Application of tri-axial accelerometer data to the interpretation of movement and behaviour of threatened black cockatoos

Abstract

Context Carnaby’s (Calyptorhychus latirostris), Baudin’s (Calyptorhynchus baudinii) and forest red-tailed black cockatoos (Calyptorhynchus banksii naso) are threatened parrot species endemic to south-western Australia. Behavioural monitoring has previously involved direct observation, which has proven challenging because of their cryptic nature, the type of habitat they move through and their speed of movement. The development of a model to accurately classify behaviour from tri-axial accelerometer data will provide greater insight into black cockatoo behaviour and ecology. Aims To develop an automated classifier model to classify accelerometer data from released black cockatoos to determine behaviour and activity budgets for three species of black cockatoo. Methods In the present study, we attached tri-axial accelerometers, housed in GPS tags, to four Carnaby’s cockatoos, three forest red-tailed black cockatoos and two Baudin’s cockatoos in captive care, undergoing rehabilitation for release back to the wild. Accelerometer data from these birds was coupled with 19 video files of the birds’ behaviour when flying, feeding and resting, to develop an automated behaviour classifier. The classifier was then used to annotate accelerometer data from 15 birds released after successful rehabilitation and to calculate activity budgets for these birds post-release. Key results We developed a classifier able to identify resting, flying and foraging behaviours from accelerometer data with 86% accuracy, as determined by the percentage of observed behaviours correctly identified by the classifier. The application of the classifier to accelerometer data from 15 released cockatoos enabled us to determine behaviours and activity budgets for all three species of black cockatoo. Black cockatoos spent most of their time at rest, followed by foraging with a short period of time flying. Conclusions Application of the classifier to data from released birds gives researchers the ability to remotely identify patterns of behaviour and calculate activity budgets. Implications Combining behaviour and activity budgets with location data provides useful insight into cockatoo movement, distribution, and habitat use. Such information is important for informing conservation efforts and addressing outstanding research objectives. Further studies including larger sample sizes of Baudin’s and forest red-tailed black cockatoos and comparing behaviour and activity between birds in breeding and non-breeding areas are warranted.

Accelerometry reveals limits to use of an energy‐saving anthropogenic food source by a threatened species: A case of Carnaby's cockatoos (Zanda latirostris) and canola

“…Development of the classification model involved manual classification of bird behaviours by an expert observer, which was then used to train a machine‐learning algorithm to recognise distinctive accelerometer signatures produced during each behaviour. The model's algorithm was able to identify these behaviours with 86% accuracy (Yeap et al., 2021 ; see Supporting Information for validity testing of classifications applied to data in this study). Daytime hours spent at rest were calculated by summing the duration between subsequent GPS locations following each location classified as resting.…”

“…A behavioural classification of either ‘resting’, ‘foraging’ or ‘flying’ was assigned to each GPS location by processing the corresponding accelerometer data frame through an automated classification model developed for black cockatoos by Yeap et al. ( 2021 ). Development of the classification model involved manual classification of bird behaviours by an expert observer, which was then used to train a machine‐learning algorithm to recognise distinctive accelerometer signatures produced during each behaviour.…”

“…A behavioural classification of either 'resting', 'foraging' or 'flying' was assigned to each GPS location by processing the corresponding accelerometer data frame through an automated classification model developed for black cockatoos by Yeap et al (2021).…”

“…Foraging on native vegetation was classified as all locations with the behavioural class 'foraging' occurring outside canola crop polygons. During the development of the behavioural classification algorithm by Yeap et al (2021), unspecified behaviours including preening and aggressive interactions (which accounted for <4% of total observations) were incorporated into the 'foraging' behavioural class. Behaviours associated with breeding such as entering and exiting the hollow and feeding the nestling were not incorporated into the classification algorithm, which was developed using observations of nonbreeding birds.…”

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

“…Behaviour has traditionally been studied through direct observation, but recent advancements in biologging now enable around‐the‐clock, non‐invasive and bias‐free data collection on a large scale (Chakravarty et al., 2019; Glass et al., 2020; Nathan et al., 2012, 2022; Studd et al., 2019). Consequently, behaviour classification on the basis of accelerometer (ACC) data has successfully been applied to mammals (Chakravarty et al., 2020; Chimienti et al., 2021; Kirchner et al., 2023), birds (Patterson et al., 2019; Yeap et al., 2021), reptiles (Fossette et al., 2010; Whitney et al., 2021) and fish (Beltramino et al., 2019; Clarke et al., 2021). Here we classify antelope behaviour based on ACC data and relate this to rising temperature.…”