New research has demonstrated that artificial intelligence (AI) can be trained to recognize individual birds, a task humans are not capable of doing in ordinary circumstances.
"Our study provides the means of overcoming one of the greatest limitations in the study of wild birds—reliably recognizing individuals." Dr. André Ferreira at the Center for Functional and Evolutionary Ecology (CEFE), France, and lead author of the study, explained in a press release.
Avian artificial intelligence
In the study, researchers from institutes in France, Germany, Portugal, and South Africa detail the process they developed for using AI to identify individual birds. They used thousands of labeled images of birds they had collected to train and test AI — in doing so, they developed the first successful model to identify individual birds in such a way.
The research, published in the British Ecological Society journal Methods in Ecology and Evolution, shows how the AI models were trained to recognize images of individual birds in wild populations of great tits and sociable weavers, as well as a captive population of zebra finches.
The AI was shown to have an accuracy of over 90% for the wild species and 87% for the captive zebra finches.
Non-invasive identification of animals
In animal behavior studies, methods for identifying individual birds can be costly for researchers and uncomfortable for the birds. For example, one method, which sees scientists attach color bands to birds' legs, has been shown to cause stress to the animals.
"The development of methods for automatic, non-invasive identification of animals completely unmarked and unmanipulated by researchers represents a major breakthrough in this research field," Dr. André Ferreira explains.
"Ultimately, there is plenty of room to find new applications for this system and answer questions that seemed unreachable in the past," he explains.
It's certainly not the first time AI has been used on flying creatures — last year, an AI model was trained on two species of butterflies and, in doing so, validated the first mathematical model of evolution.