Machine learning tools could provide transformative insights into animal communication, using AI models to decode and track conversation
There is no Rosetta Stone for translating animal communication signals, their meaning must be deciphered through careful observation and experimentation.
Annotating animal communication, such as recordings of bird calls, whale songs or primate gestures can be extremely time-consuming, and even experienced biologists often struggle to differentiate seemingly similar signal types.
Now, a group of researchers have discovered this may be fast-tracked by AI, which can decode the communication systems of whales, crows, bats, and other animals is coming within reach.
Machine learning algorithms as pattern detectors
Machine learning algorithms effectively function as powerful pattern detectors and content generators.
While able to process both written and spoken human language, as illustrated by interactive chatbots, they may also identify and classify animals’ signals from audio and video recordings.
However, that machine learning methods require vast amounts of data, as seen with the Chat GPT-3 language model, trained using hundreds of billions of ‘tokens’, which are roughly corresponding to words.
Co-author Dr Damián Blasi at Harvard University said: “That’s the equivalent of over two million books the length of Charles Darwin’s On the Origin of Species. We need creative solutions for collecting data for wild animals.”
Projects are already underway for datasets for some species
While there are challenges, there are also a few research projects experimenting with AI for animal communication, such as Project CETI (Cetacean Translation Initiative), which studies the communicative behaviour of sperm whales.
The project’s AI Lead, co-author Professor Michael Bronstein at the University of Oxford, explains: “We use gentle, bioinspired whale-mounted tags, underwater robots, and a wide range of other methods to map the full richness of these animals’ communicative behaviour.”
Co-author Professor Sonja Vernes added: “If we want to decode animal conversations, we need to know who talks to whom, and under what environmental and social conditions.
“Machine learning can help us to discover which signals animals are using and perhaps even what the signals mean, if we combine these approaches with well-designed experiments.”
“We can use this knowledge to improve animal welfare in captive settings and to design more effective conservation strategies”
Co-authors Aza Raskin and Katherine Zacarian, who are co-founders of the Earth Species Project (ESP), which studies the communication systems of a wide range of animal species, said: “As we expand our understanding of other species’ communicative behaviour, we can use this knowledge to improve animal welfare in captive settings and to design more effective conservation strategies.
“Ultimately, we hope to initiate a cultural shift driving greater respect for the many species with which we share planet Earth.”
A powerful rapid assessment tool for conservation work
In the future, it may even be possible to ‘listen in’ on animal communication in entire communities.
Raskin noted that machine learning could also potentially enable detailed comparisons of the communication of the last surviving individuals, which are all held in conservation breeding centres run by San Diego Zoo Wildlife Alliance, and transform them into historical baseline recordings.
Raskin said: “Lost calls could potentially be reintroduced. Cultural restoration is a profoundly beautiful example of the benefits of this research.”
Professor Christian Rutz from the University of St Andrews added: “If we can identify communication signals that are associated with distress or avoidance, passive acoustic monitoring systems could be used to eavesdrop on how ‘happy’ or ‘unhappy’ animals are at the landscape level.”
