Can AI text notifications help save snow leopard from extinction?

A snow leopard can’t growl. Therefore, when we step towards one of these rigid predators, it is blinking.

“Great”, as it is called, was an orphan and rescued 12 years ago in Pakistan, introduced by Gilgit-Baltic.

After many years of hope for the staff to feed her, she does not know how to hunt in the wild – and cannot be released.

“When we release her, she just goes on the sheep of the farmer and perish,” – tells us that the “Tehzeeb Hussain” warden.

Despite the laws that protect them, they annually kill from 221 to 450 snow leopards, notes the World nature Fund (WWF), which has contributed to the decline in the world over the past two decades.

More than half of these deaths were retaliation for the loss of pets.

Now scientists have estimated that in the wild there are only 4000 to 6,000 snow leopards – approximately 300 of them in Pakistan, the third largest population in the world.

To try to turn these disturbing trends, WWF – using the University of Lahor University on Sciences (Lums) – developed cameras working on artificial intelligence (AI).

Their purpose is to identify the presence of a snow leopard and prevent the village residents through a textual message to transfer the animal to safety.

High, with a solar panel mounted on top, the cameras are located high among the infertile and durable mountains on almost 3000 m (9 843 feet).

“Snow leopard territory,” says Asif Ikbal, a environmentalist from WWF Pakistan. He goes a few more steps and points to the traces on the ground: “It’s pretty new.”

ASIF hopes that this means that the camera has recorded more evidence that AI software – which allows it to distinguish people, other animals and snow leopards – works.

Currently, WWF checks 10 cameras, deployed in three villages in Gilgit-Baltistan. It took three years to teach the AI ​​model to identify these categories with impressive – if not perfect – accuracy.

Once we’re around the mountain again, Asif pulls up the computer and shows me a dashboard. There I am in the GIF series. It correctly discovers that I am a person. But when we scroll the list, I approach again, and this time I am listed both by the human and the animal. I put on a thick white fleece, so I forgive the program.

Then ASIF shows me a shot of money. This is a snow leopard recorded a few nights before, at night. He pulls up another one week before. This is a snow leopard that lifts the tail to the neighboring rock. “This is the mother of Leopard, it seems that she notes her territory,” says Asif.

Setting up the camera in rocky, high -rise areas has taken a lot of attempts and mistakes. WWF went through several types of batteries until the one that could resist the harsh winter. A specific paint was chosen to avoid displaying light when animals pass.

If the cellular service does not work in the mountains, the device continues to record and capture the data locally. But the team had to accept, there are some problems they just can’t solve.

While the camera lens was protected by a metal box, they had to replace solar panels damaged by landslides.

Not only did the technology cause problems. Getting a local community also became a problem. At first, some were suspicious and doubted whether the project could help them or snow leopards.

“We have noticed that some wires were shortened,” Asif says. “People threw blankets on the camera.”

The team also had to remember the local culture and the focus on the particular women. The cameras needed to move because women were going too often.

Some villages still still need to sign the consent and forms of privacy, which means that technology in their area cannot be watered. WWF wants a mandatory promise that local farmers will not make poachers access to personnel.

Sitar lost all six sheep in January. She says she took them to graze on the land over their home, but they were attacked by a snow leopard.

“It was three -four years of hard work, raising these animals, and it ended in one day,” she says.

The loss of her livelihood left the bed for a few days. Asked if she hopes that AI cameras can help in the future, she replies: “My phone practically does not receive services throughout the day, how can the text help?”

At the collection of the village of Elders, the leaders of the village of Hyber explain how the relations have changed over the years and that the increasing share of their villages understand the importance of snow leopards and their influence on the ecosystem.

According to WWF, Snow Leopards Hund Ibex and Blue Auper, which prevents these animals from bend and helps keep the meadows so that the villagers can feed the animal.

But not everyone is convinced. One local farmer calls into question the benefits of animals.

“We used to have 40 to 50 sheep. Now we have only four or five, and the reason is that the threat of snow leopards and Ibex eating grass,” he says.

Climate change also plays a role in why some feel the snow leopard. Scientists say the warming temperature forced the villagers to move the crop and livestock to higher areas in the mountains, encroaching on their own snow leopard habitats, making the animal more.

Whether the villages are convinced of the preservation or not, WWF reports to us that legal penalties have served as a strong deterrent in recent years. In 2020, they went to jail after the murder of a snow leopard in the Hopper Valley, approximately two hours away from Haver. One of them posted photos with a dead animal on social media.

While those who participate in the camera project hope that their AI devices can influence, they know that they cannot be the only solution.

In September, they will begin to experience the smells, sounds and lights on the camera sites to try to restrain the snow leopards from moving to the nearby villages, supplying themselves and the animal.

Their work, which tracks these “ghosts of the mountains”, has not yet ended.