Behaviour-specific spatiotemporal patterns of habitat use by sea turtles revealed using biologging and supervised machine learning

Conservation of threatened species and anthropogenic threat mitigation commonly rely on spatially managed areas selected according to habitat preference. Since the impact of threats can be behaviour-specific, such information could be incorporated into spatial management to improve conservation outcomes. However, collecting spatially explicit behavioural data is challenging.
Using multi-sensor biologging tags containing high-resolution movement sensors (e.g., accelerometer, magnetometer, GPS) and animal-borne video cameras, combined with supervised machine learning, we developed a method to automatically identify and geolocate typically ambiguous behaviours for the poorly understood flatback turtle Natator depressus. Subsequently, we evaluated behaviour-specific spatiotemporal patterns of habitat use.
Boosted regression trees successfully identified the presence of foraging and resting in 7074 dives (AUC > 0.9), using dive features representing characteristics of locomotory activity..., Flatback turtles at Yawuru Nagulagun Roebuck Bay, Western Australia were captured at sea and equipped with a CATS tag (Camera or Diary) multisensor biologging tag for up to 1 week, from 2018–2021. Data have been pre-processed into dives and their dive features, temporal covariates and observed behaviours according to methods in the main manuscript and Hounslow JL, Fossette S, Byrnes EE, Whiting SD, Lambourne RN, Armstrong NJ, Tucker AD, Richardson AR, Gleiss AC (2022) Multivariate analysis of biologging data reveals the environmental determinants of diving behaviour in a marine reptile. Royal Society Open Science 9:211860., DF.csv can be opened with any text editor (e.g MS Excel, UltraEdit).
R Files can be read into the R statistical software (version 4.0.3 or later), available at https://www.r-project.org/
Shapefiles can be opened in R, QGIS, ArcGIS etc.Â