Dorsoventral comparison of intraspecific variations in the butterfly wing pattern using a convolutional neural network

Butterfly wing patterns exhibit notable differences between the dorsal and ventral surfaces, and morphological analyses of them have provided insights into the ecological and behavioural characteristics of wing colour patterns. Conventional methods for dorsoventral comparisons are constrained by the need for homologous patches or shared features between two surfaces, limiting their applicability across species. We used a convolutional neural network (CNN)-based analysis, which can compare images of the two surfaces without focusing on homologous patches or features, to detect dorsoventral bias in intraspecific variations: sexual dimorphism and female-limited mimetic polymorphism (FMP). Using specimen images of 29 species, we first showed that the level of sexual dimorphism calculated by CNN-based analysis corresponded well with traditional assessments of sexual dissimilarity, demonstrating the validity of the method. Dorsal biases were widely detected in sexual dimorphism, suggesting that the conventional hypothesis of dorsally biased sexual selection can be supported in a broader range of species. In contrast, the FMP showed no significant bias, indicating the importance of both surfaces in mimicry. Our study demonstrates the potential versatility of CNN in comparing wing patterns between the two surfaces, while providing broader insights into the relationship between dorsoventrally different selections and dorsoventral biases in intraspecific variations.