Seeds of exotic plants transported with imported goods pose a risk of alien species invasion in cross-border transportation and logistics. It is critical to develop stringent inspection and quarantine protocols with active management to control the import and export accompanied by exotic seeds. As a result, a method for promptly identifying exotic plant seeds is urgently needed. In this study, we built a database containing 3000 images of seeds of 12 invasive plants and proposed an improved YOLOv5 target detection algorithm that incorporates a channel attention mechanism. Given that certain seeds in the same family and genus are very similar in appearance and are thus difficult to differentiate, we improved the size model of the initial anchor box to converge better; moreover, we introduce three attention modules, SENet, CBAM, and ECA-Net, to enhance the extraction of globally important features while suppressing the weakening of irrelevant features, thereby effectively solving the problem of automated inspection of similar species. Experiments on an invasive alien plant seed data set reveal that the improved network model fused with ECA-Net requires only a small increase in parameters when compared to the original YOLOv5 network model and achieved greater classification and detection accuracy without affecting detection speed.

The interplay between historical biogeography and environmental selection shapes the genetic architecture of species; however, their relative contributions in widespread and ecologically important tree species remain poorly understood. In the Sino-Japanese Floristic Region, the East China Sea has alternately acted as a barrier and a corridor during glacial-interglacial cycles, influencing species isolation and contact. However, the extent to which these historical dynamics, along with environmental gradients, have driven adaptive evolution in dominant forest trees remains unresolved. In the present study, we integrated phylogeographic reconstruction and landscape genomics based on whole-genome resequencing data from 171 individuals across 35 populations to investigate the evolutionary history and adaptive mechanisms of Quercus gilva, a keystone evergreen oak, in East Asian subtropical forests. Population genomic analyses revealed two deeply divergent genetic groups: the China group and the Japan–Korea group, and demographic modeling indicated that their divergence dates back to the Miocene epoch. The relatively high genomic diversity of Q. gilva may result from the absence of severe genetic bottlenecks throughout its evolutionary history, multiple microrefugia during the glacial periods, and postglacial secondary contact. Notably, Quaternary glacial cycles repeatedly facilitated gene flow and admixture between these groups via exposed land bridges. Landscape genomic analyses further demonstrated that adaptive divergence in Q. gilva is shaped by both geographic isolation and environmental gradients, with annual precipitation emerging as the primary climatic driver. This study provides a genome-wide perspective on how historical biogeography and environmental selection interact to shape the genetic architecture of a dominant subtropical evergreen forest species, offering novel insights into the evolutionary dynamics and adaptive evolution across East Asian biodiversity hotspots.