Predicting animal behaviour using deep learning: GPS data alone accurately predict diving in seabirds
Open accessAbstract
To prevent further global declines in biodiversity, identifying and understanding key habitats is crucial for successful conservation strategies. For example, globally, seabird populations are under threat and animal movement data can identify key at‐sea areas and provide valuable information on the state of marine ecosystems. To date, in order to locate these areas, studies have used global positioning system (GPS) to record position and are sometimes combined with time–depth recorder (TDR) devices to identify diving activity associated with foraging, a crucial aspect of at‐sea behaviour. However, the use of additional devices such as TDR s can be expensive, logistically difficult and may adversely affect the animal. Alternatively, behaviours may be resolved from measurements derived from the movement data alone. However, this behavioural analysis frequently lacks validation data for locations predicted as foraging (or other behaviours). Here, we address these issues using a combined GPS and TDR dataset from 108 individuals by training deep learning models to predict diving in European shags, common guillemots and razorbills. We validate our predictions using withheld data, producing quantitative assessment of predictive accuracy. The variables used to train these models are those recorded solely by the GPS device: variation in longitude and latitude, altitude and coverage ratio (proportion of possible fixes acquired within a set window of time). Different combinations of these variables were used to explore the qualities of different models, with the optimum models for all species predicting non‐diving and diving behaviour correctly over 94% and 80% of the time, respectively. We also demonstrate the superior predictive ability of these supervised deep learning models over other commonly used behavioural prediction methods such as hidden Markov models. Mapping these predictions provides useful insights into the foraging activity of a range of seabird species, highlighting important at sea locations. These models have the potential to be used to analyse historic GPS datasets and further our understanding of how environmental changes have affected these seabirds over time.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Various supervised machine learning methods have shown potential in automating behavior analysis from accelerometer data, identifying behavioral state from trajectories, and predicting animal movement.
“Various supervised ML methods have shown their potential in automating behavior analysis from accelerometer data68,69, identifying behavioral state from trajectories70, and predicting animal movement71.”
From Perspectives in machine learning for wildlife conservation (2022) · cites this paper as [68]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
R: A Language and Environment for Statistical Computing
R Core Team (2000) · doi:10.32614/r.manuals · Cited by 355,706 · see citing works
LeCun, Y., Bengio, Y., & Hinton, G. (2015) · Nature · doi:10.1038/nature14539 · Cited by 84,126 · see citing works
A global map of human impact on marine ecosystems
Halpern, B. S., Walbridge, S., Selkoe, K. A., Kappel, C. V., Micheli, F., D'Agrosa, C., Bruno, J. F., Casey, K. S., Ebert, C., Fox, H. E., et al. (2008) · Science · doi:10.1126/science.1149345 · Cited by 6,627 · see citing works
Terrestrial animal tracking as an eye on life and planet
Kays, R., Crofoot, M. C., Jetz, W., & Wikelski, M. (2015) · Science · doi:10.1126/science.aaa2478 · Cited by 1,638 · see citing works
Tracking apex marine predator movements in a dynamic ocean
Block, B., Jonsen, I., Jorgensen, S., Winship, A., Shaffer, S. A., Bograd, S., Hazen, E., Foley, D., Breed, G., Harrison, A.-L., et al. (2011) · Nature · doi:10.1038/nature10082 · Cited by 1,339 · see citing works
Seabird conservation status, threats and priority actions: a global assessment
CROXALL, J. P., BUTCHART, S. H. M., LASCELLES, B., STATTERSFIELD, A. J., SULLIVAN, B., SYMES, A., & TAYLOR, P. (2012) · Bird Conservation International · doi:10.1017/s0959270912000020 · Cited by 1,176 · see citing works
Seabirds as monitors of the marine environment
Furness, R. W. (1997) · ICES Journal of Marine Science · doi:10.1006/jmsc.1997.0243 · Cited by 732 · see citing works
From plankton to top predators: bottom‐up control of a marine food web across four trophic levels
Frederiksen, M., Edwards, M., Richardson, A. J., Halliday, N. C., & Wanless, S. (2006) · Journal of Animal Ecology · doi:10.1111/j.1365-2656.2006.01148.x · Cited by 613 · see citing works
