Hidden Markov models identify major movement modes in accelerometer and magnetometer data from four albatross species

Melinda G Conners,Théo Michelot,Scott A Shaffer,Richard A Phillips,Rachael A Orben,Alexei L Vyssotski,Eleanor I Heywood,Lesley H Thorne

doi:10.1186/s40462-021-00243-z

Abstract

BackgroundInertial measurement units (IMUs) with high-resolution sensors such as accelerometers are now used extensively to study fine-scale behavior in a wide range of marine and terrestrial animals. Robust and practical methods are required for the computationally-demanding analysis of the resulting large datasets, particularly for automating classification routines that construct behavioral time series and time-activity budgets. Magnetometers are used increasingly to study behavior, but it is not clear how these sensors contribute to the accuracy of behavioral classification methods. Development of effective classification methodology is key to understanding energetic and life-history implications of foraging and other behaviors.MethodsWe deployed accelerometers and magnetometers on four species of free-ranging albatrosses and evaluated the ability of unsupervised hidden Markov models (HMMs) to identify three major modalities in their behavior: ‘flapping flight’, ‘soaring flight’, and ‘on-water’. The relative contribution of each sensor to classification accuracy was measured by comparing HMM-inferred states with expert classifications identified from stereotypic patterns observed in sensor data.ResultsHMMs provided a flexible and easily interpretable means of classifying behavior from sensor data. Model accuracy was high overall (92%), but varied across behavioral states (87.6, 93.1 and 91.7% for ‘flapping flight’, ‘soaring flight’ and ‘on-water’, respectively). Models built on accelerometer data alone were as accurate as those that also included magnetometer data; however, the latter were useful for investigating slow and periodic behaviors such as dynamic soaring at a fine scale.ConclusionsThe use of IMUs in behavioral studies produces large data sets, necessitating the development of computationally-efficient methods to automate behavioral classification in order to synthesize and interpret underlying patterns. HMMs provide an accessible and robust framework for analyzing complex IMU datasets and comparing behavioral variation among taxa across habitats, time and space.

Highlights

Inertial measurement units (IMUs) with high-resolution sensors such as accelerometers are used extensively to study fine-scale behavior in a wide range of marine and terrestrial animals
We evaluated the utility of Hidden Markov Model (HMM) to classify major movement modes from magnetometer and accelerometer data collected from flying birds using four species of albatross as a case study
The trimmed standardized dataset provided a total of 239,564,250 data points summarized into a final dataset of 319,409 observations of each feature as HMM input (Table 1)

Summary

Introduction

Inertial measurement units (IMUs) with high-resolution sensors such as accelerometers are used extensively to study fine-scale behavior in a wide range of marine and terrestrial animals. Robust and practical methods are required for the computationally-demanding analysis of the resulting large datasets, for automating classification routines that construct behavioral time series and time-activity budgets. Accelerometers are popular tools in studies of animal movement, as they are small, affordable, and battery-efficient [8]. They record instantaneous movement and orientation of the animal body at a high resolution, and are a powerful means of decoding real-time behaviors and their functions in free-ranging animals [9, 10]. The instantaneous nature of accelerometer data can be exploited by behavioral classification methods to derive automated and objective behavioral time series [18]; these can be modeled with covariates to assess the drivers of movement and population processes [19]

Methods

Results

Discussion

Conclusion