Modelling reindeer rut activity using on-animal acoustic recorders and machine learning

For decades, researchers have employed sound to study the biology of wildlife, with the aim to better understand their ecology and behaviour. By utilizing on-animal recorders to capture audio from freely moving animals, scientists can decipher the vocalizations and glean insights into their behaviour and ecosystem dynamics through advanced signal processing. However, the laborious task of sorting through extensive audio recordings has been a major bottleneck. To expedite this process, researchers have turned to machine learning techniques, specifically neural networks, to streamline the analysis of data. Nevertheless, much of the existing research has focused predominantly on stationary recording devices, overlooking the potential benefits of employing on-animal recorders in conjunction with machine learning. To showcase the synergy of on-animal recorders and machine learning, we conducted a study at the Kutuharju research station in Kaamanen, Finland, where the vocalizations of rutting reindeer were recorded during their mating season. By attaching recorders to seven male reindeer during the rutting periods of 2019 and 2020, we trained convolutional neural networks to distinguish reindeer grunts with a 95% accuracy rate. This high level of accuracy allowed us to examine the reindeers' grunting behaviour, revealing patterns indicating that older, heavier males vocalized more compared to their younger, lighter counterparts. The success of this study underscores the potential of on-animal acoustic recorders coupled with machine learning techniques as powerful tools for wildlife research, hinting at their broader applications with further advancement and optimization.

Identifying animal behaviours from accelerometers: Improving predictive accuracy of machine learning by refining the variables selected, data frequency, and sample duration

Observing animals in the wild often poses extreme challenges, but animal-borne accelerometers are increasingly revealing unobservable behaviours. Automated machine learning streamlines behaviour identification from the substantial datasets generated during multi-animal, long-term studies; however, the accuracy of such models depends on the qualities of the training data. We examined how data processing influenced the predictive accuracy of random forest (RF) models, leveraging the easily observed domestic cat (Felis catus) as a model organism for terrestrial mammalian behaviours. Nine indoor domestic cats were equipped with collar-mounted tri-axial accelerometers, and behaviours were recorded alongside video footage. From this calibrated data, eight datasets were derived with (i) additional descriptive variables, (ii) altered frequencies of acceleration data (40 Hz vs. a mean over 1 s) and (iii) standardised durations of different behaviours. These training datasets were used to generate RF models that were validated against calibrated cat behaviours before identifying the behaviours of five free-ranging tag-equipped cats. These predictions were compared to those identified manually to validate the accuracy of the RF models for free-ranging animal behaviours. RF models accurately predicted the behaviours of indoor domestic cats (F-measure up to 0.96) with discernible improvements observed with post-data-collection processing. Additional variables, standardised durations of behaviours and higher recording frequencies improved model accuracy. However, prediction accuracy varied with different behaviours, where high-frequency models excelled in identifying fast-paced behaviours (e.g. locomotion), whereas lower-frequency models (1 Hz) more accurately identified slower, aperiodic behaviours such as grooming and feeding, particularly when examining free-ranging cat behaviours. While RF modelling offered a robust means of behaviour identification from accelerometer data, field validations were important to validate model accuracy for free-ranging individuals. Future studies may benefit from employing similar data processing methods that enhance RF behaviour identification accuracy, with extensive advantages for investigations into ecology, welfare and management of wild animals.

SensorDrop: A system to remotely detach individual sensors from wildlife tracking collars

