YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images.

Develoment of image recognition AI algorithms for flower-visiting arthropods has the potential to revolutionize the way we monitor pollinators. Ecologists need light-weight models that can be deployed in a field setting and can classify with high accuracy. We tested the performance of three deep learning light-weight models, YOLOv5nano, YOLOv5small, and YOLOv7tiny, at object recognition and classification in real time on eight groups of flower-visiting arthropods using open-source image data. These eight groups contained four orders of insects that are known to perform the majority of pollination services in Europe (Hymenoptera, Diptera, Coleoptera, Lepidoptera) as well as other arthropod groups that can be seen on flowers but are not typically considered pollinators (e.g., spiders-Araneae). All three models had high accuracy, ranging from 93 to 97%. Intersection over union (IoU) depended on the relative area of the bounding box, and the models performed best when a single arthropod comprised a large portion of the image and worst when multiple small arthropods were together in a single image. The model could accurately distinguish flies in the family Syrphidae from the Hymenoptera that they are known to mimic. These results reveal the capability of existing YOLO models to contribute to pollination monitoring.

Intensive grazing alters the diversity, composition and structure of plant-pollinator interaction networks in Central European grasslands.

Complex socio-economic, political and demographic factors have driven the increased conversion of Europe's semi-natural grasslands to intensive pastures. This trend is particularly strong in some of the most biodiverse regions of the continent, such as Central and Eastern Europe. Intensive grazing is known to decrease species diversity and alter the composition of plant and insect communities. Comparatively little is known, however, about how intensive grazing influences plant functional traits related to pollination and the structure of plant-pollinator interactions. In traditional hay meadows and intensive pastures in Central Europe, we contrasted the taxonomic and functional group diversity and composition, the structure of plant-pollinator interactions and the roles of individual species in networks. We found mostly lower taxonomic and functional diversity of plants and insects in intensive pastures, as well as strong compositional differences among the two grassland management types. Intensive pastures were dominated by a single plant with a specialized flower structure that is only accessible to a few pollinator groups. As a result, intensive pastures have lower diversity and specificity of interactions, higher amount of resource overlap, more uniform interaction strength and lower network modularity. These findings stand in contrast to studies in which plants with more generalized flower traits dominated pastures. Our results thus highlight the importance of the functional traits of dominant species in mediating the consequences of intensive pasture management on plant-pollinator networks. These findings could further contribute to strategies aimed at mitigating the impact of intensive grazing on plant and pollinator communities.

Effects of different types of low-intensity management on plant-pollinator interactions in Estonian grasslands.

In the face of global pollinator decline, extensively managed grasslands play an important role in supporting stable pollinator communities. However, different types of extensive management may promote particular plant species and thus particular functional traits. As the functional traits of flowering plant species (e.g., flower size and shape) in a habitat help determine the identity and frequency of pollinator visitors, they can also influence the structures of plant-pollinator interaction networks (i.e., pollination networks). The aim of this study was to examine how the type of low-intensity traditional management influences plant and pollinator composition, the structure of plant-pollinator interactions, and their mediation by floral and insect functional traits. Specifically, we compared mown wooded meadows to grazed alvar pastures in western Estonia. We found that both management types fostered equal diversity of plants and pollinators, and overlapping, though still distinct, plant and pollinator compositions. Wooded meadow pollination networks had significantly higher connectance and specialization, while alvar pasture networks achieved higher interaction diversity at a standardized sampling of interactions. Pollinators with small body sizes and short proboscis lengths were more specialized in their preference for particular plant species and the specialization of individual pollinators was higher in alvar pastures than in wooded meadows. All in all, the two management types promoted diverse plant and pollinator communities, which enabled the development of equally even and nested pollination networks. The same generalist plant and pollinator species were important for the pollination networks of both wooded meadows and alvar pastures; however, they were complemented by management-specific species, which accounted for differences in network structure. Therefore, the implementation of both management types in the same landscape helps to maintain high species and interaction diversity.

Land use and pollinator dependency drives global patterns of pollen limitation in the Anthropocene.

Land use change, by disrupting the co-evolved interactions between plants and their pollinators, could be causing plant reproduction to be limited by pollen supply. Using a phylogenetically controlled meta-analysis on over 2200 experimental studies and more than 1200 wild plants, we ask if land use intensification is causing plant reproduction to be pollen limited at global scales. Here we report that plants reliant on pollinators in urban settings are more pollen limited than similarly pollinator-reliant plants in other landscapes. Plants functionally specialized on bee pollinators are more pollen limited in natural than managed vegetation, but the reverse is true for plants pollinated exclusively by a non-bee functional group or those pollinated by multiple functional groups. Plants ecologically specialized on a single pollinator taxon were extremely pollen limited across land use types. These results suggest that while urbanization intensifies pollen limitation, ecologically and functionally specialized plants are at risk of pollen limitation across land use categories.

A review of European studies on pollination networks and pollen limitation, and a case study designed to fill in a gap.

Anthropogenic environmental change disrupts interactions between plants and their animal pollinators. To assess the importance of different drivers, baseline information is needed on interaction networks and plant reproductive success around the world. We conducted a systematic literature review to determine the state of our knowledge on plant-pollinator interactions and the ecosystem services they provide for European ecosystems. We focussed on studies that published information on plant-pollinator networks, as a community-level assessment of plant-pollinator interactions and pollen limitation, which assesses the degree to which plant reproduction is limited by pollinator services. We found that the majority of our knowledge comes from Western Europe, and thus there is a need for baseline assessments in the traditional landscapes of Eastern Europe. To address this data gap, we quantified plant-pollinator interactions and conducted breeding system and pollen supplementation experiments in a traditionally managed mountain meadow in the Western Romanian Carpathians. We found the Romanian meadow to be highly diverse, with a healthy plant-pollinator network. Despite the presence of many pollinator-dependent plant species, there was no evidence of pollen limitation. Our study is the first to provide baseline information for a healthy meadow at the community level on both plant-pollinator interactions and their relationship with ecosystem function (e.g. plant reproduction) in an Eastern European country. Alongside the baseline data, we also provide recommendations for future research, and the methodological information needed for the continued monitoring and management of Eastern European meadows.