Comparing the cost-effectiveness of drones, camera trapping and passive acoustic recorders in detecting changes in koala occupancy

Quantifying the cost-effectiveness of alternative sampling methods is crucial for efficient biodiversity monitoring and detection of population trends. In this study, we compared the cost-effectiveness of three novel sampling methods for detecting changes in koala (Phascolarctos cinereus) occupancy: thermal drones, passive acoustic recorders and camera trapping. Specifically, we fitted single-season occupancy-detection models to data recorded from 46 sites in eight bioregions of New South Wales, Australia, between 2018 and 2022. We explored the effect of weather variables on daily detection probability for each method and, using these estimates, calculated the statistical power to detect 30%, 50% and 80% declines in koala occupancy. We calculated power for different combinations of sites (1-200) and repeat surveys (2-40) and developed a cost model that found the cheapest survey design that achieved 80% power to detect change. On average, detectability of koalas was highest with one 24-h period of acoustic surveys (0.32, 95% CI's: 0.26, 0.39) compared to a 25-ha flight of drone surveys (0.28, 95% 0.15, 0.48) or a 24-h period of camera trapping consisting of six cameras (0.019, 95% CI's: 0.014, 0.025). We found a negative quadratic relationship between detection probability and air temperature for all three methods. Our power and cost analysis suggested that 148 sites surveyed with acoustic recorders deployed for 14 days would be the cheapest method to sufficiently detect a 30% decline in occupancy with 80% power. We recommend passive acoustic recorders as the most efficient sampling method for monitoring koala occupancy compared to cameras or drones. Further comparative studies are needed to compare the relative effectiveness of these methods and others when the monitoring objective is to detect change in koala abundance over time.

Systematic review of machine learning methods applied to ecoacoustics and soundscape monitoring

Soundscape ecology is a promising area that studies landscape patterns based on their acoustic composition. It focuses on the distribution of biotic and abiotic sounds at different frequencies of the landscape acoustic attribute and the relationship of said sounds with ecosystem health metrics and indicators (e.g., species richness, acoustic biodiversity, vectors of structural change, gradients of vegetation cover, landscape connectivity, and temporal and spatial characteristics). To conduct such studies, researchers analyze recordings from Acoustic Recording Units (ARUs). The increasing use of ARUs and their capacity to record hours of audio for months at a time have created a need for automatic processing methods to reduce time consumption, correlate variables implicit in the recordings, extract features, and characterize sound patterns related to landscape attributes. Consequently, traditional machine learning methods have been commonly used to process data on different characteristics of soundscapes, mainly the presence-absence of species. In addition, it has been employed for call segmentation, species identification, and sound source clustering. However, some authors highlight the importance of the new approaches that use unsupervised deep learning methods to improve the results and diversify the assessed attributes. In this paper, we present a systematic review of machine learning methods used in the field of ecoacoustics for data processing. It includes recent trends, such as semi-supervised and unsupervised deep learning methods. Moreover, it maintains the format found in the reviewed papers. First, we describe the ARUs employed in the papers analyzed, their configuration, and the study sites where the datasets were collected. Then, we provide an ecological justification that relates acoustic monitoring to landscape features. Subsequently, we explain the machine learning methods followed to assess various landscape attributes. The results show a trend towards label-free methods that can process the large volumes of data gathered in recent years. Finally, we discuss the need to adopt methods with a machine learning approach in other biological dimensions of landscapes.

Foreword to the Special Issue on ‘The rapidly expanding role of drones as a tool for wildlife research’

Drones have emerged as a popular wildlife research tool, but their use for many species and environments remains untested and research is needed on validation of sampling approaches that are optimised for unpiloted aircraft. Here, we present a foreword to a special issue that features studies pushing the taxonomic and innovation boundaries of drone research and thus helps address these knowledge and application gaps. We then conclude by highlighting future drone research ideas that are likely to push biology and conservation in exciting new directions.