopard habitat. But their real challenge began only after they returned with nearly half a million images. No human team could sort through that volume of footage manually. So they turned to AI. A system called CaTRAT, trained to recognise Himalayan wildlife, scanned each frame to identify species. But something more precise was required. A second programme was deployed, this one trained to analyse forehead patterns, which are more reliable. 'Only the clearest image from each sequence was used,' explains Raina. 'These were digitised and processed through AI software that scored pattern similarities, creating a photographic library of each individual snow leopard.' The study, published in PLOS One earlier this year, revealed a hopeful truth: snow leopards in Ladakh are thriving. And for the first time, India now has a national photo library of snow leopards—a visual archive that will enable researchers to monitor individual animals. Far to the south, in the forested corridor between Walayar and Madukkarai in Tamil Nadu, a different crisis was unfolding. Since 2008, 11 elephants had died in train collisions along a single seven-km-stretch of track. In 2024, the Coimbatore Forest Division responded by installing an AI-powered thermal surveillance system. The setup involved cameras that detect heat signatures in real-time, capable of spotting large mammals even in pitch darkness or heavy rain. The moment an elephant is detected near the tracks, the system sends instant alerts to train operators and forest teams. In its very first year, the system generated over 5,000 alerts, enabled 2,500 safe elephant crossings—and recorded zero elephant deaths. Technology is also transforming how humans coexist with big cats. In Maharashtra's Tadoba-Andhari Tiger Reserve, AI-enabled cameras were installed on the edges of 13 villages starting in 2023. These motion-sensitive devices don't just record tiger activity—they analyse it, sending real-time alerts to villagers when tigers are nearby. The system has worked so well that it caught the attention of Prime Minister Modi, who mentioned the effort during the 110th episode of Mann Ki Baat.
Scroll.in
14-07-2025
- Science
- Scroll.in
Snow leopards thriving in Ladakh Himalayan ranges, but challenges loom
High up in the remote, rugged mountains of the Himalayas, a phantom predator prowls – rarely seen, silently surviving. The snow leopard, one of the world's most elusive big cats, is famously hard to track. Until now, most knowledge about these 'ghosts of the mountains' has come from fragmented surveys, anecdotal sightings, and sparse camera trap footage. Estimating their population has remained a major challenge. But a recent study is changing that. Spanning two years and 59,000 sq km. across trans-Himalayan Ladakh, the assessment estimated that around 477 snow leopards, making up about 68% of India's total snow leopard population, live in the region. The assessment is said to be the most extensive and in-depth snow leopard survey ever conducted in India. 'We built on lessons learned from 25 years of large-scale tiger population assessments to make this study robust and replicable. It wasn't limited to known hotspots or prime habitats. This makes it the largest, most systematic, and most intensive effort ever undertaken across the snow leopard range,' says Pankaj Raina from the department of wildlife protection, Leh, union territory of Ladakh, and one of the study's co-authors. Ground work Ladakh is home to the country's largest contiguous snow leopard habitat. To understand where these elusive big cats live and estimate their numbers, researchers used a 'double-sampling' method. First, they walked over 6,000 km across the region, documenting signs like scat, paw prints, and scrape marks. Then, in the second phase, they set up 956 camera traps across high, medium, and low-density areas, capturing over 26,000 images of snow leopards. 'Difficult terrain and poor transport infrastructure made the survey a logistical challenge. We relied on ponies to carry rations and equipment, set up temporary camps in sub-zero conditions, and had to wait for winter to access some remote areas, when frozen streams allowed passage. Cameras were placed one winter and collected the next, ensuring strong coverage,' says Raina. An artificial intelligence tool called CaTRAT, designed to recognise Himalayan wildlife, was used to identify the species in the images. Biologists then verified these identifications. From this data, snow leopard photos were selected and analysed using a software called Extract-Compare, which focused on the unique forehead patterns of each animal – like a fingerprint – to tell individual snow leopards apart. It turned out to be more reliable than the commonly used side-pattern method. 'The snow leopard's long fur can ruffle in the wind and distort side patterns, but the forehead has shorter, more consistent fur, which makes identification clearer,' says Yadvendradev Jhala, an Indian National Science Academy senior scientist, also associated with the National Centre for Biological Sciences and Wildlife Institute of India, and a co-author of the study. Looking at forehead patterns not only reduced the number of cameras needed but also delivered cleaner, more consistent data. The outcome: India's first national photo library of snow leopards, wherein the unique pelage pattern of every individual is digitised using a machine learning program. Other range countries and Indian states can contribute to this library. As this database grows, it will support long-term tracking of individuals, help detect poaching, and reveal behavioural trends across years and regions. The researchers also used satellite images and climate data to study the landscape and understand what kind of terrain snow leopards prefer, and utilised a method called spatial capture-recapture (which estimates populations based on repeated sightings of known individuals across space) to estimate how many leopards were in the region. The numbers speak Researchers recorded 9,525 signs of snow leopards across the landscape. From 97,000 camera-trap nights, they identified 126 individual snow leopards. Based on the data, the study estimates that around 477 snow leopards inhabit 47,572 square kilometres of trans-Himalayan Ladakh, making up about 68% of India's total snow leopard population. Densities varied widely, from as low as 0.003 to as high as 3.18 individuals per 100 sq km. Hemis National Park and Nubra Shyok Wildlife Sanctuary showed notably high concentrations. 