Biology subjects

Forrest, S. W.

Publications and source records attributed to Forrest, S. W..

3 recordsLinked to original sources

bioRxiv2025

Predicting animal movement with deepSSF: a deep learning step selection framework

O_LIPredictions of animal movement are vital for understanding and managing wild populations. However, the fine-scale, complex decision-making of animals can pose challenges for the accurate prediction of trajectories. Step selection functions (SSFs), a common tool for inferring relationships between animal movement and the environment, are also increasingly used to simulate animal trajectories for prediction. Although admitting a lot of flexibility, the SSF framework is limited to its reliance on pre-defined functional forms for fitting to data, and SSFs that involve complex functional forms to model detailed processes can be prohibitively difficult to fit and interpret. C_LIO_LIHere, we present deepSSF, an approach to fit and predict animal movement data using deep learning. Whilst not specific to any particular model, we denote the deepSSF approach as building and training a neural network architecture that receives multiple environmental layers and scalar values as inputs, and outputs a single layer representing the next-step probability. To demonstrate a deepSSF model, we build a model in PyTorch that has distinct but interacting habitat selection and movement subnetworks, which allows for explicit representation of both processes and interpretable intermediate outputs. We apply our model to GPS data of introduced water buffalo (Bubalus bubalis) in the tropical savannas of Northern Australia. C_LIO_LIOur deepSSF model was able to learn features that are present in the habitat covariate layers, such as linear features (rivers, forest edges), and the composition of certain habitat areas, without having to specify them pre-emptively within the SSF framework. It was also able to capture the complex interactions between the habitat covariates as well as temporal dynamics across time of day and year. C_LIO_LIWe expect that the deepSSF approach will generate accurate and informative animal movement trajectories, which can be used for deepening our understanding of animal-environment systems and for the practical management of species. Considering the wide range of deep learning tools, the deepSSF approach could be extended to represent memory and social dynamic processes, with the potential for integrating non-spatial data sources such as accelerometers and physiological sensors. C_LI

ecology↗

bioRxiv2024

Simulating animal movement trajectories from temporally dynamic step selection functions

Understanding and predicting animal movement is fundamental to ecology and conservation management. Models that estimate and then predict animal movement and habitat selection parameters underpin diverse conservation applications, from mitigating invasive species spread to enhancing landscape connectivity. However, many predictive models overlook fine-scale temporal dynamics within their predictions, despite animals often displaying fine-scale behavioural variability that might significantly alter their movement, habitat selection and distribution over time. Incorporating fine-scale temporal dynamics, such as circadian rhythms, within predictive models might reduce the averaging out of such behaviours, thereby enhancing our ability to make predictions in both the short and long term. We tested whether the inclusion of fine-scale temporal dynamics improved both fine-scale (hourly) and long-term (seasonal) spatial predictions for a significant invasive species of Northern Australia, the water buffalo (Bubalus bubalis). Water buffalo require intensive management actions over vast, remote areas and display distinct circadian rhythms linked to habitat use. To inform management operations we generated hourly and dry season prediction maps by simulating trajectories from static and temporally dynamic step selection functions (SSFs) that were fitted to the GPS data of 13 water buffalo. We found that simulations generated from temporally dynamic models replicated the buffalos crepuscular movement patterns and dynamic habitat selection, resulting in more informative and accurate hourly predictions. Additionally, when the simulations were aggregated into long-term predictions, the dynamic models were more accurate and better able to highlight areas of concentrated habitat use that might indicate high-risk areas for environmental damage. Our findings emphasise the importance of incorporating fine-scale temporal dynamics in predictive models for species with clear dynamic behavioural patterns. By integrating temporally dynamic processes into animal movement trajectories, we demonstrate an approach that can enhance conservation management strategies and deepen our understanding of ecological and behavioural patterns across multiple timescales.

ecology↗

bioRxiv2022

Estimating home range and temporal space use variability reveals age-related differences in risk exposure for reintroduced parrots

Individual-level differences in animal spatial behaviour can lead to differential exposure to risk. We assessed the risk-exposure of a reintroduced population of k[a]k[a] (Nestor meridionalis) in a fenced reserve in New Zealand by GPS tracking 10 individuals and comparing the proportion of each individuals home range beyond the reserves fence in relation to age, sex, and fledging origin. To estimate dynamic space use, we used a sweeping window framework to estimate occurrence distributions from temporally overlapping snapshots. For each occurrence distribution, we calculated the proportion outside the reserves fence to assess temporal risk exposure, and the area, centroid and overlap to represent the behavioural pattern of space use. Home range area declined significantly and consistently with age, and the space use of juvenile k[a]k[a] was more dynamic, particularly in relation to positional changes of space use. The wider- ranging and more dynamic behaviour of younger k[a]k[a] resulted in consistently more time spent outside the reserve, which aligned with a higher number of incidental mortality observations. Quantifying both home range and dynamic space use is an effective approach to assess risk exposure, which can provide guidance for management interventions. We also emphasise the dynamic space use approach, which is flexible and can provide numerous insights towards a species spatial ecology.

ecology↗