Linking behavioral states to landscape features for improved conservation management

Sur, Maitreyi; Woodbridge, Brian; Esque, Todd C.; Belthoff, James R.; Bloom, Peter H.; Fisher, Robert N.; Longshore, Kathleen M.; Nussear, Kenneth E.; Tracey, Jeff A.; Braham, Melissa A.; Katzner, Todd E.

doi:10.1002/ece3.7621

Cited by 4 publications

(2 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This opens the possibility of a rich new suite of variables to define movement because velocity, acceleration, and deceleration have not just a horizontal component but also a vertical component. In fact, position on the Z plane, measured as altitude above ground, may be even more important for classifying behavior than is position on the X / Y plane (Sur et al, 2021). Most existing software implementations of popular movement analyses including BCPA (Gurarie, 2014), HMM (Michelot et al, 2016), or BPM (Calenge, 2006) assume the movement data comprise a two‐dimensional spatial component and a time component.…”

Section: Introductionmentioning

confidence: 99%

Classifying behavior from short‐interval biologging data: An example with GPS tracking of birds

Bergen

Huso

Duerr

et al. 2022

Ecology and Evolution

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Classifying behavior from short‐interval biologging data: An example with GPS tracking of birds

Bergen

Huso

Duerr

et al. 2022

Ecology and Evolution

Self Cite

View full text Add to dashboard Cite

show abstract

“…Understanding an animal's response to its environment and predicting its behaviour with environmental features is a frequent goal in animal movement ecology (Kays et al, 2015; Mercker et al, 2021) that also has important implications for conservation (Sur et al, 2021; Wijeyakulasuriya et al, 2020). As advances in technology for studying animal movement have led to an increase in quantities of movement data, computational feasibility of behavioural classification tools is also an important consideration (Clarke et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

A review of supervised learning methods for classifying animal behavioural states from environmental features

et al. 2022

Self Cite

View full text Add to dashboard Cite

1. Accurately predicting behavioural modes of animals in response to environmental features is important for ecology and conservation. Supervised learning (SL) methods are increasingly common in animal movement ecology for classifying behavioural modes. However, few examples exist of applying SL to classify polytomous animal behaviour from environmental features especially in the context of millions of animal observations. 2. We review SL methods (weighted k-nearest neighbours; neural nets; random forests; and boosted classification trees with XGBoost) for classifying polytomous animal behaviour from environmental predictors. We also describe tuning parameter selection and assessment strategies, approaches for visualizing relationships between predictors and class outputs, and computational considerations. We demonstrate these methods by predicting three categories of risk to bald eagles from colliding with wind turbines using, as predictors, 12 environmental state features associated with 1.7 million GPS telemetry data points from 57 eagles.3. Of the SL methods we considered, XGBoost yielded the most accurate model with 86.2% classification accuracy and pairwise-averaged area under the ROC curve of 90.6. Computational time of XGBoost scaled better to large data than any other SL method. We also show how SHAP values integrated in the R package (xgboost) facilitate investigation of variable relationships and importance. 4. For big data applications, XGBoost appears to provide superior classification accuracy and computational efficiency. Our results suggest XGBoost should be considered as an early modelling option in situations where the intent is to classify millions of animal behaviour observations from environmental predictors and to understand relationships between those predictors and movement behaviours.We also offer a tutorial to assist researchers in implementing this method.

show abstract

Considering behavioral state when predicting habitat use: Behavior-specific spatial models for the endangered Tasmanian wedge-tailed eagle

Pay

Patterson²,

Proft³

et al. 2022

Biological Conservation

View full text Add to dashboard Cite

Linking behavioral states to landscape features for improved conservation management

Abstract: This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

Cited by 4 publications

References 52 publications

Classifying behavior from short‐interval biologging data: An example with GPS tracking of birds

Classifying behavior from short‐interval biologging data: An example with GPS tracking of birds

A review of supervised learning methods for classifying animal behavioural states from environmental features

Considering behavioral state when predicting habitat use: Behavior-specific spatial models for the endangered Tasmanian wedge-tailed eagle

Contact Info

Product

Resources

About