AI Reveals the Secrets of the Narwhals
The narwhal, a whimsical unicorn of the Arctic seas that is often mistaken for a myth, is difficult to study. The (relatively) minute whales live far from human population centers and hunt for food deep (up to a thousand meters) under the water. Now, researchers from the University of Copenhagen and the Greenland Institute of Natural Resources are applying artificial intelligence in an attempt to understand how these strange creatures forage for food.
The hitherto-best method for tracking the habits of the elusive narwhal has been attaching instruments to them and processing the resulting acoustic and movement data. This is useful when assessing many of narwhals’ habits – but during hunting, the clicks turn to buzzing, and as a result, are much harder to analyze (particularly by hand).
So the researchers – a collaboration between mathematicians, computer scientists and marine biologists – worked to develop an AI algorithm to process those buzzes. They trained the algorithm using a large dataset garnered from five narwhals in the waters off of Greenland.
“[These] whales have very complex movement patterns, which can be tough to analyze,” explained Raghavendra Selvan, a professor in the University of Copenhagen’s Department of Computer Science. “This becomes possible only with the use of deep learning, which could learn to recognize both the various swimming patterns of whales as well as their buzzing sounds. The algorithm then discovered connections between the two.”
“We have shown that our algorithm can actually predict that when narwhals emit certain sounds, they are hunting prey. This opens up entirely new insights into the life of narwhals,” added Susanne Ditlevsen, a professor in the University of Copenhagen’s Department of Mathematical Sciences.
These sorts of insights are increasingly important for the species, with the narwhal’s extinction risk designated as “near threatened” and warming Arctic waters threatening the narwhals’ habitat and inviting more shipping traffic through the area.
“It is crucial to gain more insight into where and when narwhals hunt for food as sea ice recedes. If they are disturbed by shipping traffic, it matters whether this is in the middle of an important foraging area. Finding out however, is incredibly difficult. Here, artificial intelligence seems to be able to make a huge difference and to a great extent, provide us with knowledge that could not otherwise have been obtained,” said researcher Mads Peter Heide-Jørgensen, a professor at the Greenland Institute of Natural Resources. “In a situation where narwhals are in deep water, in the middle of the Bay of Baffin during December, we currently have no way of finding out where or when they are foraging. Here, artificial intelligence seems to be the way forward.”