Sky islands of Southwest China. II: Unraveling hidden species diversity of talpid moles using phylogenomics and skull-based deep learning

Abstract

The sky islands of Southwest China, characterized by dramatic topographical and climatic variations, are prominent hotspots of biodiversity and endemism. Organisms inhabiting middle-to-high elevation habitats in this region are geographically isolated within distinct mountain chains, which over geological time have been subjected to isolation-by-distance and isolation-by-environment. These processes have led to profound allopatric diversification and strong phylogeographic structuring, resulting in a plethora of genetically distinct cryptic species, as is becoming increasingly evident for many small mammal families. However, morphological conservatism can pose significant challenges in delineating these clades within species complexes. In this study, we leverage artificial intelligence technologies to unravel the hidden species diversity of moles (family Talpidae) in Southwest Chinas sky islands. We first employed ultraconserved elements (UCEs) to investigate the evolutionary history of talpid moles, conducted molecular species delimitation using mitochondrial and multi-locus genes, and utilized both traditional and geometric morphometrics to examine their morphological disparity. To address the challenges of morphology based cryptic species identification, we developed a deep learning Hierarchical Identification of Species NETwork (HIS-NET) to create an image-based model that analyzes four different views of the skull/mandible to distinguish genera and species hierarchically. HIS-NET not only achieved expert-level accuracy in species identification but also effectively distinguished between cryptic and known species, aiding in the identification of key morphological variation intervals. Our results support the recognition of allopatrically distributed taxa in Euroscaptor and Parascaptor as full species, thereby confirming that species diversity in this region remains underestimated. Beyond advancing our understanding of speciation in this unique and fragile ecosystem, our study serves as a proof-of-concept, demonstrating the power of deep learning in unraveling hidden biodiversity within this and other species complexes.