Flower Mapping in Grasslands With Drones and Deep Learning.

Manual assessment of flower abundance of different flowering plant species in grasslands is a time-consuming process. We present an automated approach to determine the flower abundance in grasslands from drone-based aerial images by using deep learning (Faster R-CNN) object detection approach, which was trained and evaluated on data from five flights at two sites. Our deep learning network was able to identify and classify individual flowers. The novel method allowed generating spatially explicit maps of flower abundance that met or exceeded the accuracy of the manual-count-data extrapolation method while being less labor intensive. The results were very good for some types of flowers, with precision and recall being close to or higher than 90%. Other flowers were detected poorly due to reasons such as lack of enough training data, appearance changes due to phenology, or flowers being too small to be reliably distinguishable on the aerial images. The method was able to give precise estimates of the abundance of many flowering plant species. In the future, the collection of more training data will allow better predictions for the flowers that are not well predicted yet. The developed pipeline can be applied to any sort of aerial object detection problem.

The effectiveness of flower strips and hedgerows on pest control, pollination services and crop yield: a quantitative synthesis.

Floral plantings are promoted to foster ecological intensification of agriculture through provisioning of ecosystem services. However, a comprehensive assessment of the effectiveness of different floral plantings, their characteristics and consequences for crop yield is lacking. Here we quantified the impacts of flower strips and hedgerows on pest control (18 studies) and pollination services (17 studies) in adjacent crops in North America, Europe and New Zealand. Flower strips, but not hedgerows, enhanced pest control services in adjacent fields by 16% on average. However, effects on crop pollination and yield were more variable. Our synthesis identifies several important drivers of variability in effectiveness of plantings: pollination services declined exponentially with distance from plantings, and perennial and older flower strips with higher flowering plant diversity enhanced pollination more effectively. These findings provide promising pathways to optimise floral plantings to more effectively contribute to ecosystem service delivery and ecological intensification of agriculture in the future.

The interplay of landscape composition and configuration: new pathways to manage functional biodiversity and agroecosystem services across Europe.

Managing agricultural landscapes to support biodiversity and ecosystem services is a key aim of a sustainable agriculture. However, how the spatial arrangement of crop fields and other habitats in landscapes impacts arthropods and their functions is poorly known. Synthesising data from 49 studies (1515 landscapes) across Europe, we examined effects of landscape composition (% habitats) and configuration (edge density) on arthropods in fields and their margins, pest control, pollination and yields. Configuration effects interacted with the proportions of crop and non-crop habitats, and species' dietary, dispersal and overwintering traits led to contrasting responses to landscape variables. Overall, however, in landscapes with high edge density, 70% of pollinator and 44% of natural enemy species reached highest abundances and pollination and pest control improved 1.7- and 1.4-fold respectively. Arable-dominated landscapes with high edge densities achieved high yields. This suggests that enhancing edge density in European agroecosystems can promote functional biodiversity and yield-enhancing ecosystem services.

High effectiveness of tailored flower strips in reducing pests and crop plant damage.

Providing key resources to animals may enhance both their biodiversity and the ecosystem services they provide. We examined the performance of annual flower strips targeted at the promotion of natural pest control in winter wheat. Flower strips were experimentally sown along 10 winter wheat fields across a gradient of landscape complexity (i.e. proportion non-crop area within 750 m around focal fields) and compared with 15 fields with wheat control strips. We found strong reductions in cereal leaf beetle(CLB) density (larvae: 40%; adults of the second generation: 53%) and plant damage caused by CLB (61%) in fields with flower strips compared with control fields. Natural enemies of CLB were strongly increased in flower strips and in part also in adjacent wheat fields. Flower strip effects on natural enemies, pests and crop damage were largely independent of landscape complexity(8-75% non-crop area). Our study demonstrates a high effectiveness of annual flower strips in promoting pest control, reducing CLB pest levels below the economic threshold. Hence, the studied flower strip offers a viable alternative to insecticides. This highlights the high potential of tailored agri-environment schemes to contribute to ecological intensification and may encourage more farmers to adopt such schemes.