Marine megafauna are difficult to observe and count because many species travel widely and spend large amounts of time submerged. As such, management programmes seeking to conserve these species are often hampered by limited information about population levels. Unoccupied aircraft systems (UAS, aka drones) provide a potentially useful technique for assessing marine animal populations, but a central challenge lies in analysing the vast amounts of data generated in the images or video acquired during each flight. Neural networks are emerging as a powerful tool for automating object detection across data domains and can be applied to UAS imagery to generate new population‐level insights. To explore the utility of these emerging technologies in a challenging field setting, we used neural networks to enumerate olive ridley turtles Lepidochelys olivacea in drone images acquired during a mass‐nesting event on the coast of Ostional, Costa Rica. Results revealed substantial promise for this approach; specifically, our model detected 8% more turtles than manual counts while effectively reducing the manual validation burden from 2,971,554 to 44,822 image windows. Our detection pipeline was trained on a relatively small set of turtle examples (N = 944), implying that this method can be easily bootstrapped for other applications, and is practical with real‐world UAS datasets. Our findings highlight the feasibility of combining UAS and neural networks to estimate population levels of diverse marine animals and suggest that the automation inherent in these techniques will soon permit monitoring over spatial and temporal scales that would previously have been impractical.
Seabirds are integral components of marine ecosystems and, with many populations globally threatened, there is a critical need for effective and scalable seabird monitoring strategies. Many seabird species nest in burrows, which can make traditional monitoring methods costly, infeasible, or damaging to nesting habitats. Traditional burrow occupancy surveys, where possible, can occur infrequently and therefore lead to an incomplete understanding of population trends. For example, in Oregon, during the last three decades there have been large changes in the abundance of Leach’s storm-petrels (Hydrobates leucorhoa), which included drastic declines at some colonies. Unfortunately, traditional monitoring failed to capture the timing and magnitude of change, limiting managers’ ability to determine causes of the decline and curtailing management options. New, easily repeatable methods of quantifying relative abundance are needed. For this study, we tested three methods of remote monitoring: passive acoustic monitoring, time-lapse cameras, and radar. Abundance indices derived from acoustics and imagery: call rates, acoustic energy, and counts were significantly related to traditional estimates of burrow occupancy of Leach’s storm-petrels. Due to sampling limitations, we were unable to compare radar to burrow occupancy. Image counts were significantly correlated with all other indices, including radar, while indices derived from acoustics and radar were not correlated. Acoustic data likely reflect different aspects of the population and hold the potential for the further development of indices to disentangle phenology, attendance of breeding birds, and reproductive success. We found that image counts are comparable with standard methods (e.g., radar) in producing annual abundance indices. We recommend that managers consider a sampling scheme that incorporates both acoustics and imaging, but for sites inaccessible to humans, radar remains the sole option. Implementation of acoustic and camera based monitoring programs will provide much needed information for a vulnerable group of seabirds.
Due to rapidly changing global environmental conditions, many animals are now experiencing concurrent changes in both resource availability and the foraging cues associated with finding those resources. By employing flexible, plastic foraging strategies that use different types of environmental foraging cues, animals could adapt to these novel future environments. To evaluate the extent to which such flexibility and plasticity exist, we analyzed a large dataset of a clade (Sulidae; the boobies) of widespread aerial tropical predators that feed in highly variable marine habitats. These surface foragers are typical of many ocean predators that face dynamic and patchy foraging environments and use a combination of static and ephemeral oceanographic features to locate prey. We compared foraging habitats and behaviors of four species at seven colonies in the eastern and central Pacific Ocean that varied greatly in depth, topography, and primary productivity. Foraging behaviors, recorded by GPS‐tracking tags, were compared to remotely sensed environmental features, to characterize habitat‐behavior interactions. K‐means clustering grouped environmental characteristics into five habitat clusters across the seven sites. We found that boobies relied on a combination of static and ephemeral cues, especially depth, chlorophyll‐a concentrations, and sea surface height (ocean surface topography). Notably, foraging behaviors were strongly predicted by local oceanographic habitats across species and sites, suggesting a high degree of behavioral plasticity in use of different foraging cues. Flexibility allows these top predators to adapt to, and exploit, static and ephemeral oceanic features. Plasticity may well facilitate these species, and other similarly dynamic foragers, to cope with increasingly changing environmental conditions.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.