Dynamic Models of Animal Movement with Spatial Point Process\n Interactions

2015/03/30 by James C. Russell, Russell, James C., Ephraim M. Hanks +3
Environmental Science · Mathematics · #Ecology and Vegetation Dynamics Studies #Morphological variations and asymmetry #Animal Ecology and Behavior Studies

paper · pdf · doi:10.48550/arxiv.1503.08692

Abstract

When analyzing animal movement, it is important to account for interactions\nbetween individuals. However, statistical models for incorporating interaction\nbehavior in movement models are limited. We propose an approach that models\ndependent movement by augmenting a dynamic marginal movement model with a\nspatial point process interaction function within a weighted distribution\nframework. The approach is flexible, as marginal movement behavior and\ninteraction behavior can be modeled independently. Inference for model\nparameters is complicated by intractable normalizing constants. We develop a\ndouble Metropolis-Hastings algorithm to perform Bayesian inference. We\nillustrate our approach through the analysis of movement tracks of guppies\n(Poecilia reticulata)\n

Related

• Multiscale modelling of animal movement with persistent dynamics
• Robustness of movement models: can models bridge the gap between temporal scales of data sets and behavioural processes?
• Statistical modelling of individual animal movement: an overview of key methods and a discussion of practical challenges
• A new family of Gaussian processes for modeling animal movement: application to bat telemetry data
• Animal Movement Models with Mechanistic Selection Functions