'The average density across the entire Ladakh landscape is about one snow leopard per 100 sq km. But at Hemis National Park, it goes up to as much as three per 100 square kilometres. That's very high,' says Jhala. The researchers found that snow leopards preferred lower-elevation grasslands with abundant prey, both wild and domestic. More than half of the sightings (61%) occurred outside protected areas, in landscapes shared with people, livestock, and seasonal tourists. 'We also GPS-collared 10 individuals. Data (yet to be published) show home ranges from 100 to 500 sq km, depending on habitat and prey availability. This confirms they are wide-ranging animals, often moving far beyond protected areas,' says Raina. Coexistence in a changing land The survey findings highlight the importance of shared landscapes and coexistence. Local communities in Ladakh have lived alongside wildlife for generations, guided by cultural values and sustainable pastoral practices. 'Snow leopards are not poached here. The combination of the Buddhist culture and economic incentives to preserve the species has allowed their population to increase in density,' says Jhala. Yet coexistence is not without its challenges. Snow leopards feed on both wild prey, such as blue sheep, ibex, and Ladakh urial, and on domestic livestock. In winter, when food is scarce, they follow herds into lower valleys shared by people and animals alike. These multi-use valleys, especially along the Indus river, are crucial to winter grazing. This overlap can lead to conflict, especially when snow leopards hunt livestock. To mitigate this potential for conflict, the researchers stress the need for compensation schemes and policies that support both wildlife and local communities. Moreover, Ladakh's unique land-use pattern has helped the snow leopard thrive. 'Human activities, including agriculture, are performed only on 0.5% of the total geographical area, leaving the rest beyond human influence. It makes almost all landscapes in Ladakh viable for conservation,' says Raina. What comes next Snow leopards are more than charismatic icons. They are apex predators, crucial to maintaining the ecological balance of fragile mountain ecosystems. Yet their survival is increasingly under pressure. The study flags several looming threats: growing tourism, road and dam construction, habitat loss, and climate-driven changes in vegetation. Among the most urgent concerns is the rise of free-ranging dogs, a direct consequence of garbage accumulating near army camps and expanding towns. 'There's a natural community of carnivores here, such as wolves, lynx, brown bears, foxes, but feral dogs are a man-made crisis. They pose a serious threat to both snow leopards and wolves, and the situation will only worsen if left unchecked,' says Jhala. Additionally, conserving only protected areas is not enough. Development must be based on cumulative impact assessments and shared mitigation strategies. 'Ladakh has its own ecological and cultural context. Copy-pasting development models from elsewhere will not work,' says Raina. To address this gap, the study calls for long-term monitoring, expansion into under-studied regions, and stronger protections for shared-use landscapes. 'Our findings show Ladakh's snow leopard population is contiguous; it connects with populations in China, Tibet, Nepal, Pakistan and the Karakoram (mountain range). So, any new infrastructure must be planned with care, to ensure it doesn't fragment this vital corridor. This is also a good dataset to showcase why green infrastructure – animal passages, corridors – needs to be the norm,' says Jhala. What also makes this survey significant is its alignment with global conservation frameworks such as PAWS (Population Assessment of the World's Snow Leopards). By applying standardised methods across a vast and varied landscape, the researchers have created a replicable model that could be scaled across the Indian Himalayas. This unified approach will only improve snow leopard conservation in the future. 'Moreover, its comprehensive, replicable methodology will also be able to help monitor other carnivores, such as wolves, lynx and brown bear, using the same camera trap data,' says Jhala.
Time of India
23-06-2025
- Science
- Time of India
Scientists use clever trick to count ghosts of the mountains
NEW DELHI: Wildlife scientists while enumerating snow leopards in India during the last population assessment used a smart trick to make the elusive big cats in the high and rugged Himalayas pose in front of cameras and get their foreheads having distinctive patterns, akin to human fingerprints, photographed. Tired of too many ads? go ad free now They used a scent, which only had a localised effect, in luring and making a snow leopard bend down and expose its forehead to the appropriately positioned camera trap, according to a recent study that explained the methodology adopted to count the big cats, nicknamed 'ghost of the mountains'. It was done by spraying a small amount of perfume just below the cameras that were deployed near their favoured scent marking rocks on high-ridge tops, said the authors of the study published last month in the open-access journal PLOS One. They added that once the curious leopards lower their heads to smell, the enumerators got their prized-unique pictures Though the snow leopard population assessment in India was done during 2019-23 and the counting figure, total 718 in India, was released last year, the scent lure method was revealed in the study by Pankaj Raina from the Ladakh wildlife protection department and co-authors, including senior wildlife scientist at the Indian national science academy, Yadvendradev V Jhala, and others from the Dehradun-based Wildlife Institute of India. "We identified individual snow leopards through their unique forehead pattern," said the authors while underlining that every camera trap photograph was geotagged and stamped with the time and date information in the metadata. "The photo-captured species were identified using an AI-based software programme, CaTRAT, customised to identify Himalayan species. The identified species were subsequently validated by biologists," they said. The counting figures, released in 2024, show the highest number, 477, of snow leopards in Ladakh out of total population of 718 in India. Among the remaining ones, 124 snow leopards are in Uttarakhand, 51 in Himachal Pradesh, 36 in Arunachal Pradesh, 21 in Sikkim and 9 in Jammu & Kashmir. Covering approximately 1.2 lakh sq km, the counting exercise was conducted using a meticulous two-step framework. The first step involved evaluating snow leopard spatial distribution while the second step involved estimation using camera traps in each identified stratified region. During the exercise, camera traps were deployed at 1,971 locations, including 956 in Ladakh.
