Most brown bears may look like carbon copies of each other, but they all have their own little differences in appearance and behavior. Still, telling individual bears apart can be a real challenge that requires a trained eye and years of close observation. Thankfully, artificial intelligence is making bear-watching a whole lot easier.
A new study published in Current Biology has unveiled an AI program that can identify individual brown bears in the wild based on distinct facial features and poses. It has already shown promise in Alaska, where brown bears are regularly observed to understand how the species moves and behaves.
Brown Bear Viewing in Alaska
Alaska is home to approximately 30,000 brown bears, which makes up over 98 percent of the U.S. brown bear population. Bear viewing sites across the state are popular destinations from July through September, the best time for visitors to see bears eat and play.
One of these sites, the McNeil River State Game Sanctuary, has the largest seasonal gathering of brown bears in the world. Nearly 150 bears congregate there in the summer, drawn to the masses of chum salmon that return to McNeil River to spawn.
AI program helps identify brown bears in Alaska.
(Image Credit: Beth Rosenberg/ CC BY-SA 4.0)
The summertime arrival of brown bears isn’t just for entertainment; it also gives scientists a chance to watch individual bears and keep an eye on population dynamics and ecosystem health.
Brown bears aren’t so easy to distinguish from one another, however. They don’t have clear-cut marks, and so it takes a lot of time and effort to tell each bear apart. It gets even trickier across seasons, as bears emerge from hibernation in spring at their leanest, then change in size and appearance later in the year.
Read More: Orange Rivers in Alaska Signify a Color-Changing Crisis, Exposing Fish to Toxic Metals
Collecting Faces and Poses
Researchers wanted to find a more practical way to identify individual bears, which is how the new AI model, PoseSwin, was born. The system focuses on facial features that don’t change much over time: muzzle shape, brow bone angle, placement of ears, while also including pose information (including frontal, profile, and tilted views).
“Our biological intuition was that head features combined with pose would be more reliable than body shape alone, which changes dramatically with weight gain,” said study author Alexander Mathis, a professor at École Polytechnique Fédérale de Lausanne, Switzerland, in a statement. “The data proved us right — PoseSwin significantly outperformed models that used body images or ignored pose information.”
AI helps identify bears in Alaska.
(Image Credit: Beth Rosenberg/ CC BY-SA 4.0)
The researchers trained PoseSwin by repeatedly showing the AI algorithm three images: two of the same bear taken at separate times and one of a different bear. The program learned to group photos of the same bear near each other, pushing photos of other bears away.
Leaving Bears Alone
PoseSwin was tested with photos taken by visitors to Katmai National Park and Preserve, located around 37 miles (60 km) away from McNeil River. The algorithm recognized individual bears from these photos, showing where they were moving in search of food.
“The technology could eventually be used to analyze the thousands of pictures that visitors take every year and help to build a map of how brown bears use this expansive area. This helps us to understand what they need, how their population dynamics work, and many other important ecological questions,” said study author Beth Rosenberg, a researcher at Alaska Pacific University who captured over 72,000 photos of 109 different brown bears from 2017 to 2022.
With PoseSwin, researchers can track bears without being invasive. Bears may sometimes avoid areas where they have encountered humans, causing them to change movement patterns, miss reproductive opportunities, or lose out on fat and protein from crucial feeding sites.
The researchers have observed bears — each given their own name, like “Rocky,” “Sloth,” and “Not Ears” — traveling between McNeil River and Katmai. Knowing how these bears move, they say, could provide a better understanding of how the local ecosystem is functioning.
Read More: Are Animals Like Mountain Lions and Bears Leaving Yellowstone National Park?
This article has been updated to include additional information on bear behavior on 2/5/26 by the Discover staff.
Article Sources
Our writers at Discovermagazine.com use peer-reviewed studies and high-quality sources for our articles, and our editors review for scientific accuracy and editorial standards. Review the sources used below for this article:
- This article references information from a study published in Current Biology:Individual identification of brown bears using pose-aware metric learning
- This article references information from the Alaska Department of Fish and Game: Brown Bear (Ursus arctos)