The growing diversity of animal-borne sensor types is revolutionizing our understanding of wildlife biology. For example, researcher-developed sensors, such as audio and video loggers, are being increasingly attached to wildlife tracking collars to provide insights into a range of topics from species interactions to physiology. However, such devices are often prohibitively power-intensive, relative to conventional wildlife collar sensors, and their retrieval without compromising long-term data collection and animal welfare remains a challenge. We present an open-source system (SensorDrop) for remotely detaching individual sensors from wildlife collars. SensorDrop facilitates the retrieval of power-intensive sensors while leaving non-resource-intensive sensors intact on animals. SensorDrop systems can be made using commercially available components and are a fraction of the cost of other timed drop-off devices that detach full wildlife tracking collars. From 2021 to 2022, eight SensorDrop units were successfully deployed on free-ranging African wild dog packs in the Okavango Delta as part of audio-accelerometer sensor bundles attached to wildlife collars. All SensorDrop units detached after 2-3 weeks and facilitated the collection of audio and accelerometer data while leaving wildlife GPS collars intact to continue collecting locational data (>1 year), critical for long-term conservation population monitoring in the region. SensorDrop offers a low-cost method to remotely detach and retrieve individual sensors from wildlife collars. By selectively detaching battery-depleted sensors, SensorDrop maximizes the amount of data collected per wildlife collar deployment and mitigates ethical concerns on animal rehandling. SensorDrop adds to the growing body of open-source animal-borne technologies being utilized by wildlife researchers to innovate and expand upon data collection practices and supports the continued ethical use of novel technologies within wildlife studies.

Addressing Power Issues in Biologging: An Audio/Inertial Recorder Case Study

In the past decades, biologging, i.e., the development and deployment of animal-borne loggers, has revolutionized ecology. Despite recent advances, power consumption and battery size however remain central issues and limiting factors, constraining the quantity of data that can be collected and the size of the animals that can be studied. Here, we present strategies to achieve ultra-low power in biologging, using the design of a lightweight audio-inertial logger as an example. It is designed with low-power MEMS sensors, and a firmware based on a small embedded RTOS. Both methodologies for power reduction and experimental results are detailed. With an average power consumption reduced to 5.3 mW, combined with a battery of 1800 mAh, the logger provides 900 h of continuous 8 kHz audio, 50 Hz accelerometer and 10 Hz magnetometer data.

Diurnal and Nocturnal Behaviour of Cheetahs (Acinonyx jubatus) and Lions (Panthera leo) in Zoos

Mammals are constantly exposed to exogenous and endogenous influences that affect their behaviour and daily activity. Light and temperature, as well as anthropogenic factors such as husbandry routines, visitors, and feeding schedules are potential influences on animals in zoological gardens. In order to investigate the effects of some of these factors on animal behaviour, observational studies based on the analyses of activity budgets can be used. In this study, the daily and nightly activity budgets of six lions (Panthera leo) and five cheetahs (Acinonyx jubatus) from four EAZA institutions were investigated. Focused on the influencing factor light and feeding, we analysed these activity budgets descriptively. Behaviour was recorded and analysed during the winter months over an observation period of 14 days and 14 nights using infrared-sensitive cameras. Our results show that lions and cheetahs exhibit activity peaks at crepuscular and feeding times, regardless of husbandry. Thus, lions in captivity shift nocturnal behaviour familiar from the wild to crepuscular and diurnal times. In cheetahs, in contrast, captive and wild individuals show similar 24 h behavioural rhythms. The resting behaviour of both species is more pronounced at night, with cheetahs having a shorter overall sleep duration than lions. This study describes the results of the examined animals and is not predictive. Nevertheless, the results of this study make an important contribution to gaining knowledge about possible factors influencing the behaviour of lions and cheetahs in zoos and offer implications that could be useful for improving husbandry and management.

Using on-board sound recordings to infer behaviour of free-moving wild animals

Technological advances in the last 20 years have enabled researchers to develop increasingly sophisticated miniature devices (tags) that record an animal's behaviour not from an observational, external viewpoint, but directly on the animals themselves. So far, behavioural research with these tags has mostly been conducted using movement or acceleration data. But on-board audio recordings have become more and more common following pioneering work in marine mammal research. The first questions that come to mind when recording sound on-board animals concern their vocal behaviour. When are they calling? How do they adjust their behaviour? What acoustic parameters do they change and how? However, other topics like foraging behaviour, social interactions or environmental acoustics can now be addressed as well and offer detailed insight into the animals' daily life. In this Review, we discuss the possibilities, advantages and limitations of on-board acoustic recordings. We focus primarily on bats as their active-sensing, echolocating lifestyle allows many approaches to a multi-faceted acoustic assessment of their behaviour. The general ideas and concepts, however, are applicable to many animals and hopefully will demonstrate the versatility of on-board acoustic recordings and stimulate new research.