A study conducted by the University of Essex and published in Communications Biology utilized artificial intelligence to shed light on the longstanding debate around the theory of evolution. While Charles Darwin believed sexual selection was responsible for the diverse appearances of males in a species, Alfred Russel Wallace contended that natural selection influenced both sexes equally. To test these theories, the University of Essex researchers chose to study the birdwing butterfly group.
Using an AI algorithm called ButterflyNet, the team analyzed a comprehensive dataset of 16,000 birdwing butterfly photographs from London’s Natural History Museum. The AI method involved the curation and digitization of the museum’s butterfly collection; teaching ButterflyNet to identify and group images based on visual similarities; generating a multidimensional butterfly space for analyzing evolutionary relationships and disparities; validating the AI-derived findings with genetic data; and introducing a metric called the sexual disparity difference to measure variation between the sexes.
The conclusions drawn from the study affirmed elements of both Darwin’s and Wallace’s theories. The male birdwing butterflies displayed more distinct shapes and patterns, in line with Darwin’s theory of sexual selection. However, significant variation was observed among females, especially within the Troides genus, supporting Wallace’s claim that natural selection could influence female phenotypes.
AI has been applied previously in the field of evolutionary biology. Remarkably, a study by researchers from Colorado State University using AI concluded that elephants, just like humans, communicate by calling each other by name. The study proposed that elephants had developed such communication methods due to their necessity to socialize and work cooperatively in groups. This finding lends credibility to one of Darwin’s key arguments, suggesting that animals, akin to humans, evolved such abilities for similar survival advantages.
Consequently, the application of AI in studies like these provides a powerful tool for testing and validating theories of evolution, and for understanding the remarkable diversity in the animal world. As mentioned by Dr. Hoyal Cuthill: “This is an exciting time, when machine learning is enabling new, large-scale tests of longstanding questions in evolutionary science.”
