Summary: A new study reveals African lions produce two types of roars, overturning long-held assumptions and opening the door to more precise wildlife monitoring. Using machine learning, researchers automatically distinguished between full-throated and newly identified intermediary roars with over 95% accuracy, eliminating much of the human bias in vocal identification.
This breakthrough greatly enhances conservation efforts by enabling reliable, noninvasive population tracking. As lion numbers continue to drop across Africa, AI-driven bioacoustics may become a critical tool for protecting vulnerable big-cat populations.
Key Facts:
- Two Roar Types: Lions produce both full-throated roars and a newly identified intermediary roar.
- AI Precision: Machine learning classified roar types with 95.4% accuracy, outperforming expert judgment.
- Conservation Impact: Improved acoustic monitoring supports better population estimates and protection strategies.
Source: University of Exeter
A new study has found African lions produce not one, but two distinct types of roars – a discovery set to transform wildlife monitoring and conservation efforts.
Researchers at the University of Exeter have identified a previously unclassified “intermediary roar” alongside the famous full-throated roar.
The study, published in Ecology and Evolution, used artificial intelligence to automatically differentiate between lion roars for the first time.
This new approach had a 95.4 per cent accuracy and significantly reduced human bias to improve the identification of individual lions.
Lead author Jonathan Growcott from the University of Exeter said: “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.”
According to the International Union for Conservation of Nature red list, lions are listed as vulnerable to extinction. The total population of wild lions in Africa is estimated to be between 20,000 and 25,000, but this number has decreased by half in the last 25 years.
The study establishes that a lion’s roaring bout contains both a full-throated roar and a newly named intermediary roar, challenging the long-held belief that only one roar type existed.
These findings echo similar advances in the study of other large carnivores, such as spotted hyaenas, and highlight the growing potential of bioacoustics in ecological research.
Researchers used advanced machine learning techniques and by implementing this automated, data-driven approach to classify full-throated roars, the team improved the ability to distinguish individual lions. The new process simplifies passive acoustic monitoring, making it more accessible and reliable compared to traditional methods like camera traps or spoor surveys.
Jonathan Growcott continued: “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 was a collaborative effort between the University of Exeter, the Wildlife Conservation Unit at the University of Oxford, Lion Landscapes, Frankfurt Zoological Society, TAWIRI (Tanzania Wildlife Institute for Research) and TANAPA (Tanzania National Parks Authority), as well as computer scientists from Exeter and Oxford.
Funding: The work was supported by the Lion Recovery Fund, WWF Germany, the Darwin Initiative, and the UKRI AI Centre for Doctoral Training in Environmental Intelligence.
Key Facts:
A: They identified a second, distinct “intermediary roar” alongside the classic full-throated roar.
A: It classifies roars with 95.4% accuracy, reducing human bias and improving individual identification.
A: Precise acoustic tracking helps estimate population sizes and strengthens protection of rapidly declining lion populations.
Editorial Notes:
- This article was edited by a Neuroscience News editor.
- Journal paper reviewed in full.
- Additional context added by our staff.
About this AI and communication research news
Author: Louise Vennells
Source: University of Exeter
Contact: Louise Vennells – University of Exeter
Image: The image is credited to Neuroscience News
Original Research: Open access.
“Roar Data: Redefining a lion’s roar using machine learning” by J. Growcott et al. Ecology and Evolution
Abstract
Roar Data: Redefining a lion’s roar using machine learning
For territorial advertisement and intra-pride communication African lions emit a roaring bout, of which one component, is their iconic roar.
The full-throated roar of a lion has recently been shown to be a unique and individually identifiable signature. At the same time, the frequency of large-scale passive acoustic monitoring surveys has increased. As such, a lion’s roar may soon become a useful tool to count individuals and estimate population density, to supplement traditional survey techniques.
Currently, selecting full-throated roars is heavily dependent on expert inference and is therefore subject to human-induced bias. We propose a data-driven approach to automatically classify lions’ full-throated roars from the other vocalisations that constitute a roaring bout.
By using two-state Gaussian Hidden-Markov Models, we also demonstrate that two types of roars exist within a lion’s roaring bout—a full-throated roar and a newly named intermediary roar—and these can be classified at an accuracy of 84.7%.
We further demonstrate that using simple metrics to describe lion vocalisations—maximum frequency (Hz) and vocalisation length (s)—and K-means clustering is sufficient to classify lion call types, at a high accuracy (95.4%), and that using data-driven predicted full-throated roars results in an improved ability to identify individuals (F1-score 0.87 vs. manual full-throated roar classification 0.80).
Here, we establish an easy-to-understand and implement process that will reduce the knowledge gap and make passive acoustic monitoring more accessible in a field currently dominated by other monitoring techniques (e.g., camera surveys), paving the way for novel research.
