用深度学习分析鸟类形态演化，自动捕捉复杂特征与进化规律
Quantifying Avian Morphological Evolution through Deep Representation Learning
- 用ResNet34提取1万+鸟种图像特征，构建无标记点的形态空间
- 嵌入向量中蕴含显著系统发育信号，与生态形态特征强相关
- 发现白垩纪末大灭绝后形态差异快速扩张，支持适应辐射假说
生物形态演化与生态适应和物种存续密切相关，但传统几何形态测量依赖人工标记点，受限于解剖同源性要求，难以量化羽毛、纹理等非刚性特征。为此，我们提出一种基于深度学习的可扩展、无标记点形态测量框架。通过在超过1万种鸟类图像上训练的ResNet34提取高维特征向量，将原始视觉语义投影至高维形态空间。即使无先验分类知识，该视觉形态空间仍能自然恢复经典分类层级，并有效捕捉同源与趋同现象。分析显示，网络嵌入中存在高度显著的系统发育信号，主成分与已知生态及形态特征强烈相关。进一步采用新型球面祖先状态重建算法，揭示了白垩纪-古近纪灭绝事件后形态差异呈现显著的‘早期爆发’模式，支持适应辐射的空位填充假说。
原文摘要 · Abstract (English)
The evolution of biological morphology is fundamentally linked to ecological adaptation and species survival, yet traditional morphological evolution relies on landmark-based geometric morphometrics, a process constrained by subjective manual annotation, strict requirements for anatomical homology, and an inability to easily quantify complex, non-rigid traits such as plumage and texture. To overcome these limitations, we propose a scalable, landmark-free morphometric framework driven by deep learning. By extracting high-dimensional feature vectors from a Convolutional Neural Network (ResNet34) trained on images of over 10,000 bird species, we project raw visual semantics into a high-dimensional morphospace. Even without a priori taxonomic knowledge, this visual morphospace naturally recovers classical hierarchical taxonomy and effectively captures both homology and convergence. Analyses reveal a highly significant phylogenetic signal within the network's embeddings, with principal components correlating strongly with established ecological and morphological traits. Furthermore, by implementing a novel spherical Ancestral State Reconstruction algorithm, we uncover a pronounced "early-burst" pattern of disparity following the K-Pg mass extinction, supporting the niche-filling hypothesis of adaptive radiation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。