Movement of animals in relation to objects in their environment is important in many areas of ecology and wildlife conservation. Tools for analysis of movement data, however, still remain
rather limited. In previous work, we developed nonlinear regression models for movement in relation to a single landscape feature. Here we greatly expand these previous models by using artificial neural networks. The new models add substantial flexibility and capabilities, including the ability to incorporate multiple factors and covariates. We devise a likelihood-based model fitting procedure that utilizes genetic algorithms.
We demonstrate the approach with movement data for several species in response to roads and urban boundaries. Model selection via AIC indicates that the best approximating models are those that include response to these human-made landscape elements. The proposed methodology can be useful for global positioning system tracking data that are becoming more common in studies of animal movement behavior.