{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T01:03:51Z","timestamp":1779843831864,"version":"3.53.1"},"reference-count":60,"publisher":"The Royal Society","issue":"238","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,27]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The accurate identification of foraging locations is critical for wildlife conservation. While remote sensing and biologging devices provide much of the necessary data, their deployment is often complicated by factors such as weight, battery life and sensor capacity, limiting their effectiveness for long-term tracking of wide-ranging species. In this study, we evaluate the effectiveness of saltwater immersion data from light-level geolocation loggers (global location sensor; GLS) as a predictor of foraging behaviour in a pursuit-diving seabird, the red-footed booby (Sula sula rubripes). Using co-deployed tri-axial acceleration data as a high-resolution benchmark, we compare the performance of deep learning models for classifying dive and non-dive states. Predictions are cross-validated on withheld individuals for generalizability. Using a small pilot dataset, we find that models trained solely on GLS data only slightly underperform those trained on acceleration data despite the resolution discrepancy, classifying the diving behaviours of unseen birds with 93.65% accuracy. These findings suggest that GLS data alone may be sufficient to reliably infer dive events and, by extension, foraging locations, for pursuit-diving seabirds, providing a minimally invasive, scalable method to enrich year-round GLS migratory tracking studies using models derived from co-deployment of GLS and global positioning system devices.<\/jats:p>","DOI":"10.1098\/rsif.2025.0172","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:32:51Z","timestamp":1779841971000},"source":"Crossref","is-referenced-by-count":0,"title":["Deep neural networks to predict foraging behaviour: saltwater immersion data can accurately predict diving in seabirds"],"prefix":"10.1098","volume":"23","author":[{"given":"Luke","family":"Swaby","sequence":"first","affiliation":[{"name":"Imperial College London 1 , ,","place":["London, UK"]},{"name":"Zoological Society of London 2 , ,","place":["London, UK"],"department":["Institute of Zoology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Carr","sequence":"additional","affiliation":[{"name":"Zoological Society of London 2 , ,","place":["London, UK"],"department":["Institute of Zoology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0927-2734","authenticated-orcid":false,"given":"Ruth","family":"Dunn","sequence":"additional","affiliation":[{"name":"Lancaster University 3 , ,","place":["Lancaster, UK"],"department":["Lancaster Environment Centre"]},{"name":"Heriot-Watt University 4 , ,","place":["Edinburgh, UK"],"department":["The Lyell Centre"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malcolm A. C.","family":"Nicoll","sequence":"additional","affiliation":[{"name":"Zoological Society of London 2 , ,","place":["London, UK"],"department":["Institute of Zoology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6459-5213","authenticated-orcid":false,"given":"Alice M.","family":"Trevail","sequence":"additional","affiliation":[{"name":"University of Exeter 5 , ,","place":["Penryn, UK"],"department":["Environment and Sustainability Institute"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephen C.","family":"Votier","sequence":"additional","affiliation":[{"name":"Heriot-Watt University 4 , ,","place":["Edinburgh, UK"],"department":["The Lyell Centre"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah","family":"Wood","sequence":"additional","affiliation":[{"name":"Zoological Society of London 2 , ,","place":["London, UK"],"department":["Institute of Zoology"]},{"name":"Heriot-Watt University 4 , ,","place":["Edinburgh, UK"],"department":["The Lyell Centre"]},{"name":"University of Exeter 5 , ,","place":["Penryn, UK"],"department":["Environment and Sustainability Institute"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0560-8942","authenticated-orcid":false,"given":"Robin","family":"Freeman","sequence":"additional","affiliation":[{"name":"Zoological Society of London 2 , ,","place":["London, UK"],"department":["Institute of Zoology"]},{"name":"University College London 6 , ,","place":["London, UK"],"department":["Centre for Biodiversity and Environment Research"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"175","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"2026052620324883200_R1","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1002\/fee.2125","article-title":"Marine top predators as climate and ecosystem sentinels","volume":"17","author":"Hazen","year":"2019","journal-title":"Front. Ecol. Environ."