USING FIRST-PASSAGE TIME IN THE ANALYSIS OF AREA-RESTRICTED SEARCH AND HABITAT SELECTION
Fauchald, P., & Tveraa, T. (2003) · Ecology · doi:10.1890/0012-9658(2003)084[0282:ufptit]2.0.co;2 · Cited by 588 · see citing works
How to reliably estimate the tortuosity of an animal's path:
Benhamou, S. (2004) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2004.03.016 · Cited by 586 · see citing works
Misc Functions of the Department of Statistics, ProbabilityTheory Group (Formerly: E1071), TU Wien
MEYER, D. A., Dimitriadou, E., Hornik, K., Weingessel, A., & Leisch, F. (2015) · Cited by 523 · see citing works
Applications of machine learning in animal behaviour studies
Valletta, J. J., Torney, C., Kings, M., Thornton, A., & Madden, J. (2017) · Animal Behaviour · doi:10.1016/j.anbehav.2016.12.005 · Cited by 505 · cited 1× · see citing works
“The computational power requirements and perceived complexity of constructing deep learning networks may have hindered their use in previous studies; Valletta et al. (2017) in their review highlight the potential for using deep learning methods in predictive animal behaviour studies, but conclude…”
BackgroundNathan, R., Spiegel, O., Fortmann‐Roe, S., Harel, R., Wikelski, M. C., & Getz, W. M. (2012) · Journal of Experimental Biology · doi:10.1242/jeb.058602 · Cited by 502 · see citing works
Flexible and practical modeling of animal telemetry data: hidden Markov models and extensions
Langrock, R., King, R., Matthiopoulos, J., Thomas, L., Fortin, D., & Morales, J. M. (2012) · Ecology · doi:10.1890/11-2241.1 · Cited by 465 · see citing works
Michelot, T., Langrock, R., & Patterson, T. A. (2016) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.12578 · Cited by 440 · see citing works
Martiskainen, P., Järvinen, M., Skön, J.-P., Tiirikainen, J., Kolehmainen, M., & Mononen, J. (2009) · Applied Animal Behaviour Science · doi:10.1016/j.applanim.2009.03.005 · Cited by 405 · see citing works
Population Trend of the World’s Monitored Seabirds, 1950-2010
Paleczny, M., Hammill, E., Karpouzi, V., & Pauly, D. (2015) · PLOS ONE · doi:10.1371/journal.pone.0129342 · Cited by 397 · see citing works
Classifying movement behaviour in relation to environmental conditions using hidden Markov models
Patterson, T. A., Basson, M., Bravington, M. V., & Gunn, J. (2009) · Journal of Animal Ecology · doi:10.1111/j.1365-2656.2009.01583.x · Cited by 335 · see citing works
META-ANALYSIS OF ANIMAL MOVEMENT USING STATE-SPACE MODELS
Jonsen, I. D., Myers, R. A., & Flemming, J. M. (2003) · Ecology · doi:10.1890/02-0670 · Cited by 290 · see citing works
GPS Tracking of Foraging Albatrosses
Weimerskirch, H., Bonadonna, F., Bailleul, F., Mabille, G., Dell’Omo, G., & Lipp, H. (2002) · Science · doi:10.1126/science.1068034 · Cited by 249 · see citing works
Guilford, T., Meade, J., Willis, J. K., Phillips, R. A., Boyle, D. E., Roberts, S., Collett, M., Freeman, R., & Perrins, C. M. (2009) · Proceedings of the Royal Society B Biological Sciences · doi:10.1098/rspb.2008.1577 · Cited by 248 · see citing works
Self-citationSeabird foraging ranges as a preliminary tool for identifying candidate Marine Protected Areas
Thaxter, C. B., Lascelles, B., Sugar, K., et al. (2012) · Biological Conservation · doi:10.1016/j.biocon.2011.12.009 · Cited by 231 · see citing works
Breed, G. A., Jonsen, I. D., Myers, R. A., Bowen, W. D., & Leonard, M. L. (2009) · Ecology · doi:10.1890/07-1483.1 · Cited by 217 · see citing works
Using fractal dimensions for characterizing tortuosity of animal trails
Dicke, M., & BURROUGH, P. A. (1988) · Physiological Entomology · doi:10.1111/j.1365-3032.1988.tb01122.x · Cited by 185 · see citing works
Forester, J. D., Ives, A. R., Turner, M. G., Anderson, D. P., Fortin, D., Beyer, H. L., Smith, D. W., & Boyce, M. S. (2007) · Ecological Monographs · doi:10.1890/06-0534 · Cited by 181 · see citing works
A review of the use of seabirds as indicators in fisheries and ecosystem management
Einoder, L. D. (2008) · Fisheries Research · doi:10.1016/j.fishres.2008.09.024 · Cited by 175 · see citing works
Interpolation of animal tracking data in a fluid environment
Tremblay, Y., Shaffer, S. A., Fowler, S. L., Kuhn, C. E., McDonald, B. I., Weise, M. J., Bost, C. A., Weimerskirch, H., Crocker, D. E., Goebel, M. E., et al. (2005) · Journal of Experimental Biology · doi:10.1242/jeb.01970 · Cited by 168 · see citing works
Maxwell, S. M., Breed, G. A., Nickel, B. A., et al. (2011) · PLoS ONE · doi:10.1371/journal.pone.0019905 · Cited by 146 · see citing works
Mallory, M. L., Robinson, S. A., Hebert, C. E., et al. (2009) · Marine Pollution Bulletin · doi:10.1016/j.marpolbul.2009.08.024 · Cited by 145 · see citing works
