New research from James Cook University (JCU) combining artificial intelligence with acoustic monitoring to track mammal populations across eastern Australia is a game-changing step for animal conservation.
The study, recently published in Methods in Ecology and Evolution, used artificial intelligence (AI) to analyse over 300,000 hours of vocal recordings of mammal species from Far North Queensland to southern New South Wales and discovered a new approach to mammal monitoring that will have a ground-breaking impact on conservation.
"Australia is the worst place for mammal extinctions in the world," said lead researcher and JCU Postdoctoral Research Fellow Dr Sebastian Hoefer.
"Many of our mammals are endemic, with highly restricted ranges and important ecological roles.
"Monitoring their populations is vital for effective conservation — yet traditional techniques are difficult to scale across large areas."
Dr Hoefer explained their idea was inspired by similar successes in bird monitoring.
"AI processing of bird recordings has worked really well across entire ecoregions, so we wanted to see if the same technique could be applied to vocalising mammals," he said.
In a first, the team fed the equivalent of 36 years of terrestrial mammal recordings from national parks, conservation areas and reserves across eastern Australia into the open source BirdNET AI software.
"You can imagine it's a bit like ChatGPT," Dr Hoefer said.
"It's a machine learning recogniser that's been trained on birds, but we can tell it what we want to find.
"For example, we can input a single example call from a mammal — say, a male koala bellowing — and then instruct the system to locate all similar sounds across the recordings."
Dr Hoefer explained that the strength of this new approach lies in its ability to process massive amounts of data collected over vast areas and timeframes — something traditional methods, like camera traps or field surveys, struggle to achieve.
"It worked extremely well, especially for long-term monitoring," he said.
"Now we can rely on acoustic monitoring and AI for vocal mammal species, and this allows us to redirect more time and funding towards monitoring mammals that don't vocalise."
In terms of conservation, the research is expanding the understanding of the presence and activity patterns of mammals in the wild which can help guide management decisions.
"It was amazing to discover how effective using mammal calls can be to detect and monitor species over such large scales," said Dr Hoefer.
"This approach gives us new insights into where, when, and how species are active in the landscape. For example, deer have very specific vocalising periods during the rutting season.
"By continuously recording throughout the year, we can identify these peak activity windows and plan targeted management or monitoring during those times."
Looking ahead, the researchers plan to develop a species-specific recogniser for these mammals, trained on the validated calls collected during this study.
"This will make it even easier to detect and monitor mammal species across Australia in the future," Dr Hoefer said.