},{"key":"2026052620324883200_R2","doi-asserted-by":"crossref","DOI":"10.1016\/j.ecolind.2021.107687","article-title":"Isotopic niche plasticity in a marine top predator as indicator of a large marine ecosystem food web status","volume":"126","author":"Ciancio","year":"2021","journal-title":"Ecol. Indic."},{"key":"2026052620324883200_R3","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1023\/A:1016136723584","article-title":"Selecting indicator species to monitor ecological integrity: a review","volume":"78","author":"Carignan","year":"2002","journal-title":"Environ. Monit. Assess."},{"key":"2026052620324883200_R4","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1093\/icesjms\/fsn155","article-title":"Seabirds as indicators of the marine environment","volume":"65","author":"Parsons","year":"2008","journal-title":"ICES J. Mar. Sci."},{"key":"2026052620324883200_R5","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1016\/j.biocon.2011.12.009","article-title":"Seabird foraging ranges as a preliminary tool for identifying candidate Marine Protected Areas","volume":"156","author":"Thaxter","year":"2012","journal-title":"Biol. Conserv."},{"key":"2026052620324883200_R6","first-page":"463","article-title":"Seabirds as bio-indicators of changing marine ecosystems: new perspectives","volume":"14","author":"Bost","year":"1993","journal-title":"Acta Oecologica Int. J. Ecol."},{"key":"2026052620324883200_R7","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1016\/j.fishres.2008.09.024","article-title":"A review of the use of seabirds as indicators in fisheries and ecosystem management","volume":"95","author":"Einoder","year":"2009","journal-title":"Fish. Res."},{"key":"2026052620324883200_R8","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1016\/j.marpolbul.2009.08.024","article-title":"Seabirds as indicators of aquatic ecosystem conditions: a case for gathering multiple proxies of seabird health","volume":"60","author":"Mallory","year":"2010","journal-title":"Mar. Pollut. Bull."},{"key":"2026052620324883200_R9","doi-asserted-by":"crossref","first-page":"1215","DOI":"10.1098\/rspb.2008.1577","article-title":"Migration and stopover in a small pelagic seabird, the Manx shearwater Puffinus puffinus: insights from machine learning","volume":"276","author":"Guilford","year":"2009","journal-title":"Proc. R. Soc. B Biol. Sci."},{"key":"2026052620324883200_R10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3354\/esr00269","article-title":"Biologging technologies: new tools for conservation. Introduction","volume":"10","author":"Bograd","year":"2010","journal-title":"Endang. Species. Res."},{"key":"2026052620324883200_R11","doi-asserted-by":"crossref","DOI":"10.1098\/rsbl.2016.0024","article-title":"Seabird diversity hotspot linked to ocean productivity in the Canary Current Large Marine Ecosystem","volume":"12","author":"Grecian","year":"2016","journal-title":"Biol. Lett."},{"key":"2026052620324883200_R12","doi-asserted-by":"crossref","DOI":"10.1111\/conl.12824","article-title":"Multispecies tracking reveals a major seabird hotspot in the North Atlantic","volume":"14","author":"Davies","year":"2021","journal-title":"Conserv. Lett."},{"key":"2026052620324883200_R13","doi-asserted-by":"crossref","first-page":"155","DOI":"10.3354\/meps14479","article-title":"Multi-colony tracking reveals segregation in foraging range, space use, and timing in a tropical seabird","volume":"724","author":"Trevail","year":"2023","journal-title":"Mar. Ecol. Prog. Ser."},{"key":"2026052620324883200_R14","doi-asserted-by":"crossref","first-page":"5247","DOI":"10.1016\/j.cub.2023.10.060","article-title":"Tracking seabird migration in the tropical Indian Ocean reveals basin-scale conservation need","volume":"33","author":"Trevail","year":"2023","journal-title":"Curr. Biol."