Affordable RFID loggers for monitoring animal movement, activity, and behaviour

Effective conservation management strategies require accurate information on the movement patterns and behaviour of wild animals. To collect these data, researchers are increasingly turning to remote sensing technology such as radio-frequency identification (RFID). RFID technology is a powerful tool that has been widely implemented in ecological research to identify and monitor unique individuals, but it bears a substantial price tag, restricting this technology to generously-funded disciplines and projects. To overcome this price hurdle, we provide detailed step-by-step instructions to source the components for, and construct portable RFID loggers in house, at a fraction of the cost (~5%) of commercial RFID units. Here, we assess the performance of these RFID loggers in the field and describe their application in two studies of Australian mammal species; monitoring nest-box use in the Northern quolls (Dasyurus hallucatus) and observing the foraging habits of quenda (Isoodon fusciventer) at feeding stations. The RFID loggers performed well, identifying quenda in >80% of visits, and facilitating the collection of individual-level behavioural data including common metrics such as emergence time, latency to approach, and foraging effort. While the technology itself is not novel, by lowering the cost per unit, our loggers enabled greater sample sizes, increasing statistical power from 0.09 to 0.75 in the quoll study. Further, we outline and provide solutions to the limitations of this design. Our RFID loggers proved an innovative method for collecting accurate behavioural and movement data. With their ability to successfully identify individuals, the RFID loggers described here can act as an alternative or complementary tool to camera traps. These RFID loggers can also be applied in a wide variety of projects which range from monitoring animal welfare or demographic traits to studies of anti-predator responses and animal personality, making them a valuable addition to the modern ecologists’ toolkit.

Predator suppression by a toxic invader does not cascade to prey due to predation by alternate predators

Invasive species often have catastrophic direct effects on native species through increased competition and predation. Less well understood are indirect, cascading effects across trophic levels. To reveal trophic disruptions caused by invasive species, it is necessary to document interactions between species at different trophic levels and across guilds. Here, we take this approach to quantify the impact of the invasion of cane toads at a riparian site in the Kimberley, northwest Australia. These toads are toxic to many native vertebrate predators and following toad arrival we observed the expected severe population decline in monitor lizards. Contrary to expectations however, this did not facilitate species in the next trophic level down: the abundance of their reptilian prey, as well as nest success of a songbird whose nests were predominantly depredated by monitor lizards, remained unchanged. Instead, detailed observations suggest a change in the suite of nest predators, with monitor lizards being replaced by other—mainly avian—predators, possibly reflecting their release from competitors that are more efficient nest predators. Hence, our findings highlight complex indirect effects of an invasive species across trophic levels and indicate that trophic cascades can go undetected when failing to include direct observations on predator–prey interactions.

Domain-Aware Neural Architecture Search for Classifying Animals in Camera Trap Images

Simple Summary

Camera traps acquire visual data in a non-disturbing and round-the-clock manner, so they are popular for ecological researchers observing wildlife. Each camera trap may record thousands of images of diverse species and bring about millions of images that need to be classified. Many methods have been proposed to classify camera trap images, but almost all methods rely on very deep convolutional neural networks that require intensive computational resources. Such resources may be unavailable and become formidable in cases where the surveillance area is large or becomes greatly expanded. We turn our attention to camera traps organized as groups, where each group produces images that are processed by the edge device with lightweight networks tailored for images produced by the group. To achieve this goal, we propose a method to automatically design networks deployable for edge devices with respect to given images. With the proposed method, researchers without any experience in designing neural networks can develop networks applicable for edge devices. Thus, camera trap images can be processed in a distributed manner through edge devices, lowering the costs of transferring and processing data accumulated at camera traps.

Abstract

Camera traps provide a feasible way for ecological researchers to observe wildlife, and they often produce millions of images of diverse species requiring classification. This classification can be automated via edge devices installed with convolutional neural networks, but networks may need to be customized per device because edge devices are highly heterogeneous and resource-limited. This can be addressed by a neural architecture search capable of automatically designing networks. However, search methods are usually developed based on benchmark datasets differing widely from camera trap images in many aspects including data distributions and aspect ratios. Therefore, we designed a novel search method conducted directly on camera trap images with lowered resolutions and maintained aspect ratios; the search is guided by a loss function whose hyper parameter is theoretically derived for finding lightweight networks. The search was applied to two datasets and led to lightweight networks tested on an edge device named NVIDIA Jetson X2. The resulting accuracies were competitive in comparison. Conclusively, researchers without knowledge of designing networks can obtain networks optimized for edge devices and thus establish or expand surveillance areas in a cost-effective way.

Turning ghosts into dragons: improving camera monitoring outcomes for a cryptic low-density Komodo dragon population in eastern Indonesia

Abstract Context Detection probability is a key attribute influencing population-level wildlife estimates necessary for conservation inference. Increasingly, camera traps are used to monitor threatened reptile populations and communities. Komodo dragon (Varanus komodoensis) populations have been previously monitored using camera traps; however, considerations for improving detection probability estimates for very low-density populations have not been well investigated. Aims Here we compare the effects of baited versus non-baited camera monitoring protocols to influence Komodo dragon detection and occupancy estimates alongside monitoring survey design and cost considerations for ongoing population monitoring within the Wae Wuul Nature Reserve on Flores Island, Indonesia. Methods Twenty-six camera monitoring stations (CMS) were deployed throughout the study area with a minimum of 400 m among CMS to achieve independent sampling units. Each CMS was randomly assigned as a baited or non-baited camera monitoring station and deployed for 6 or 30 daily sampling events. Key results Baited camera monitoring produced higher site occupancy estimates with reduced variance. Komodo dragon detection probability estimates were 0.15 ± 0.092–0.22 (95% CI), 0.01 ± 0.001–0.03, and 0.03 ± 0.01–0.04 for baited (6 daily survey sampling events), unbaited (6 daily survey sampling events) and long-unbaited (30 daily survey sampling events) sampling durations respectively. Additionally, the provision of baited lures at cameras had additional benefits for Komodo detection, survey design and sampling effort costs. Conclusions Our study indicated that baited cameras provide the most effective monitoring method to survey low-density Komodo dragon populations in protected areas on Flores. Implications We believe our monitoring approach now lends itself to evaluating population responses to ecological and anthropogenic factors, hence informing conservation efforts in this nature reserve.