Artemisia pollen dataset for exploring the potential ecological indicators in deep time

Abstract

Abstract. Artemisia, along with Chenopodiaceae, is the dominant component growing in the desert and dry grassland of the Northern Hemisphere. Artemisia pollen with its high productivity, wide distribution, and easy identification is usually regarded as an eco-indicator for assessing aridity and distinguishing grassland from desert vegetation in terms of the pollen relative abundance ratio of Chenopodiaceae/Artemisia (C/A). Nevertheless, divergent opinions on the degree of aridity evaluated by Artemisia pollen have been circulating in the palynological community for a long time. To solve the confusion, we first selected 36 species from nine clades and three outgroups of Artemisia based on the phylogenetic framework, which attempts to cover the maximum range of pollen morphological variation. Then, sampling, experiments, photography, and measurements were taken using standard methods. Here, we present pollen datasets containing 4018 original pollen photographs, 9360 pollen morphological trait measurements, information on 30 858 source plant occurrences, and corresponding environmental factors. Hierarchical cluster analysis on pollen morphological traits was carried out to subdivide Artemisia pollen into three types. When plotting the three pollen types of Artemisia onto the global terrestrial biomes, different pollen types of Artemisia were found to have different habitat ranges. These findings change the traditional concept of Artemisia being restricted to arid and semi-arid environments. The data framework that we designed is open and expandable for new pollen data of Artemisia worldwide. In the future, linking pollen morphology with habitat via these pollen datasets will create additional knowledge that will increase the resolution of the ecological environment in the geological past. The Artemisia pollen datasets are freely available at Zenodo (https://doi.org/10.5281/zenodo.6900308; Lu et al., 2022).

Weakly Supervised Collaborative Learning for Airborne Pollen Segmentation and Classification from SEM Images

“…SEM images can be used to improve the performance of pollen identification in practice [ 20 , 21 , 22 , 23 , 24 , 25 ], since the high resolution of SEM unlocks the potential to provide the obvious differentiation of the pollen grains for the experts (as shown in Table 1 ). In our study, we obtained 1324 SEM pollen images in total (805 Cupressaceae, 248 Fraxinus and 271 Ginkgo) from Beijing Meteorological Center, which served as the data for our automatic pollen identification task.…”

“…Therefore, SEM images have exhibited significant potential to enhance the ability to accurately identify airborne pollens in an automatic manner for the palynology community [ 19 ]. Currently, some preliminary research works on SEM-based automatic pollen identification have been reported [ 20 , 21 , 22 , 23 , 24 , 25 ]. An early example of an SEM-image-based method was [ 20 ], in which the authors extracted the texture features to train a Fisher linear discriminant classifier.…”

“…Yang et al [ 22 ] first employed the R-CNN to detect pollen grains in SEM images, then AlexNet, GoogLeNet, and ResNet50 were trained for banana shrub and Papaver rhoeas pollen identification. To subdivide Artemisia pollen into three types, hierarchical clustering analysis on the pollen’s morphological features was carried out by Lu et al [ 23 ]. Polling et al [ 24 ] trained VGG16 to increase the taxonomic accuracy for Urtica and Parietaria.…”

The potential of Artemisia spp. plant extracts and endophytic bacteria to increase plant productivity: A review

“…The ability of a species to adapt and survive in both warm and cool environments provides a highly valuable defence mechanism against extinction. The distribution and vegetative and reproductive development of these plants are influenced by geographical location, local climate, and prevailing meteorological conditions (Anibogwu et al, 2021;Lu et al, 2022).…”