},{"key":"2026052620324883200_R15","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1146\/annurev-animal-050322-073657","article-title":"Biologging and biotelemetry: tools for understanding the lives and environments of marine animals","volume":"11","author":"Watanabe","year":"2023","journal-title":"Annu. Rev. Anim. Biosci."},{"key":"2026052620324883200_R16","doi-asserted-by":"crossref","first-page":"462","DOI":"10.1111\/j.1474-919X.2008.00805.x","article-title":"GPS tracking of the foraging movements of Manx shearwaters Puffinus puffinus breeding on Skomer Island, Wales","volume":"150","author":"Guilford","year":"2008","journal-title":"Ibis"},{"key":"2026052620324883200_R17","doi-asserted-by":"crossref","DOI":"10.1098\/rsos.160317","article-title":"Seabird diving behaviour reveals the functional significance of shelf-sea fronts as foraging hotspots","volume":"3","author":"Cox","year":"2016","journal-title":"R. Soc. Open Sci."},{"key":"2026052620324883200_R18","doi-asserted-by":"crossref","first-page":"257","DOI":"10.3354\/meps11080","article-title":"Foraging behaviour of sympatric razorbills and puffins","volume":"520","author":"Shoji","year":"2015","journal-title":"Mar. Ecol. Prog. Ser."},{"key":"2026052620324883200_R19","doi-asserted-by":"crossref","DOI":"10.1098\/rsif.2012.0570","article-title":"Behavioural mapping of a pelagic seabird: combining multiple sensors and a hidden Markov model reveals the distribution of at-sea behaviour","volume":"10","author":"Dean","year":"2013","journal-title":"J. R. Soc. Interface"},{"key":"2026052620324883200_R20","doi-asserted-by":"crossref","DOI":"10.1007\/s00227-024-04445-y","article-title":"From route to dive: multi-scale habitat selection in a foraging tropical seabird","volume":"171","author":"Dunn","year":"2024","journal-title":"Mar. Biol."},{"key":"2026052620324883200_R21","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1111\/j.2041-210X.2010.00013.x","article-title":"Meta-analysis of transmitter effects on avian behaviour and ecology","volume":"1","author":"Barron","year":"2010","journal-title":"Methods Ecol. Evol."},{"key":"2026052620324883200_R22","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.1642\/0004-8038(2003)120[1082:EOSTOA]2.0.CO;2","article-title":"Effects of satellite transmitters on albatrosses and petrels","volume":"120","author":"Phillips","year":"2003","journal-title":"Auk"},{"key":"2026052620324883200_R23","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1046\/j.0269-8463.2001.00606.x","article-title":"The potential costs of flipper-bands to penguins","volume":"16","author":"Jackson","year":"2002","journal-title":"Funct. Ecol."},{"key":"2026052620324883200_R24","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1111\/2041-210X.12934","article-title":"A phylogenetically controlled meta-analysis of biologging device effects on birds: deleterious effects and a call for more standardized reporting of study data","volume":"9","author":"Bodey","year":"2018","journal-title":"Methods Ecol. Evol."},{"key":"2026052620324883200_R25","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1080\/03078698.2022.2151065","article-title":"Acute impacts from Teflon harnesses used to fit biologging devices to black-legged kittiwakes Rissa tridactyla","volume":"36","author":"Clewley","year":"2021","journal-title":"Ringing Migr."},{"key":"2026052620324883200_R26","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1111\/ibi.13247","article-title":"Reduced breeding success in great black-backed gulls (Larus marinus) due to harness-mounted GPS device","volume":"166","author":"Lopez","year":"2024","journal-title":"Ibis"},{"key":"2026052620324883200_R27","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-72199-w","article-title":"Short-term behavioural impact contrasts with long-term fitness consequences of biologging in a long-lived seabird","volume":"10","author":"Gillies","year":"2020","journal-title":"Sci. Rep."},{"key":"2026052620324883200_R28","volume-title":"The migration ecology of birds","author":"Newton","year":"2010"},{"key":"2026052620324883200_R29","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0041195","article-title":"Migration routes and strategies in a highly aerial migrant, the common swift Apus apus, revealed by light-level geolocators","volume":"7","author":"\u00c5kesson","year":"2012","journal-title":"PLoS One"},{"key":"2026052620324883200_R30","doi-asserted-by":"crossref","first-page":"2243","DOI":"10.1111\/2041-210X.13698","article-title":"Double-tagging scores of seabirds reveals that light-level geolocator accuracy is limited by species idiosyncrasies and equatorial solar profiles","volume":"12","author":"Halpin","year":"2021","journal-title":"Methods Ecol. Evol."