Abstract Pollinating insects are in decline globally, threatening pollination services and driving a growing interest in pollinator monitoring and conservation. However, the implementation of conservation programs for these insects is often hindered by labor‐intensive monitoring methods and insufficient data to assess population trends. We detail a method for surveying and censusing ground nesting bee aggregations, pairing automated UAV image capture with a custom trained computer vision‐based object detection workflow using the YOLOv5m architecture. To highlight the ease of application and accuracy of the workflow, we surveyed a roughly 65 m 2 portion of a large Colletes inaequalis nesting aggregation. We compared the efficiency and performance of our model to manual counts of a technician. Our model detected the location of 1094 nests, representing 88% of the nests present in our test dataset, and a true‐positive rate of 97%. Adjusting for error, our model estimated a total of 1250 nests across the study site, comparable to the total estimated from a manual count of 1259 nests. Our model detected nests 20 times faster than the manual counts while mapping the aggregation with millimetre accuracy. Spatial analyses show that bee nest density was heterogeneous, with dense spatially clustered regions comprised of upwards of 60 nests per m 2 . Synthesis and applications . Our novel application of UAV imagery and object detection models for mapping and censusing ground nesting bee aggregations represents a rapid, cost‐effective solution for overcoming limitations in traditional manual methods. This workflow has applications for bee conservation, management and research such as monitoring bee nesting populations before and after habitat restoration or habitat disruption events, quantifying the impacts of management strategies or repeat censusing of populations over time to determine nesting population demographics and early identification of local extirpation risk. Our workflow generates essential data with the high throughput required to help inform the conservation decisions needed to stem global bee declines.
Mueller et al. (Thu,) studied this question.