Wildlife tracking data management: a new vision
Urbano, F., Cagnacci, F., Calenge, C., et al. (2010) · Philosophical Transactions of the Royal Society B Biological Sciences · doi:10.1098/rstb.2010.0081 · Cited by 136 · see citing works
(2004) · Poyser eBooks · doi:10.5040/9781472596840 · Cited by 128 · see citing works
Guilford, T., Meade, J., Freeman, R., Biro, D., Evans, T. J., Bonadonna, F., Boyle, D. E., ROBERTS, S., & Perrins, C. M. (2008) · Ibis · doi:10.1111/j.1474-919x.2008.00805.x · Cited by 120 · see citing works
Self-citationDean, B. J., Freeman, R., Kirk, H. L., Leonard, K., Phillips, R. A., Perrins, C. M., & Guilford, T. (2012) · Journal of The Royal Society Interface · doi:10.1098/rsif.2012.0570 · Cited by 119 · see citing works
Self-citationAnalysis of movements and behavior of caribou (Rangifer tarandus) using hidden Markov models
Franke, A., Caelli, T., & Hudson, R. J. (2003) · Ecological Modelling · doi:10.1016/j.ecolmodel.2003.06.004 · Cited by 119 · see citing works
Sustained disruption of narwhal habitat use and behavior in the presence of Arctic killer whales
Breed, G. A., Matthews, C. J. D., Marcoux, M., Higdon, J. W., Leblanc, B., Petersen, S. D., Orr, J. R., Reinhart, N. R., & Ferguson, S. H. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611707114 · Cited by 109 · see citing works
Grünewälder, S., Broekhuis, F., Macdonald, D. W., et al. (2012) · PLoS ONE · doi:10.1371/journal.pone.0049120 · Cited by 100 · see citing works
A state–space model to derive bluefin tuna movement and habitat from archival tags
Royer, F., Fromentin, J., & Gaspar, P. (2005) · Oikos · doi:10.1111/j.0030-1299.2005.13777.x · Cited by 97 · see citing works
Supervised accelerometry analysis can identify prey capture by penguins at sea
Carroll, G., Slip, D. J., Jonsen, I. D., & Harcourt, R. G. (2014) · Journal of Experimental Biology · doi:10.1242/jeb.113076 · Cited by 91 · see citing works
State-space methods for more completely capturing behavioral dynamics from animal tracks
Breed, G. A., da Costa, D. P., Jonsen, I. D., et al. (2012) · Ecological Modelling · doi:10.1016/j.ecolmodel.2012.03.021 · Cited by 89 · see citing works
Thaxter, C. B., Wanless, S., Daunt, F., et al. (2010) · Journal of Experimental Biology · doi:10.1242/jeb.037390 · Cited by 87 · see citing works
(2005) · Choice Reviews Online · doi:10.5860/choice.42-2814 · Cited by 83 · see citing works
GPS tracking devices reveal foraging strategies of Black-legged Kittiwakes
Kotzerka, J., Garthe, S., & Hatch, S. A. (2009) · Journal für Ornithologie · doi:10.1007/s10336-009-0479-y · Cited by 70 · see citing works
Positional entropy during pigeon homing I: application of Bayesian latent state modelling
Roberts, S., Guilford, T., Rezek, I. A., et al. (2004) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2003.07.002 · Cited by 54 · see citing works
Self-citationA new multi-scale measure for analysing animal movement data
Postlethwaite, C., Brown, P., & Dennis, T. E. (2012) · Journal of Theoretical Biology · doi:10.1016/j.jtbi.2012.10.007 · Cited by 53 · see citing works
Evaluating the statistical power of detecting changes in the abundance of seabirds at sea
Maclean, I. M. D., Rehfisch, M. M., Skov, H., et al. (2012) · Ibis · doi:10.1111/j.1474-919x.2012.01272.x · Cited by 53 · see citing works
Freeman, R., Dean, B. J., Kirk, H. L., et al. (2013) · Journal of The Royal Society Interface · doi:10.1098/rsif.2013.0279 · Cited by 45 · see citing works
Self-citationForaging behaviour of sympatric razorbills and puffins
Shoji, A., Elliott, K., Fayet, A. L., Boyle, D., Perrins, C. M., & Guilford, T. (2014) · Marine Ecology Progress Series · doi:10.3354/meps11080 · Cited by 45 · see citing works
Self-citationDean, B. J., Kirk, H. L., Fayet, A. L., Shoji, A., Freeman, R., Leonard, K., Perrins, C. M., & Guilford, T. (2015) · Marine Ecology Progress Series · doi:10.3354/meps11443 · Cited by 45 · see citing works
Self-citationRemotely sensed wind speed predicts soaring behaviour in a wide-ranging pelagic seabird
Gibb, R., Shoji, A., Fayet, A. L., Perrins, C. M., Guilford, T., & Freeman, R. (2017) · Journal of The Royal Society Interface · doi:10.1098/rsif.2017.0262 · Cited by 43 · see citing works
Self-citationMeier, R., Wynn, R. B., Votier, S., Grivé, M. M., Rodríguez, A., Maurice, L., van Loon, E. V., Jones, A., Suberg, L., Arcos, J. M., et al. (2015) · Biological Conservation · doi:10.1016/j.biocon.2015.05.012 · Cited by 42 · see citing works
Self-citationUse of time-at-depth recorders for estimating depth and diving performance of European shags.
