Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning

Abstract

Focal animal sampling and continuous recording of behavior in situ are essential in the study of ecology. However, observation gaps and missing records are unavoidable because the focal individual can move out of sight and recording devices do not always work properly. Using an inverse reinforcement learning (IRL) framework, we have developed a novel gap-filling method to predict the most likely route that an animal would have traveled; within this framework, an algorithm learns a reward function from animal trajectories to find the environmental features preferred by the animal. We applied this approach to GPS trajectories obtained from streaked shearwaters (Calonectris leucomelas) and provide evidence of the advantages of the IRL approach over previously used interpolation methods. These advantages are as follows: (1) No assumptions about the parametric distribution governing movements are needed, (2) no assumptions regarding landscape preferences and restrictions are needed, and (3) large spatiotemporal gaps can be filled. This work demonstrates how IRL can enhance the ability to fill gaps in animal trajectories and construct reward-space maps in heterogeneous environments. The proposed methodology can assist movement research, which seeks to understand phenomena that are ecologically and evolutionarily significant, such as habitat selection and migration.

Internet of Things for evaluating foraging and feeding behavior of cattle on grassland-based farming systems: concepts and review of sensor technologies

“…The ultimate goal is to suggest managerial options to the farmer. Specialized grassland management techniques allow farmers to improve the decision-making process by applying sound principles and guidelines for managing cattle grazing in the grazing lands [86]. To this end, behavioral models for a pasture-based dairy cow from GPS data can be developed.…”

Visual analytics of sensor movement data for cheetah behaviour analysis

“…Browning et al (2018) employ deep learning on GPS movement data to analyse foraging behaviour of seabirds and conclude that the GPS data alone is sufficient for accurate prediction. Hirakawa et al (2018) investigate the use of machine learning for filling the gaps in movement recordings of streaked shearwater birds. Their conclusion is that their method can predict realistic paths without assumptions on the parametric distribution of the movement.…”

A review of methods to model route choice behavior of bicyclists

“…Hirakawa et al [8] use maximum entropy IRL to learn from bird behaviour. As birds are equipped with GPS loggers but gaps may occur due to unavoidable issues with the equipment, a method is needed to fill those gaps with the most likely trajectory.…”