A groundbreaking study has revealed that African lions produce not just one, but two distinct types of roars—challenging long-standing assumptions and opening new possibilities for wildlife conservation. Researchers from the University of Exeter identified a previously unrecognized "intermediary roar" alongside the well-known full-throated roar, marking a significant advancement in the understanding of lion vocalizations. Published in Ecology and Evolution, the study leveraged artificial intelligence to automatically classify lion roars with 95.4% accuracy, drastically reducing the subjectivity associated with human expert analysis. This data-driven approach minimizes human bias and enhances the reliability of individual lion identification, a critical factor in monitoring population dynamics and tracking animal movements. Lead author Jonathan Growcott from the University of Exeter explained, "Lion roars are more than just iconic sounds—they serve as unique acoustic signatures that can help estimate population sizes and monitor individual animals. For years, identifying these roars depended heavily on expert judgment, which introduced potential inaccuracies. Our AI-powered method offers a more precise, objective, and scalable solution—essential tools for conservationists striving to protect declining lion populations." According to the International Union for Conservation of Nature (IUCN) Red List, lions are classified as vulnerable to extinction. The current wild lion population in Africa is estimated at between 20,000 and 25,000 individuals—a figure that has dropped by nearly half over the past 25 years due to habitat loss, human-wildlife conflict, and poaching. The study demonstrates that a single lion roaring bout typically includes both the full-throated roar and the newly identified intermediary roar, contradicting the previous belief that only one type existed. This discovery aligns with similar advances in the study of other large carnivores, such as spotted hyenas, and underscores the growing importance of bioacoustics in ecological research. By using advanced machine learning techniques, the research team developed a system capable of reliably distinguishing individual lions based on their roars. This innovation simplifies passive acoustic monitoring—recording animal sounds in the wild—making it a more efficient and cost-effective alternative to traditional methods like camera traps or spoor surveys. Growcott emphasized the need for a fundamental shift in wildlife monitoring: "We believe there must be a widespread adoption of passive acoustic techniques in conservation. As bioacoustic technology continues to improve, it will play a vital role in protecting lions and other endangered species." The research was a collaborative effort involving the University of Exeter, the Wildlife Conservation Unit at the University of Oxford, Lion Landscapes, the Frankfurt Zoological Society, TAWIRI (Tanzania Wildlife Institute for Research), TANAPA (Tanzania National Parks Authority), and computer scientists from both Exeter and Oxford.