Behavioral classification of low-frequency acceleration and temperature data from a free-ranging small mammal

Development of a multisensor biologging collar and analytical techniques to describe high-resolution spatial behavior in free-ranging terrestrial mammals

Biologging has proven to be a powerful approach to investigate diverse questions related to movement ecology across a range of spatiotemporal scales and increasingly relies on multidisciplinary expertise. However, the variety of animal-borne equipment, coupled with little consensus regarding analytical approaches to interpret large, complex data sets presents challenges and makes comparison between studies and study species difficult. Here, we present a combined hardware and analytical approach for standardizing the collection, analysis, and interpretation of multisensor biologging data. Here, we present (i) a custom-designed integrated multisensor collar (IMSC), which was field tested on 71 free-ranging wild boar (Sus scrofa) over 2 years; (ii) a machine learning behavioral classifier capable of identifying six behaviors in free-roaming boar, validated across individuals equipped with differing collar designs; and (iii) laboratory and field-based calibration and accuracy assessments of animal magnetic heading measurements derived from raw magnetometer data. The IMSC capacity and durability exceeded expectations, with a 94% collar recovery rate and a 75% cumulative data recording success rate, with a maximum logging duration of 421 days. The behavioral classifier had an overall accuracy of 85% in identifying the six behavioral classes when tested on multiple collar designs and improved to 90% when tested on data exclusively from the IMSC. Both laboratory and field tests of magnetic compass headings were in precise agreement with expectations, with overall median magnetic headings deviating from ground truth observations by 1.7° and 0°, respectively. Although multisensor equipment and sophisticated analyses are now commonplace in biologging studies, the IMSC hardware and analytical framework presented here provide a valuable tool for biologging researchers and will facilitate standardization of biologging data across studies. In addition, we highlight the potential of additional analyses available using this framework that can be adapted for use in future studies on terrestrial mammals.

African dryland antelope trade-off behaviours in response to heat extremes

Climate change is predicted to narrow the prescriptive zone of dryland species, potentially leading to behavioural modifications with fitness consequences. This study explores the behavioural responses of three widespread African antelope species-springbok, kudu and eland-to extreme heat in a dryland savanna. We classified the behaviour of 29 individuals during the hot, dry season on the basis of accelerometer data using supervised machine learning and analysed the impact of afternoon heat on behaviour-specific time allocation and overall dynamic body acceleration (ODBA), a proxy for energy expenditure, along with compensatory changes over the 24-hour cycle. Extreme afternoon heat reduced feeding time in all three antelope species, increased ruminating and resting time, while only minimally affecting walking time. With rising heat, all three species reduced ODBA on feeding, while eland reduced and kudu increased ODBA on walking. Diel responses in behaviour differed between species, but were generally characterised by daytime reductions in feeding and increases in ruminating or resting on hot days compared to cool days. While antelope compensated for heat-driven behavioural change over the 24-hour cycle in some cases, significant differences persisted in others, including reduced feeding and increased rumination and resting. The impact of heat on antelope behaviour reveals trade-offs between feeding and thermoregulation, as well as between feeding and rumination, the latter suggesting a strategy to enhance nutrient uptake through increased digestive efficiency, while the walking response suggests narrow constraints between cost and necessity. Our findings suggest that heat influences both behaviour-specific time allocation and energy expenditure. Altered diel behaviour patterns and incomplete compensation over the 24-hour cycle point to fitness consequences. The need to prioritise thermoregulation over feeding is likely to narrow the prescriptive zone of these dryland antelope.

Supervised versus unsupervised approaches to classification of accelerometry data

Sophisticated animal-borne sensor systems are increasingly providing novel insight into how animals behave and move. Despite their widespread use in ecology, the diversity and expanding quality and quantity of data they produce have created a need for robust analytical methods for biological interpretation. Machine learning tools are often used to meet this need. However, their relative effectiveness is not well known and, in the case of unsupervised tools, given that they do not use validation data, their accuracy can be difficult to assess. We evaluated the effectiveness of supervised (n = 6), semi-supervised (n = 1), and unsupervised (n = 2) approaches to analyzing accelerometry data collected from critically endangered California condors (Gymnogyps californianus). Unsupervised K-means and EM (expectation-maximization) clustering approaches performed poorly, with adequate classification accuracies of <0.8 but very low values for kappa statistics (range: -0.02 to 0.06). The semi-supervised nearest mean classifier was moderately effective at classification, with an overall classification accuracy of 0.61 but effective classification only of two of the four behavioral classes. Supervised random forest (RF) and k-nearest neighbor (kNN) machine learning models were most effective at classification across all behavior types, with overall accuracies >0.81. Kappa statistics were also highest for RF and kNN, in most cases substantially greater than for other modeling approaches. Unsupervised modeling, which is commonly used for the classification of a priori-defined behaviors in telemetry data, can provide useful information but likely is instead better suited to post hoc definition of generalized behavioral states. This work also shows the potential for substantial variation in classification accuracy among different machine learning approaches and among different metrics of accuracy. As such, when analyzing biotelemetry data, best practices appear to call for the evaluation of several machine learning techniques and several measures of accuracy for each dataset under consideration.

