RT journal article
T1 Assessing topographic features and population abundance in an Antarctic penguin colony through UAV-based deep-learning models
A1 Belyaev, Oleg
A1 Román, Alejandro
A1 Belliure, Josabel
A1 Navarro, Gabriel
A1 Barbero González, Luis Carlos
A1 Tovar Sánchez, Antonio
A2 Ciencias de la Tierra
K1 UAV
K1 Deep-learning
K1 Chinstrap penguin
K1 Pygoscelis antarcticus
K1 Breeding site features
K1 Vapour col
AB Penguins play an essential biochemical role in the Antarctic ecosystem, being the study of their dynamics ofutmost importance to understand their environment, behaviour and populational trends in the current climatechange scenario. In this study, we used multi-rotor Unmanned Aerial Vehicles (UAVs) along the coast of thechinstrap penguin (Pygoscelis antarcticus) colony of Vapour Col (Deception Island, Antarctica) to map potentialsites of biochemical interactions with the surrounding sea water. Several runoff discharge points were identified,where a precise placing of environmental sampling station is suggested. Additionally, UAVs were used incombination with Object Detection Architectures to obtain the chinstrap colony population size. Applying asimulation for clutch initiation dates due to our off-laying peak count, we obtained an estimated range of 13,250to 22,000 breeding pairs in the 2021/2022 breeding season, also suggesting an alternative approach usingchinstrap chicks as proxy to estimate adult numbers. This research shows the utility of UAV-deep learning forenvironment characterization and wildlife monitoring, providing a solid framework for upcoming studies in thearea.
PB Elsevier
SN 1872-826X
YR 2024
FD 2024-09-11
LK http://hdl.handle.net/10498/36041
UL http://hdl.handle.net/10498/36041
LA eng
DS Repositorio Institucional de la Universidad de Cádiz
RD 11-nov-2026