Deep-learning-based pan-phenomic data reveals the explosive evolution of avian visual disparity

2026-02-03

AI Summary

Traditional morphological analyses are often constrained by subjectivity, limiting their ability to objectively uncover patterns of avian morphological evolution. This study pioneers the integration of deep learning embeddings into panoramic phenotypic evolutionary analysis by applying a ResNet34 model to over ten thousand bird images. High-dimensional phenotypic embedding spaces were constructed from fully connected layer weights and evaluated for biological relevance using phylogenetic comparative methods and adversarial examples. The resulting embedding space effectively captures overall body shape rather than mere textural features, revealing a significant positive correlation between morphological disparity and species richness. Furthermore, the analysis uncovers an “early burst” of rapid visual morphological diversification in birds following the Cretaceous–Paleogene (K–Pg) mass extinction, offering a novel perspective on macroevolutionary dynamics.

Technology Category

• Machine Learning: Evolutionary Learning
• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Lexical Semantics and Morphology

Application Category

• Web Mining and Content Analysis: Models for Web evolution
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

The evolution of biological morphology is critical for understanding the diversity of the natural world, yet traditional analyses often involve subjective biases in the selection and coding of morphological traits. This study employs deep learning techniques, utilising a ResNet34 model capable of recognising over 10,000 bird species, to explore avian morphological evolution. We extract weights from the model's final fully connected (fc) layer and investigate the semantic alignment between the high-dimensional embedding space learned by the model and biological phenotypes. The results demonstrate that the high-dimensional embedding space encodes phenotypic convergence. Subsequently, we assess the morphological disparity among various taxa and evaluate the association between morphological disparity and species richness, demonstrating that species richness is the primary driver of morphospace expansion. Moreover, the disparity-through-time analysis reveals a visual"early burst"after the K-Pg extinction. While mainly aimed at evolutionary analysis, this study also provides insights into the interpretability of Deep Neural Networks. We demonstrate that hierarchical semantic structures (biological taxonomy) emerged in the high-dimensional embedding space despite being trained on flat labels. Furthermore, through adversarial examples, we provide evidence that our model in this task can overcome texture bias and learn holistic shape representations (body plans), challenging the prevailing view that CNNs rely primarily on local textures.

Problem

• morphological evolution
• phenotypic disparity
• avian diversity
• subjective bias
• morphospace

Innovation

• deep learning
• morphological disparity
• phenotypic convergence
• adversarial examples
• embedding space