A Correlated Three-Dimensional Integral Fractional Ornstein-Uhlenbeck Process Model for Animal Movement
Predicting the paths of animals poses a significant challenge, given the intricate nature of their behaviors, the impact of unpredictable environmental elements, individual differences, and the scarcity of precise data on their movements.
Overview
Abstract
Predicting the paths of animals poses a significant challenge, given the intricate nature of their behaviors, the impact of unpredictable environmental elements, individual differences, and the scarcity of precise data on their movements. Furthermore, complexities arise from factors like migration, hunting, reproduction, and social interactions, making it even more challenging to precisely predict their trajectories. Various models in the literature attempt to investigate animal telemetry by either modeling the velocity, the telemetry data, or both concurrently using Gaussian processes. In this work, we consider 3D trajectories with coordinate axes corresponding to longitude, latitude and altitude. We propose to model the velocity of each coordinate axis for animal telemetry data as correlated fractional Ornstein-Uhlenbeck (cfOU) processes. We develop a fast simulation algorithm of telemetry trajectories using an approach via finite-dimensional distributions. We use the maximum likelihood method for parameter estimation. Finally, we present a 3D telemetry application of bats that disperse close to Germany.
Brief Biography
Jose Hermenegildo Ramirez Gonzalez finished his PhD studies at CIMAT, Mexico in 2023. He is interested in topics related to particle systems in random environments and population dynamics. He is currently in his first year of postdoc and he is working on stochastic processes related to animal telemetry.