AUTHOR=Maglietta Rosalia , Caccioppoli Rocco , Piazzolla Daniele , Saccotelli Leonardo , Cherubini Carla , Scagnoli Elena , Piermattei Viviana , Marcelli Marco , De Lucia Giuseppe Andrea , Lecci Rita , Causio Salvatore , Dimauro Giovanni , De Franco Francesco , Scuro Matteo , Coppini Giovanni 

TITLE=Habitat suitability modeling of loggerhead sea turtles in the Central-Eastern Mediterranean Sea: a machine learning approach using satellite tracking data

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 11 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2024.1493598

DOI=10.3389/fmars.2024.1493598

ISSN=2296-7745

ABSTRACT=This study focuses on the design, development and validation of a multidisciplinary framework which uses machine learning algorithms for analyzing the movement patterns, acquired using satellite tags, of seven loggerhead sea turtles (Caretta caretta, Linnaeus 1758) in the Adriatic and Northern Ionian Seas (Central-Eastern Mediterranean Sea). Argos satellite tracking data -enriched with a panel of sixteen environmental variables obtained from the Copernicus Marine Service and EMODnetbathymetry dataset -were analyzed using Random Forest models, obtaining an accuracy of 80.9% when classifying presence versus pseudo-absence of loggerhead sea turtles. Sea bottom depth, surface chlorophyll (chl-a), and mixed layer depth (MLD) were identified as the most influential features in the habitat suitability of these specimens. Moreover, statistically significant differences, evaluated using t-test statistics, were found between coastal and pelagic locations, for the different seasons, in mixed layer depth, chl-a, 3D-clorophyll, salinity and phosphate.Despite the limited number of tagged animals, this study confirms that the distribution pattern of loggerhead sea turtles in the Mediterranean coastal and pelagic areas is influenced mainly by sea water features and productivity, which are related to the potential abundance of prey species. This multidisciplinary framework offers a replicable approach applicable to different species and geographical areas. Furthermore, it will be valuable for analyzing data from a larger number of tagged animals in future studies and establishes a solid foundation for such analyses.