Developing a classification system to assign activity states to two species of freshwater turtles

Research in ecology often requires robust assessment of animal behaviour, but classifying behavioural patterns in free-ranging animals and in natural environments can be especially challenging. New miniaturised bio-logging devices such as accelerometers are increasingly available to record animal behaviour remotely, and thereby address the gap in knowledge related to behaviour of free-ranging animals. However, validation of these data is rarely conducted and classification model transferability across closely-related species is often not tested. Here, we validated accelerometer and water sensor data to classify activity states in two free-ranging freshwater turtle species (Blanding's turtle, Emydoidea blandingii, and Painted turtle, Chrysemys picta). First, using only accelerometer data, we developed a decision tree to separate motion from motionless states, and second, we included water sensor data to classify the animal as being motionless or in-motion on land or in water. We found that accelerometers separated in-motion from motionless behaviour with > 83% accuracy, whereas models also including water sensor data predicted states in terrestrial and aquatic locations with > 77% accuracy. Despite differences in values separating activity states between the two species, we found high model transferability allowing cross-species application of classification models. Note that reducing sampling frequency did not affect predictive accuracy of our models up to a sampling frequency of 0.0625 Hz. We conclude that the use of accelerometers in animal research is promising, but requires prior data validation and development of robust classification models, and whenever possible cross-species assessment should be conducted to establish model generalisability.

Behavioural adjustments of predators and prey to wind speed in the boreal forest

Wind speed can have multifaceted effects on organisms including altering thermoregulation, locomotion, and sensory reception. While forest cover can substantially reduce wind speed at ground level, it is not known if animals living in forests show any behavioural responses to changes in wind speed. Here, we explored how three boreal forest mammals, a predator and two prey, altered their behaviour in response to average daily wind speeds during winter. We collected accelerometer data to determine wind speed effects on activity patterns and kill rates of free-ranging red squirrels (n = 144), snowshoe hares (n = 101), and Canada lynx (n = 27) in Kluane, Yukon from 2015 to 2018. All 3 species responded to increasing wind speeds by changing the time they were active, but effects were strongest in hares, which reduced daily activity by 25%, and lynx, which increased daily activity by 25%. Lynx also increased the number of feeding events by 40% on windy days. These results highlight that wind speed is an important abiotic variable that can affect behaviour, even in forested environments.

An implantable neurophysiology platform: Broadening research capabilities in free-living and non-traditional animals

Animal-borne sensors that can record and transmit data (“biologgers”) are becoming smaller and more capable at a rapid pace. Biologgers have provided enormous insight into the covert lives of many free-ranging animals by characterizing behavioral motifs, estimating energy expenditure, and tracking movement over vast distances, thereby serving both scientific and conservational endpoints. However, given that biologgers are usually attached externally, access to the brain and neurophysiological data has been largely unexplored outside of the laboratory, limiting our understanding of how the brain adapts to, interacts with, or addresses challenges of the natural world. For example, there are only a handful of studies in free-living animals examining the role of sleep, resulting in a wake-centric view of behavior despite the fact that sleep often encompasses a large portion of an animal’s day and plays a vital role in maintaining homeostasis. The growing need to understand sleep from a mechanistic viewpoint and probe its function led us to design an implantable neurophysiology platform that can record brain activity and inertial data, while utilizing a wireless link to enable a suite of forward-looking capabilities. Here, we describe our design approach and demonstrate our device’s capability in a standard laboratory rat as well as a captive fox squirrel. We also discuss the methodological and ethical implications of deploying this new class of device “into the wild” to fill outstanding knowledge gaps.

