With the increase in the digitization efforts of herbarium collections worldwide, dataset repositories such as iDigBio and GBIF now have hundreds of thousands of herbarium sheet images ready for exploration. Although this serves as a new source of plant leaves data, herbarium datasets have an inherent challenge to deal with the sheets containing other non-plant objects such as color charts, barcodes, and labels. Even for the plant part itself, a combination of different overlapping, damaged, and intact individual leaves exist together with other plant organs such as stems and fruits, which increases the complexity of leaf trait extraction and analysis. Focusing on segmentation and trait extraction on individual intact herbarium leaves, this study proposes a pipeline consisting of deep learning semantic segmentation model (DeepLabv3+), connected component analysis, and a single-leaf classifier trained on binary images to automate the extraction of an intact individual leaf with phenotypic traits. The proposed method achieved a higher F1-score for both the in-house dataset (96%) and on a publicly available herbarium dataset (93%) compared to object detection-based approaches including Faster R-CNN and YOLOv5. Furthermore, using the proposed approach, the phenotypic measurements extracted from the segmented individual leaves were closer to the ground truth measurements, which suggests the importance of the segmentation process in handling background noise. Compared to the object detection-based approaches, the proposed method showed a promising direction toward an autonomous tool for the extraction of individual leaves together with their trait data directly from herbarium specimen images.
Biological invasion is a serious threat to biodiversity and ecosystem function in nature reserves. However, the knowledge of the spatial patterns and underlying mechanisms of plant invasions in nature reserves is still limited. Based on a recent dataset on both invasive and native plants in 67 nature reserves of China, we used correlation, regression, and variation partitioning methods to statistically assess the relative roles of the “human activity,” “biotic acceptance,” and “environmental heterogeneity” hypotheses in explaining the geographic pattern of plant invasion. A total of 235 invasive plant species were compiled from 67 nature reserves. The high explanatory power of the human activity variables supported the human activity hypothesis. The biotic acceptance hypothesis was weakly supported since no significant correlations between climatic variables and invasion levels were found when the effects of the other factors were controlled. The environmental heterogeneity hypothesis was partially supported, since the number of native plants, representing environmental heterogeneity at fine-scale explained remarkable proportion of spatial variance of invasive plants but not that of the proportion of invasive plants. We predict that nature reserves with high plant diversity affected by rapid economic development and increasing temperature will face a serious threat of exotic plant invasion. In conclusion, our results provide crucial clues for understanding geographic variance of plant invasion in China’s nature reserves and spatial risk assessment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.