Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets
Abstract Background State-space models, such as Hidden Markov Models (HMMs), are increasingly used to classify animal tracks into behavioural states. Typically, step length and turning angles of successive locations are used to infer where and when an animal is resting, foraging, or travelling. Howe...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2023-07-01
|
Series: | Movement Ecology |
Subjects: | |
Online Access: | https://doi.org/10.1186/s40462-023-00401-5 |
_version_ | 1797769300557168640 |
---|---|
author | Sarah Saldanha Sam L. Cox Teresa Militão Jacob González-Solís |
author_facet | Sarah Saldanha Sam L. Cox Teresa Militão Jacob González-Solís |
author_sort | Sarah Saldanha |
collection | DOAJ |
description | Abstract Background State-space models, such as Hidden Markov Models (HMMs), are increasingly used to classify animal tracks into behavioural states. Typically, step length and turning angles of successive locations are used to infer where and when an animal is resting, foraging, or travelling. However, the accuracy of behavioural classifications is seldom validated, which may badly contaminate posterior analyses. In general, models appear to efficiently infer behaviour in species with discrete foraging and travelling areas, but classification is challenging for species foraging opportunistically across homogenous environments, such as tropical seas. Here, we use a subset of GPS loggers deployed simultaneously with wet-dry data from geolocators, activity measurements from accelerometers, and dive events from Time Depth Recorders (TDR), to improve the classification of HMMs of a large GPS tracking dataset (478 deployments) of red-billed tropicbirds (Phaethon aethereus), a poorly studied pantropical seabird. Methods We classified a subset of fixes as either resting, foraging or travelling based on the three auxiliary sensors and evaluated the increase in overall accuracy, sensitivity (true positive rate), specificity (true negative rate) and precision (positive predictive value) of the models in relation to the increasing inclusion of fixes with known behaviours. Results We demonstrate that even with a small informed sub-dataset (representing only 9% of the full dataset), we can significantly improve the overall behavioural classification of these models, increasing model accuracy from 0.77 ± 0.01 to 0.85 ± 0.01 (mean ± sd). Despite overall improvements, the sensitivity and precision of foraging behaviour remained low (reaching 0.37 ± 0.06, and 0.06 ± 0.01, respectively). Conclusions This study demonstrates that the use of a small subset of auxiliary data with known behaviours can both validate and notably improve behavioural classifications of state space models of opportunistic foragers. However, the improvement is state-dependant and caution should be taken when interpreting inferences of foraging behaviour from GPS data in species foraging on the go across homogenous environments. |
first_indexed | 2024-03-12T21:06:00Z |
format | Article |
id | doaj.art-569b8881dfeb4ed58a3c7712a46c1007 |
institution | Directory Open Access Journal |
issn | 2051-3933 |
language | English |
last_indexed | 2024-03-12T21:06:00Z |
publishDate | 2023-07-01 |
publisher | BMC |
record_format | Article |
series | Movement Ecology |
spelling | doaj.art-569b8881dfeb4ed58a3c7712a46c10072023-07-30T11:27:10ZengBMCMovement Ecology2051-39332023-07-0111111510.1186/s40462-023-00401-5Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasetsSarah Saldanha0Sam L. Cox1Teresa Militão2Jacob González-Solís3Institut de Recerca de la Biodiversitat (IRBio), Universitat de Barcelona (UB)Centre National d’Études Spatiales (CNES)Institut de Recerca de la Biodiversitat (IRBio), Universitat de Barcelona (UB)Institut de Recerca de la Biodiversitat (IRBio), Universitat de Barcelona (UB)Abstract Background State-space models, such as Hidden Markov Models (HMMs), are increasingly used to classify animal tracks into behavioural states. Typically, step length and turning angles of successive locations are used to infer where and when an animal is resting, foraging, or travelling. However, the accuracy of behavioural classifications is seldom validated, which may badly contaminate posterior analyses. In general, models appear to efficiently infer behaviour in species with discrete foraging and travelling areas, but classification is challenging for species foraging opportunistically across homogenous environments, such as tropical seas. Here, we use a subset of GPS loggers deployed simultaneously with wet-dry data from geolocators, activity measurements from accelerometers, and dive events from Time Depth Recorders (TDR), to improve the classification of HMMs of a large GPS tracking dataset (478 deployments) of red-billed tropicbirds (Phaethon aethereus), a poorly studied pantropical seabird. Methods We classified a subset of fixes as either resting, foraging or travelling based on the three auxiliary sensors and evaluated the increase in overall accuracy, sensitivity (true positive rate), specificity (true negative rate) and precision (positive predictive value) of the models in relation to the increasing inclusion of fixes with known behaviours. Results We demonstrate that even with a small informed sub-dataset (representing only 9% of the full dataset), we can significantly improve the overall behavioural classification of these models, increasing model accuracy from 0.77 ± 0.01 to 0.85 ± 0.01 (mean ± sd). Despite overall improvements, the sensitivity and precision of foraging behaviour remained low (reaching 0.37 ± 0.06, and 0.06 ± 0.01, respectively). Conclusions This study demonstrates that the use of a small subset of auxiliary data with known behaviours can both validate and notably improve behavioural classifications of state space models of opportunistic foragers. However, the improvement is state-dependant and caution should be taken when interpreting inferences of foraging behaviour from GPS data in species foraging on the go across homogenous environments.https://doi.org/10.1186/s40462-023-00401-5Semi-supervisionHMMBehavioural classificationOpportunistic foragingTropical oceansBehavioural modes |
spellingShingle | Sarah Saldanha Sam L. Cox Teresa Militão Jacob González-Solís Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets Movement Ecology Semi-supervision HMM Behavioural classification Opportunistic foraging Tropical oceans Behavioural modes |
title | Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets |
title_full | Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets |
title_fullStr | Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets |
title_full_unstemmed | Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets |
title_short | Animal behaviour on the move: the use of auxiliary information and semi-supervision to improve behavioural inferences from Hidden Markov Models applied to GPS tracking datasets |
title_sort | animal behaviour on the move the use of auxiliary information and semi supervision to improve behavioural inferences from hidden markov models applied to gps tracking datasets |
topic | Semi-supervision HMM Behavioural classification Opportunistic foraging Tropical oceans Behavioural modes |
url | https://doi.org/10.1186/s40462-023-00401-5 |
work_keys_str_mv | AT sarahsaldanha animalbehaviouronthemovetheuseofauxiliaryinformationandsemisupervisiontoimprovebehaviouralinferencesfromhiddenmarkovmodelsappliedtogpstrackingdatasets AT samlcox animalbehaviouronthemovetheuseofauxiliaryinformationandsemisupervisiontoimprovebehaviouralinferencesfromhiddenmarkovmodelsappliedtogpstrackingdatasets AT teresamilitao animalbehaviouronthemovetheuseofauxiliaryinformationandsemisupervisiontoimprovebehaviouralinferencesfromhiddenmarkovmodelsappliedtogpstrackingdatasets AT jacobgonzalezsolis animalbehaviouronthemovetheuseofauxiliaryinformationandsemisupervisiontoimprovebehaviouralinferencesfromhiddenmarkovmodelsappliedtogpstrackingdatasets |