A new study has offered a new means of overcoming one of the greatest limitations in the study of wild birds – reliably recognizing individuals. In the study, scientists have developed an Artificial Intelligence to train computers to identify individual birds.
The study published in the British Ecological Society journal Methods in Ecology and Evolution describes the process of using AI to identify birds individually. This involves collecting thousands of labeled images of birds and then using this data to train and test AI models.
Scientists trained the AI models to recognize images of individual birds in wild populations of great tits and sociable weavers and a captive populace of zebra finches, probably the most regularly contemplated winged creatures in behavioral ecology. After training, the AI models were tested with images of the people they had not seen before and had a precision of over 90% for the wild species and 87% for the captive zebra finches.
In animal behavior studies, individually identifying animals is one of the most expensive and time-consuming factors, limiting the scope of behaviors and the size of the populations that researchers can study. Current identification methods like attaching color bands to birds’ legs can also be stressful for the animals.
These issues could be solved with AI models. Dr. André Ferreira said: “The development of methods for automatic, non-invasive identification of animals completely unmarked and unmanipulated by researchers represents a breakthrough in this research field. Ultimately, there is plenty of room to find new applications for this system and answer questions that seemed unreachable in the past.”
AI’s need to be fed with thousands of labeled images to identify individuals accurately. Companies like Facebook can do this for human recognition since they approach a large number of pictures of different people that are willfully tagged by users. In any case, getting such labeled photos of animals is challenging and has made a bottleneck in research.
Scientists addressed this issue by building feeders with camera traps and sensors. Most birds in the investigation populaces conveyed a passive integrated transponder (PIT) tag, like the microchips implanted in pet cats and dogs. Antennae on the bird feeders were able to peruse the identity of the bird from these labels and trigger the cameras.
Being able to distinguish individual animals from each other is essential for the long-term monitoring of populations and protecting species from pressures such as climate change. While some species, such as leopards, have distinct patterns that allow humans to recognize them by eye, most species require additional visual identifiers, such as color bands attached to birds’ legs, for us to tell them apart. Even then, methods like this are hugely time consuming and error-prone.
AI methods like the one shown in this study use a type of deep learning known as convolutional neural networks; these are optimal for solving image classification problems. In ecology, these methods have previously been used to identify animals at a species level and individual primates, pigs, and elephants. However, until now, it hasn’t been explored in smaller animals like birds.
Dr. André Ferreira said, “The model can identify birds from new pictures as long as the birds in those pictures are previously known to the models. This means that if new birds join the study population, the computer will not be able to identify them.”
The appearance of individual birds can change over time, for instance, molting, and it’s not known how the performance of the AI model will be affected. Images of the same bird taken months apart could be mistakenly identified as different individuals.
The authors add that both these limitations can be overcome with large enough datasets containing thousands of images of thousands of individuals over long periods, which they are currently trying to collect.
Journal Reference:
- André C. Ferreira et al. Deep learning‐based methods for individual recognition in small birds. DOI: 10.1111/2041-210X.13436