AI Unveils Evolutionary Patterns Predicted by Darwin and Wallace

Summary: A novel AI-powered study explores evolutionary differences between male and female birdwing butterflies, shedding new light on a historical debate between Charles Darwin and Alfred Russel Wallace.

Using machine learning to analyze over 16,000 butterfly specimens, researchers found that both sexes contribute to species diversity. Males often show more variation, supporting Darwin’s theories of sexual selection, while subtle variations in females align with Wallace’s ideas on natural selection.

These findings expand on classical theories by showing how both mechanisms operate together to drive biodiversity.

Key Facts:

  1. AI analyzed over 16,000 male and female birdwing butterflies for evolutionary patterns.
  2. Males showed more variation, supporting Darwin’s sexual selection theory.
  3. Subtle variations in females align with Wallace’s natural selection theory.

Source: University of Essex

Pioneering AI-powered research on butterflies has probed the under-studied evolution of females and adds to a debate between the founding fathers of evolution.

The University of Essex study – published in Communications Biology – explores a controversy between Victorian scientists Charles Darwin and Alfred Russel Wallace.

Darwin thought males had more variation, as females often chose mates based on male appearance.

Whereas Wallace thought natural selection across sexes was the biggest factor in difference.

This shows a robot and a butterfly.
The research showed evolutionary patterns predicted by both Darwin and Wallace were found in the butterflies. Credit: Neuroscience News

For over a century, scientists have mostly studied males because their differences are more obvious, while females, with more subtle evolutionary changes, had been less studied.

By using high-tech machine learning Dr Jennifer Hoyal Cuthill examined more than 16,000 male and female birdwing butterflies, with collaborators from the Natural History Museum and AI research institute Cross Labs, Cross Compass.

This is the first time the visual differences between sexes have been explored across the species, which live in Southeast Asia and Australasia.

Birdwing butterflies were chosen for this study because of their spectacular wing colour patterns and differences between males and females.

Dr Hoyal Cuthill, from the School of Life Sciences, said: “This is an exciting time, when machine learning is enabling new, large-scale tests of longstanding questions in evolutionary science.

“For the first time we are able to measure the visible extents of evolution to test how much variation is present in different biological groups and among both males and females.

“Machine learning is giving us new information on the evolutionary processes which generate and maintain biodiversity, including in historically neglected groups.”

The study looked at photographs of butterflies from the Natural History Museum collections, which show a range of traits, like wing shapes, colours, and patterns, across several species.

It found that while males often have more distinct shapes and patterns, both males and females contribute to the overall diversity.

The research showed evolutionary patterns predicted by both Darwin and Wallace were found in the butterflies.

Showing that both males and females contribute to diversity among species.

The males showed more variation in appearance, which fits with Darwin’s idea that females choose mates based on these traits.

However, the deep learning also found subtle variation in females, matching Wallace’s predictions about natural selection allowing diversity in female phenotypes.

Dr Hoyal Cuthill said: “Birdwings have been described as among the most beautiful butterflies in the world. This study gives us new insights into the evolution of their remarkable but endangered diversity.

“In this case study of birdwing butterfly photographs, it is sex that appears to have driven the greatest evolutionary change, including extreme male shapes, colours and patterns.

“However, within the group of birdwing butterflies, we found contrasting examples where female birdwing butterflies are more diverse in visible phenotype than males, and vice versa.

“High visible diversity among male butterflies supports the real-word importance of sexual selection from female mate choice on male variation, as originally suggested by Darwin.

“Cases where female butterflies are more visibly diverse than the males of their species, support an additional, important role for naturally selected female variation in inter-species diversity, as suggested by Wallace.

“Large-scale studies of evolution using machine learning offer new opportunities to resolve debates that have been outstanding since the founding of evolutionary science.”

About this evolution and AI research news

Author: Ben Hall
Source: University of Essex
Contact: Ben Hall – University of Essex
Image: The image is credited to Neuroscience News

Original Research: Open access.
Male and female contributions to diversity among birdwing butterfly images” by Jennifer Hoyal Cuthill et al. Communications Biology


Abstract

Male and female contributions to diversity among birdwing butterfly images

Machine learning (ML) newly enables tests for higher inter-species diversity in visible phenotype (disparity) among males versus females, predictions made from Darwinian sexual selection versus Wallacean natural selection, respectively.

Here, we use ML to quantify variation across a sample of > 16,000 dorsal and ventral photographs of the sexually dimorphic birdwing butterflies (Lepidoptera: Papilionidae).

Validation of image embedding distances, learnt by a triplet-trained, deep convolutional neural network, shows ML can be used for automated reconstruction of phenotypic evolution achieving measures of phylogenetic congruence to genetic species trees within a range sampled among genetic trees themselves.

Quantification of sexual disparity difference (male versus female embedding distance), shows sexually and phylogenetically variable inter-species disparity. 

Ornithoptera exemplify high embedded male image disparity, diversification of selective optima in fitted multi-peak OU models and accelerated divergence, with cases of extreme divergence in allopatry and sympathy.

However, genus Troides shows inverted patterns, including comparatively static male embedded phenotype, and higher female than male disparity – though within an inferred selective regime common to these females. Birdwing shapes and colour patterns that are most phenotypically distinctive in ML similarity are generally those of males.

However, either sex can contribute majoritively to observed phenotypic diversity among species.

Join our Newsletter
I agree to have my personal information transferred to AWeber for Neuroscience Newsletter ( more information )
Sign up to receive our recent neuroscience headlines and summaries sent to your email once a day, totally free.
We hate spam and only use your email to contact you about newsletters. You can cancel your subscription any time.