Identification of reindeer fine-scale foraging behaviour using tri-axial accelerometer data

Animal behavioural responses to the environment ultimately affect their survival. Monitoring animal fine-scale behaviour may improve understanding of animal functional response to the environment and provide an important indicator of the welfare of both wild and domesticated species. In this study, we illustrate the application of collar-attached acceleration sensors for investigating reindeer fine-scale behaviour. Using data from 19 reindeer, we tested the supervised machine learning algorithms Random forests, Support vector machines, and hidden Markov models to classify reindeer behaviour into seven classes: grazing, browsing low from shrubs or browsing high from trees, inactivity, walking, trotting, and other behaviours. We implemented leave-one-subject-out cross-validation to assess generalizable results on new individuals. Our main results illustrated that hidden Markov models were able to classify collar-attached accelerometer data into all our pre-defined behaviours of reindeer with reasonable accuracy while Random forests and Support vector machines were biased towards dominant classes. Random forests using 5-s windows had the highest overall accuracy (85%), while hidden Markov models were able to best predict individual behaviours and handle rare behaviours such as trotting and browsing high. We conclude that hidden Markov models provide a useful tool to remotely monitor reindeer and potentially other large herbivore species behaviour. These methods will allow us to quantify fine-scale behavioural processes in relation to environmental events.

Categorising cheetah behaviour using tri-axial accelerometer data loggers: a comparison of model resolution and data logger performance

BACKGROUND

Extinction is one of the greatest threats to the living world, endangering organisms globally, advancing conservation to the forefront of species research. To maximise the efficacy of conservation efforts, understanding the ecological, physiological, and behavioural requirements of vulnerable species is vital. Technological advances, particularly in remote sensing, enable researchers to continuously monitor movement and behaviours of multiple individuals simultaneously with minimal human intervention. Cheetahs, Acinonyx jubatus, constitute a "vulnerable" species for which only coarse behaviours have been elucidated. The aims of this study were to use animal-attached accelerometers to (1) determine fine-scale behaviours in cheetahs, (2) compare the performances of different devices in behaviour categorisation, and (3) provide a behavioural categorisation framework.

METHODS

Two different accelerometer devices (CEFAS, frequency: 30 Hz, maximum capacity: ~ 2 g; GCDC, frequency: 50 Hz, maximum capacity: ~ 8 g) were mounted onto collars, fitted to five individual captive cheetahs. The cheetahs chased a lure around a track, during which time their behaviours were videoed. Accelerometer data were temporally aligned with corresponding video footage and labelled with one of 17 behaviours. Six separate random forest models were run (three per device type) to determine the categorisation accuracy for behaviours at a fine, medium, and coarse resolution.

RESULTS

Fine- and medium-scale models had an overall categorisation accuracy of 83-86% and 84-88% respectively. Non-locomotory behaviours were best categorised on both loggers with GCDC outperforming CEFAS devices overall. On a coarse scale, both devices performed well when categorising activity (86.9% (CEFAS) vs. 89.3% (GCDC) accuracy) and inactivity (95.5% (CEFAS) vs. 95.0% (GCDC) accuracy). This study defined cheetah behaviour beyond three categories and accurately determined stalking behaviours by remote sensing. We also show that device specification and configuration may affect categorisation accuracy, so we recommend deploying several different loggers simultaneously on the same individual.

CONCLUSION

The results of this study will be useful in determining wild cheetah behaviour. The methods used here allowed broad-scale (active/inactive) as well as fine-scale (e.g. stalking) behaviours to be categorised remotely. These findings and methodological approaches will be useful in monitoring the behaviour of wild cheetahs and other species of conservation interest.

Integrative Studies of the Effects of Mothers on Offspring: An Example from Wild North American Red Squirrels

Animal species vary in whether they provide parental care or the type of care provided, and this variation in parental care among species has been a common focus of comparative studies. However, the proximate causes and ultimate consequences of within-species variation in parental care have been less studied. Most studies about the impacts of within-species variation in parental care on parental fitness have been in primates, whereas studies in laboratory rodents have been invaluable for understanding what causes inter-individual variation in parental care and its influence on offspring characteristics. We integrated both of these perspectives in our long-term study of North American red squirrels (Tamiasciurus hudsonicus) in the Yukon, Canada, where we have focused on understanding the impacts of mothers on offspring. This includes documenting the impacts that mothers or the maternal environment itself has on their offspring, identifying how changes in maternal physiology impact offspring characteristics, the presence of individual variation in maternal attentiveness toward offspring before weaning and its fitness consequences, and postweaning maternal care and its fitness consequences. We provide an overview of these contributions to understanding the impacts mothers have on their offspring in red squirrels using an integrative framework and contrast them with studies in the laboratory.

