Examining the Role of Climate in Shaping Wing Morphology in Erebia butterflies

Abstract

Understanding how environmental gradients shape morphological variation is a central question that links to ecology, evolution, and species responses to climate change. We investigated the relationship between climate and the morphology of Erebia butterflies. We combined species distribution modelling(SDM) and multidimensional morphospace analysis. We quantified wing morphology by extracting feature embeddings of segmented wings by a fine-tuned Segment Anything model (SAM2), which gave us a representation of shape and pattern variation across dorsal and ventral surfaces of forewings and hindwings. Principal component analysis (PCA) revealed morphological differentiation between species. Forewings showed large interspecific separation, particularly along PC1, with low overlapping, which indicates that there is pronounced divergence in traits associated with flight and environmental adaptation. In contrast, hindwings showed large overlap and weaker differentiation, suggesting stronger functional constraints. Differences between dorsal and ventral surfaces further highlighted distinct ecological roles: dorsal surfaces showed broader environmental sensitivity, while ventral surfaces exhibited more selective responses. Climatic variables significantly influenced morphological variation across all wing components. Precipitation seasonality (bio16, bio18, bio19), temperature extremes (bio10, bio11), and elevation (bio20) emerged as key drivers, while short-term extremes such as precipitation of the wettest month (bio13) showed limited or inconsistent effects. Axis-specific analyses further showed that PC1 captured a major gradient combining temperature and precipitation effects, whereas PC2 and PC3 reflected seasonal and thermal variability. Comparison with SDM results revealed partial decoupling between environmental drivers of species distribution and morphological variation, suggesting that factors determining habitat suitability do not always directly translate into phenotypic differentiation. Overall, this study demonstrates that wing morphology in Erebia butterflies reflects integrated climatic gradients and functional specialization within the wing system. By combining deep learning–based feature extraction with ecological modeling, this work provides a scalable framework for studying climate-driven morphological variation and offers insights into how species may respond to ongoing environmental change.