Segmenting biological specimens from photos to understand the evolution of UV plumage in passerine birds

Ultraviolet (UV) colouration is thought to be an important signalling mechanism in many bird species, yet broad insights regarding the prevalence of UV plumage colouration and the factors promoting its evolution are currently lacking. Here, we develop a novel image segmentation pipeline based on deep learning that considerably outperforms classical (i.e. non-deep learning) segmentation methods, and use this to extract accurate information on whole-body plumage colouration from photographs of >24,000 museum specimens covering >4,500 species of passerine birds. Our results demonstrate that UV reflectance, particularly as a component of other colours, is widespread across the passerine radiation but is strongly phylogenetically conserved. We also find clear evidence in support of the role of light environment in promoting the evolution of UV plumage colouration, and a weak trend towards higher UV plumage reflectance among bird species with ultraviolet rather than violet-sensitive visual systems. Overall, our study provides important broad-scale insight into an enigmatic component of avian colouration, as well as demonstrating that deep learning has considerable promise for allowing new data to be bought to bear on long-standing questions in ecology and evolution.