A group of scientists based at the University of Oxford, have used machine learning algorithms, widely known as AI, and discovered that each lion has a unique, identifiable and trackable roar.
Lions are known for their uniqueness in behaviour and character, what makes them distinct from other wild animals in the animal kingdom is their mighty and thrilling roar that can be heard from 8 kilometres (5 miles) away.
Lions may roar for a couple of reasons, which include; roaring mightily to show off their territorial ownership, intimidating rivals or to locate fellow pride members.
By using the new machine learning technologies, the scientists based in WildCRU at the University of Oxford, partnered with fellow researchers in the Department of Computer Science to discover a new device, known as a biologger.
The biologger can be attached to an existing lion GPS collar to record audio and movement data. The biologgers then allow the scientists to associate each roar with the correct lion by cross-referencing movement and audio data through the large datasets of roar recordings collected.
After the data was collected by the biologgers, the scientists trained a pattern recognition algorithm to “learn” each individual’s roars and then tested the algorithm on sequences that it had not seen before to determine whether the shape of the contour as a whole is an important distinguishing feature.
Results were later published in Bioacoustics, and revealed that each individual lion produces a distinct frequency pattern with 91.5% accuracy.
According to the findings, the overall shape of the fundamental frequency (f0) of the full-throated roar contour is consistent within each individuals’ roars and sufficiently different from other individuals to allow for accurate classification of individual identity.
While previous studies have revealed that lions can recognize the calls of other individuals, allowing them to locate distant companions and also to avoid potentially hostile neighbours. Until then, only little has been understood about how individuals convey identity information in the structure of their calls.
The latest research has revealed a possible mechanism for individual vocal recognition amongst African lions. This indicate that individual lions may be able to learn the subtle variations in the fundamental frequency of other lions’ roars and therefore associate particular variations with particular identities in the wild.
“African lion numbers are declining and developing cost effective tools for monitoring, and ultimately better protecting, populations is a conservation priority. The ability to remotely evaluate the number of individual lions in a population from their roars could revolutionize the way in which lion populations are assessed,” said Andrew J. Loveridge, from WildCRU at the Department of Zoology.
By using the new machine learning technologies, scientists could also develop alternative techniques for assessing the animal’s population and improve conservation as the top most priority.
“Being able to accurately distinguish between individual roars using machine learning algorithms could facilitate the development of alternative techniques for assessing population density and tracking individual movements across the landscape,” said Andrew Markham, from the Department of Computer Science at Oxford.
As technology is rapidly growing, the scientists and researchers are developing ways to precisely track individual animals and their behaviour to see if they could find sufficient information.