},{"key":"2026052620324883200_R31","doi-asserted-by":"crossref","first-page":"265","DOI":"10.3354\/meps266265","article-title":"Accuracy of geolocation estimates for flying seabirds","volume":"266","author":"Phillips","year":"2004","journal-title":"Mar. Ecol. Prog. Ser."},{"key":"2026052620324883200_R32","doi-asserted-by":"crossref","first-page":"2874","DOI":"10.1890\/04-1852","article-title":"Robust state\u2013space modeling of animal movement data","volume":"86","author":"Jonsen","year":"2005","journal-title":"Ecology"},{"key":"2026052620324883200_R33","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1111\/j.1365-2656.2009.01583.x","article-title":"Classifying movement behaviour in relation to environmental conditions using hidden Markov models","volume":"78","author":"Patterson","year":"2009","journal-title":"J. Anim. Ecol."},{"key":"2026052620324883200_R34","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1016\/j.ecolmodel.2012.03.021","article-title":"State-space methods for more completely capturing behavioral dynamics from animal tracks","volume":"235\u2013236","author":"Breed","year":"2012","journal-title":"Ecol. Model."},{"key":"2026052620324883200_R35","doi-asserted-by":"crossref","first-page":"986","DOI":"10.1242\/jeb.058602","article-title":"Using tri-axial acceleration data to identify behavioral modes of free-ranging animals: general concepts and tools illustrated for griffon vultures","volume":"215","author":"Nathan","year":"2012","journal-title":"J. Exp. Biol."},{"key":"2026052620324883200_R36","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1016\/j.applanim.2009.03.005","article-title":"Cow behaviour pattern recognition using a three-dimensional accelerometer and support vector machines","volume":"119","author":"Martiskainen","year":"2009","journal-title":"Appl. Anim. Behav. Sci."},{"key":"2026052620324883200_R37","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0049120","article-title":"Movement activity based classification of animal behaviour with an application to data from cheetah (Acinonyx jubatus)","volume":"7","author":"Gr\u00fcnew\u00e4lder","year":"2012","journal-title":"PLoS One"},{"key":"2026052620324883200_R38","first-page":"4295","article-title":"Supervised accelerometry analysis can identify prey capture by penguins at sea","volume":"217","author":"Carroll","year":"2014","journal-title":"J. Exp. Biol."},{"key":"2026052620324883200_R39","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural networks for pattern recognition","author":"Bishop","year":"1995"},{"key":"2026052620324883200_R40","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"2026052620324883200_R41","first-page":"851","article-title":"Deep learning in bioinformatics","volume":"18","author":"Min","year":"2017","journal-title":"Briefings Bioinform."},{"key":"2026052620324883200_R42","doi-asserted-by":"crossref","first-page":"1632","DOI":"10.1111\/2041-210X.13256","article-title":"Applications for deep learning in ecology","volume":"10","author":"Christin","year":"2019","journal-title":"Methods Ecol. Evol."},{"key":"2026052620324883200_R43","doi-asserted-by":"crossref","first-page":"1640","DOI":"10.1111\/2041-210X.13901","article-title":"Deep learning as a tool for ecology and evolution","volume":"13","author":"Borowiec","year":"2022","journal-title":"Methods Ecol. Evol."},{"key":"2026052620324883200_R44","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1111\/2041-210X.12926","article-title":"Predicting animal behaviour using deep learning: GPS data alone accurately predict diving in seabirds","volume":"9","author":"Browning","year":"2018","journal-title":"Methods Ecol. Evol."},{"key":"2026052620324883200_R45","doi-asserted-by":"crossref","first-page":"802","DOI":"10.1111\/2041-210X.13172","article-title":"A novel biomechanical approach for animal behaviour recognition using accelerometers","volume":"10","author":"Chakravarty","year":"2019","journal-title":"Methods Ecol. Evol."