Limitations of using surrogates for behaviour classification of accelerometer data: refining methods using random forest models in Caprids

BACKGROUND

Animal-attached devices can be used on cryptic species to measure their movement and behaviour, enabling unprecedented insights into fundamental aspects of animal ecology and behaviour. However, direct observations of subjects are often still necessary to translate biologging data accurately into meaningful behaviours. As many elusive species cannot easily be observed in the wild, captive or domestic surrogates are typically used to calibrate data from devices. However, the utility of this approach remains equivocal.

METHODS

Here, we assess the validity of using captive conspecifics, and phylogenetically-similar domesticated counterparts (surrogate species) for calibrating behaviour classification. Tri-axial accelerometers and tri-axial magnetometers were used with behavioural observations to build random forest models to predict the behaviours. We applied these methods using captive Alpine ibex (Capra ibex) and a domestic counterpart, pygmy goats (Capra aegagrus hircus), to predict the behaviour including terrain slope for locomotion behaviours of captive Alpine ibex.

RESULTS

Behavioural classification of captive Alpine ibex and domestic pygmy goats was highly accurate (> 98%). Model performance was reduced when using data split per individual, i.e., classifying behaviour of individuals not used to train models (mean ± sd = 56.1 ± 11%). Behavioural classifications using domestic counterparts, i.e., pygmy goat observations to predict ibex behaviour, however, were not sufficient to predict all behaviours of a phylogenetically similar species accurately (> 55%).

CONCLUSIONS

We demonstrate methods to refine the use of random forest models to classify behaviours of both captive and free-living animal species. We suggest there are two main reasons for reduced accuracy when using a domestic counterpart to predict the behaviour of a wild species in captivity; domestication leading to morphological differences and the terrain of the environment in which the animals were observed. We also identify limitations when behaviour is predicted in individuals that are not used to train models. Our results demonstrate that biologging device calibration needs to be conducted using: (i) with similar conspecifics, and (ii) in an area where they can perform behaviours on terrain that reflects that of species in the wild.

Decoupling the effects of food and density on life-history plasticity of wild animals using field experiments: Insights from the steward who sits in the shadow of its tail, the North American red squirrel

Long-term studies of wild animals provide the opportunity to investigate how phenotypic plasticity is used to cope with environmental fluctuations and how the relationships between phenotypes and fitness can be dependent upon the ecological context. Many previous studies have only investigated life-history plasticity in response to changes in temperature, yet wild animals often experience multiple environmental fluctuations simultaneously. This requires field experiments to decouple which ecological factor induces plasticity in fitness-relevant traits to better understand their population-level responses to those environmental fluctuations. For the past 32 years, we have conducted a long-term integrative study of individually marked North American red squirrels Tamiasciurus hudsonicus Erxleben in the Yukon, Canada. We have used multi-year field experiments to examine the physiological and life-history responses of individual red squirrels to fluctuations in food abundance and conspecific density. Our long-term observational study and field experiments show that squirrels can anticipate increases in food availability and density, thereby decoupling the usual pattern where animals respond to, rather than anticipate, an ecological change. As in many other study systems, ecological factors that can induce plasticity (such as food and density) covary. However, our field experiments that manipulate food availability and social cues of density (frequency of territorial vocalizations) indicate that increases in social (acoustic) cues of density in the absence of additional food can induce similar life-history plasticity, as does experimental food supplementation. Changes in the levels of metabolic hormones (glucocorticoids) in response to variation in food and density are one mechanism that seems to induce this adaptive life-history plasticity. Although we have not yet investigated the energetic response of squirrels to elevated density or its association with life-history plasticity, energetics research in red squirrels has overturned several standard pillars of knowledge in physiological ecology. We show how a tractable model species combined with integrative studies can reveal how animals cope with resource fluctuations through life-history plasticity.

Machine learning goes wild: Using data from captive individuals to infer wildlife behaviours

1. Remotely tracking distinct behaviours of animals using acceleration data and machine learning has been carried out successfully in several species in captive settings. In order to study the ecology of animals in natural habitats, such behaviour classification models need to be transferred to wild individuals. However, at present, the development of those models usually requires direct observation of the target animals. 2. The goal of this study was to infer the behaviour of wild, free-roaming animals from acceleration data by training behaviour classification models on captive individuals, without the necessity to observe their wild conspecifics. We further sought to develop methods to validate the credibility of the resulting behaviour extrapolations. 3. We trained two machine learning algorithms proposed by the literature, Random Forest (RF) and Support Vector Machine (SVM), on data from captive red foxes (Vulpes vulpes) and later applied them to data from wild foxes. We also tested a new advance for behaviour classification, by applying a moving window to an Artificial Neural Network (ANN). Finally, we investigated four strategies to validate our classification output. 4. While all three machine learning algorithms performed well under training conditions (Kappa values: RF (0.82), SVM (0.78), ANN (0.85)), the established methods, RF and SVM, failed in classifying distinct behaviours when transferred from captive to wild foxes. Behaviour classification with the ANN and a moving window, in contrast, inferred distinct behaviours and showed consistent results for most individuals. 5. Our approach is a substantial improvement over the methods previously proposed in the literature as it generated plausible results for wild fox behaviour. We were able to infer the behaviour of wild animals that have never been observed in the wild and to further illustrate the credibility of the output. This framework is not restricted to foxes but can be applied to infer the behaviour of many other species and thus empowers new advances in behavioural ecology.