Wanless, S., Harris, M. P., Burger, A. E., et al. (1997) · Digital Commons - University of South Florida (University of South Florida) · Cited by 23 · see citing works
Foraging flexibility and search patterns are unlinked during breeding in a free-ranging seabird
Shoji, A., Aris‐Brosou, S., Owen, E., et al. (2016) · Marine Biology · doi:10.1007/s00227-016-2826-x · Cited by 18 · see citing works
Self-citationBrowning, E., Bolton, M., Owen, E., et al. (2017) · Data Archiving and Networked Services (DANS) · doi:10.5061/dryad.t7ck5 · Cited by 2 · see citing works
Self-citation
Flagged first, then by citations
Research works printed but not linked: 1
- BirdLife International. (2010). Marine important bird areas toolkit: Standardised techniques for identifying priority sites for the conservation of seabirds at-sea. Cambridge, UK: BirdLife International.
Cited by
Sorted by citations
Perspectives in machine learning for wildlife conservation
Tuia, D., Kellenberger, B., Beery, S., Costelloe, B. R., Zuffi, S., Risse, B., Mathis, A., Mathis, M. W., van Langevelde, F., Burghardt, T., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-27980-y · Cited by 740 · see citing works
Applications for deep learning in ecology
Christin, S., Hervet, É., & Lecomte, N. (2019) · Methods in Ecology and Evolution · doi:10.1111/2041-210x.13256 · Cited by 724 · see citing works
Optimizing the use of biologgers for movement ecology research
Williams, H. J., Taylor, L. A., Benhamou, S., Bijleveld, A. I., Clay, T. A., de Grissac, S., Demšar, U., English, H. M., Franconi, N., Gómez‐Laich, A., et al. (2020) · Journal of Animal Ecology · doi:10.1111/1365-2656.13094 · Cited by 333 · see citing works
A review of Earth Artificial Intelligence
Sun, Z., Sandoval, L., Crystal-Ornelas, R., Mousavi, S. M., Wang, J., Lin, C., Cristea, N., Tong, D., Carande, W. H., Ma, X., et al. (2022) · Computers & Geosciences · doi:10.1016/j.cageo.2022.105034 · Cited by 271 · see citing works
- Authors
- Browning, E., Bolton, M., Owen, E., Shoji, A., Guilford, T., & Freeman, R.
- Affiliations
- Zoological Society of London (GB)
- Royal Society for the Protection of Birds (GB)
- University of Oxford (GB)
- Corresponding author
- Browning, Ella
- Freeman, Robin
- Venue
- Methods in Ecology and Evolution
- Publisher
- Wiley
- Published
- 2017-11-20
- Volume
- 9
- Issue
- 3
- Pages
- 681-692
- ISSN
- 2041-210X (ISSN-L)
- OpenAlex
- W2766023553
- Cited by
- 107
- References
- 53
- Citations by year
- 2026: 6 · 2025: 6 · 2024: 14 · 2023: 7 · 2022: 17 · 2021: 28 · 2020: 8 · 2019: 15 · 2018: 6
- FWCI
- 5.98
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Methods in Ecology and Evolution (publishedVersion, cc-by)
- UCL Discovery (University College London) (submittedVersion)
- Funders
- Natural Environment Research Council (NE/L002485/1)
- Topics
- Physical Sciences › Environmental Science › Ecology › Avian ecology and behavior
- Physical Sciences › Environmental Science › Ecology › Marine animal studies overview
- Physical Sciences › Environmental Science › Ecology › Wildlife Ecology and Conservation
- Keywords
- GPS tracking, time-depth recorders, foraging behavior, European shag, common guillemot, razorbill, deep learning, marine conservation, hidden Markov models, animal movement
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