},{"key":"2026052620324883200_R46","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1111\/1365-2656.13040","article-title":"Estimates for energy expenditure in free-living animals using acceleration proxies: a reappraisal","volume":"89","author":"Wilson","year":"2020","journal-title":"J. Anim. Ecol."},{"key":"2026052620324883200_R47","volume-title":"The sulidae: gannets and boobies (no.154)","author":"Nelson","year":"1978"},{"key":"2026052620324883200_R48","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s40462-021-00251-z","article-title":"Interspecific and intraspecific foraging differentiation of neighbouring tropical seabirds","volume":"9","author":"Austin","year":"2021","journal-title":"Mov. Ecol."},{"key":"2026052620324883200_R49","volume-title":"R: a language and environment for statistical computing","author":"R Core Team","year":"2021"},{"key":"2026052620324883200_R50","doi-asserted-by":"crossref","first-page":"53","DOI":"10.1098\/rspb.2004.2918","article-title":"The three-dimensional flight of red-footed boobies: adaptations to foraging in a tropical environment?","volume":"272","author":"Weimerskirch","year":"2005","journal-title":"Proc. R. Soc. B Biol. Sci."},{"key":"2026052620324883200_R51","first-page":"196","article-title":"The red-footed booby on Aldabra Atoll, Indian Ocean","volume":"62","author":"Diamond","year":"1974","journal-title":"Ardea"},{"key":"2026052620324883200_R52","unstructured":"Pitman\n              R\n            , BallanceL. 1993Booby prey-capturing behavior in the eastern tropical Pacific. InAbstract. Pacific Seabird Group 20th Annual Meeting. Seattle, WA: Pacific Seabird Group."},{"key":"2026052620324883200_R53","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"2026052620324883200_R54","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1009890","article-title":"Deep inference of seabird dives from GPS-only records: performance and generalization properties","volume":"18","author":"Roy","year":"2022","journal-title":"PLoS Comput. Biol."},{"key":"2026052620324883200_R55","doi-asserted-by":"crossref","DOI":"10.1111\/jav.02869","article-title":"Dynamic body acceleration improves mapping of at-sea foraging behavior in black-tailed gulls Larus crassirostris","volume":"2022","author":"Ma","year":"2022","journal-title":"J. Avian Biol."},{"key":"2026052620324883200_R56","doi-asserted-by":"crossref","DOI":"10.1098\/rsif.2013.0279","article-title":"Predictive ethoinformatics reveals the complex migratory behaviour of a pelagic seabird, the Manx shearwater","volume":"10","author":"Freeman","year":"2013","journal-title":"J. R. Soc. Interface"},{"key":"2026052620324883200_R57","unstructured":"Birdlife International\n          . 2024Seabird tracking database: a platform for seabird researchers to share their tracking data with the research and conservation communities. Seehttps:\/\/www.seabirdtracking.org\/ (accessed5-February-2024)."},{"key":"2026052620324883200_R58","article-title":"robinfreeman\/seabirds_dive_predict: seabirds dive prediction (v1.0.0). Zenodo","author":"Swaby","year":"2026"},{"key":"2026052620324883200_R59","article-title":"Data for: Deep neural networks to predict foraging behaviour: salt-water immersion data can accurately predict diving in seabirds. Harvard Dataverse, V1","author":"Freeman","year":"2025"},{"key":"2026052620324883200_R60","article-title":"Supplementary material from: Deep neural networks to predict foraging behaviour: salt-water immersion data can accurately predict diving in seabirds. Figshare.","author":"Swaby","year":"2026"}],"container-title":["Journal of the Royal Society Interface"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article-pdf\/doi\/10.1098\/rsif.2025.0172\/6141184\/rsif.2025.0172.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article-pdf\/doi\/10.1098\/rsif.2025.0172\/6141184\/rsif.2025.0172.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:33:01Z","timestamp":1779841981000},"score":1,"resource":{"primary":{"URL":"https:\/\/royalsocietypublishing.org\/rsif\/article\/23\/238\/20250172\/481915\/Deep-neural-networks-to-predict-foraging-behaviour"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":60,"journal-issue":{"issue":"238","published-print":{"date-parts":[[2026,5,27]]}},"URL":"https:\/\/doi.org\/10.1098\/rsif.2025.0172","relation":{},"ISSN":["1742-5662"],"issn-type":[{"value":"1742-5662","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]},"article-number":"20250172"}}