Journal Article

Treed Gaussian processes for animal movement modeling

Rieber, Camille J., Haukos, David A., Hefley, Trevor J.

2024

Overview

Wildlife telemetry data may be used to answer a diverse range of questions relevant to wildlife ecology and management. One challenge to modeling telemetry data is that animal movement often varies greatly in pattern over time, and current continuous‐time modeling approaches to handle such nonstationarity require bespoke and often complex models that may pose barriers to practitioner implementation. We demonstrate a novel application of treed Gaussian process (TGP) modeling, a Bayesian machine learning approach that automatically captures the nonstationarity and abrupt transitions present in animal movement. The machine learning formulation of TGPs enables modeling to be nearly automated, while their Bayesian formulation allows for the derivation of movement descriptors with associated uncertainty measures. We demonstrate the use of an existing R package to implement TGPs using the familiar Markov chain Monte Carlo algorithm. We then use estimated movement trajectories to derive movement descriptors that can be compared across individuals and populations. We applied the TGP model to a case study of lesser prairie‐chickens (Tympanuchus pallidicinctus) to demonstrate the benefits of TGP modeling and compared distance traveled and residence times across lesser prairie‐chicken individuals and populations. For broad usability, we outline all steps necessary for practitioners to specify relevant movement descriptors (e.g., turn angles, speed, contact points) and apply TGP modeling and trajectory comparison to their own telemetry datasets. Combining the predictive power of machine learning and the statistical inference of Bayesian methods to model movement trajectories allows for the estimation of statistically comparable movement descriptors from telemetry studies. Our use of an accessible R package allows practitioners to model trajectories and estimate movement descriptors, facilitating the use of telemetry data to answer applied management questions. We apply a recently developed Bayesian machine learning model to both increase the accessibility of complex animal movement models and simultaneously achieve advanced modeling of highly varied telemetry data. By nesting this model within a widely applicable inferential framework and utilizing an accessible R package for modeling, we facilitate application by practitioners to model trajectories, estimate movement descriptors, and answer applied management questions.

• Publisher: John Wiley & Sons, Inc,John Wiley and Sons Inc,Wiley
• Subject: Algorithms / Animals / Bayesian analysis / Bayesian model / Chickens / Conservation Ecology / Contact angle / Ecology / Gaussian process / Global positioning systems / GPS / Learning algorithms / lesser prairie‐chicken / Machine learning / Markov chains / Mathematical models / Modelling / Movement Ecology / movement modeling / Population studies / Populations / population‐level inference / Questions / Rocket launches / Statistical inference / Statistical models / Telemetry / Trajectory analysis / treed Gaussian processes / Wildlife / Wildlife management