loading page

Validating hidden Markov models for seabird behavioural inference
  • +4
  • Rebecca Akeresola,
  • Ruth King,
  • Gail Robertson,
  • Adam Butler,
  • Víctor Elvira,
  • Esther Jones,
  • Julie Black
Rebecca Akeresola
The University of Edinburgh

Corresponding Author:[email protected]

Author Profile
Ruth King
The University of Edinburgh
Author Profile
Gail Robertson
Biomathematics and Statistics Scotland
Author Profile
Adam Butler
Biomathematics and Statistics Scotland
Author Profile
Víctor Elvira
The University of Edinburgh
Author Profile
Esther Jones
Biomathematics and Statistics Scotland
Author Profile
Julie Black
Joint Nature Conservation Committee
Author Profile

Abstract

Understanding animal movement and behaviour can aid spatial planning and inform conservation management. However, it is difficult to directly observe behaviours in remote and hostile terrain such as the marine environment. Behaviours can be inferred from telemetry data using hidden Markov models (HMMs), but model predictions are not typically validated due to difficulty obtaining ‘ground truth’ behavioural information. We investigate the accuracy of HMM-inferred behaviours by considering a unique dataset provided by Joint Nature Conservation Committee. The data consist of simultaneous proxy movement tracks of the boat (defined as visual tracks as birds are followed by eye) and seabird behaviour obtained at the same time-frequency by observers on the boat. We use these data to assess whether (i) visual track is a good proxy for true bird locations in relation to HMM-inferred behaviours, and (ii) inferred behaviours from HMMs fitted to visual tracking data accurately represent true behaviours as identified by behavioural observations taken from the boat. We demonstrate that visual tracking data can be regarded as a good proxy for true movement data of birds in terms of similarity in inferred behaviours. Accuracy of HMMs ranging from 71% to 87% during chick-rearing and 54% to 70% during incubation was generally insensitive to model choice, even when AIC values varied substantially across different models. Finally, we show that for foraging, a state of primary interest for conservation purposes, identified missed foraging bouts lasted for only a few seconds. We conclude that HMMs fitted to tracking data can accurately identify important conservation-relevant behaviours, demonstrated using visual tracking data. Therefore, confidence in using HMMs for behavioural inference should increase even when validation data are unavailable. This has important implications for animal conservation, where the size and location of protected areas are often informed by behaviours identified using HMMs fitted to movement data.
Submitted to Ecology and Evolution
06 Feb 20241st Revision Received
07 Feb 2024Review(s) Completed, Editorial Evaluation Pending
22 Feb 2024Editorial Decision: Accept