Combining Spatial and Telemetric Features for Learning Animal Movement Models

TL;DR

This paper presents a novel graphical model that combines radio telemetry data with spatial features to improve animal movement tracking and modeling, demonstrating superior performance over existing methods.

Contribution

It introduces a new statistical framework integrating diverse data sources for more accurate and interpretable animal movement models.

Findings

Outperforms existing radio telemetry software in real data applications

Provides an efficient stochastic gradient algorithm for model fitting

Produces accurate location estimates and interpretable movement patterns

Abstract

We introduce a new graphical model for tracking radio-tagged animals and learning their movement patterns. The model provides a principled way to combine radio telemetry data with an arbitrary set of userdefined, spatial features. We describe an efficient stochastic gradient algorithm for fitting model parameters to data and demonstrate its effectiveness via asymptotic analysis and synthetic experiments. We also apply our model to real datasets, and show that it outperforms the most popular radio telemetry software package used in ecology. We conclude that integration of different data sources under a single statistical framework, coupled with appropriate parameter and state estimation procedures, produces both accurate location estimates and an interpretable statistical model of animal movement.