Researchers using artificial intelligence have discovered that African lions produce two distinct types of roars, including a previously unrecognized intermediary version. This breakthrough, detailed in a new study, enhances monitoring techniques for the vulnerable species. The finding promises more accurate conservation efforts amid declining lion populations.
A team from the University of Exeter has identified an intermediary roar in African lions, challenging the previous belief that they only produce one type. Published in Ecology and Evolution, the study employed machine learning to classify roars with 95.4% accuracy, minimizing human bias in identification.
Lead author Jonathan Growcott explained the significance: "Lion roars are not just iconic—they are unique signatures that can be used to estimate population sizes and monitor individual animals. Until now, identifying these roars relied heavily on expert judgment, introducing potential human bias. Our new approach using AI promises more accurate and less subjective monitoring, which is crucial for conservationists working to protect dwindling lion populations."
The International Union for Conservation of Nature lists lions as vulnerable, with an estimated 20,000 to 25,000 wild individuals remaining in Africa—a decline of about half over the past 25 years. This AI-driven method improves passive acoustic monitoring, offering a reliable alternative to traditional approaches like spoor surveys or camera traps.
Growcott emphasized the need for change: "We believe there needs to be a paradigm shift in wildlife monitoring and a large-scale change to using passive acoustic techniques. As bioacoustics improve, they'll be vital for the effective conservation of lions and other threatened species."
The research involved collaborations with the University of Oxford's Wildlife Conservation Unit, Lion Landscapes, Frankfurt Zoological Society, TAWIRI, and TANAPA. Funding was provided by the Lion Recovery Fund, WWF Germany, the Darwin Initiative, and the UKRI AI Centre for Doctoral Training in Environmental Intelligence.