Exploration profiles drive activity patterns and temporal niche specialization in a wild rodent

Individual niche specialization can have important consequences for competition, fitness, and, ultimately, population dynamics and ecological speciation. The temporal window and the level of daily activity are niche components that may vary with sex, breeding season, food supply, population density, and predator’s circadian rhythm. More recently, ecologists emphasized that traits such as dispersal and space use could depend on personality differences. Boldness and exploration have been shown to correlate with variation in foraging patterns, habitat use, and home range. Here, we assessed the link between exploration, measured from repeated novel environment tests, activity patterns, and temporal niche specialization in wild eastern chipmunks (Tamias striatus). Intrinsic differences in exploration should drive daily activity patterns through differences in energy requirements, space use, or the speed to access resources. We used collar-mounted accelerometers to assess whether individual exploration profiles predicted: 1) daily overall dynamic body acceleration, reflecting overall activity levels; 2) mean activity duration and the rate of activity sequences, reflecting the structure of daily activity; and 3) patterns of dawn and dusk activity, reflecting temporal niche differentiation. Exploration and overall activity levels were weakly related. However, both dawn activity and rate of activity sequences increased with the speed of exploration. Overall, activity patterns varied according to temporal variability in food conditions. This study emphasizes the role of intrinsic behavioral differences in activity patterns in a wild animal population. Future studies will help us understand how yearly seasonality in reproduction, food abundance, and population density modulate personality-dependent foraging patterns and temporal niche specialization.

Optimisation of energetic and reproductive gains explains behavioural responses to environmental variation across seasons and years

Animals switch between inactive and active states, simultaneously impacting their energy intake, energy expenditure and predation risk, and collectively defining how they engage with environmental variation and trophic interactions. We assess daily activity responses to long-term variation in temperature, resources and mating opportunities to examine whether individuals choose to be active or inactive according to an optimisation of the relative energetic and reproductive gains each state offers. We show that this simplified behavioural decision approach predicts most activity variation (R²  = 0.83) expressed by free-ranging red squirrels over 4 years, as quantified through accelerometer recordings (489 deployments; 5066 squirrel-days). Recognising activity as a determinant of energetic status, the predictability of activity variation aggregated at a daily scale, and the clear signal that behaviour is environmentally forced through optimisation of gain, provides an integrated approach to examine behavioural variation as an intermediary between environmental variation and energetic, life-history and ecological outcomes.

Feeling the heat: Elevated temperature affects male display activity of a lekking grassland bird

Most species-climate models relate range margins to long-term mean climate but lack mechanistic understanding of the ecological or demographic processes underlying the climate response. We examined the case of a climatically limited edge-of-range population of a medium-sized grassland bird, for which climate responses may involve a behavioural trade-off between temperature stress and reproduction. We hypothesised that temperature will be a limiting factor for the conspicuous, male snort-call display behaviour, and high temperatures would reduce the display activity of male birds.

Using remote tracking technology with tri-axial accelerometers we classified and studied the display behaviour of 17 free-ranging male little bustards, Tetrax tetrax, at 5 sites in the Iberian Peninsula. Display behaviour was related to temperature using two classes of Generalized Additive Mixed Models (GAMMs) at different temporal resolutions. GAMMs showed that temperature, time of the day and Julian date explained variation in display behaviour within the day, with birds snort-calling significantly less during higher temperatures. We also showed that variation in daily snort-call activity was related to average daytime temperatures, with our model predicting an average decrease in daytime snort-call display activity of up to 10.4% for the temperature increases projected by 2100 in this region due to global warming. For lekking birds and mammals undertaking energetically-costly displays in a warming climate, reduced display behaviour could impact inter- and intra-sex mating behaviour interactions through sexual selection and mate choice mechanisms, with possible consequences on mating and reproductive success. The study provides a reproducible example for how accelerometer data can be used to answer research questions with important conservation inferences related to the impacts of climate change on a range of taxonomic groups.