Arijón, MarianelaRodríguez Pérez, DanielGaspar Dellatorre, FernandoSánchez Carnero, Noela2026-01-212026-01-212025-09-16Arijon, Marianela, Rodríguez-Pérez, Daniel, Dellatorre, Fernando Gaspar, Sánchez-Carnero, Noela (2025). “Acoustic monitoring of Undaria pinnatifida forests: first approach using broadband echosounders in Patagonia Argentina”. Marine Environmental Research, 212:107555; DOI: 10.1016/j.marenvres.2025.1075550141-1136https://doi.org/10.1016/j.marenvres.2025.107555https://hdl.handle.net/20.500.14468/31513This is an Accepted Manuscript of an article published by Elsevier in "Marine Environmental Research, 212 (2025):107555", available at: https://doi.org/10.1016/j.marenvres.2025.107555Este es el manuscrito aceptado del artículo publicado por Elsevier en "Marine Environmental Research, 212 (2025):107555", disponible en línea: https://doi.org/10.1016/j.marenvres.2025.107555Undaria pinnatifida (hereafter Undaria) was first recorded in the Southwest Atlantic in 1992 in Golfo Nuevo (GN), Argentina. Since its introduction, in Golfo Nuevo, Argentina, in 1992, Undaria pinnatifida has become a species of significant ecological and economic importance, prompting interest in monitoring its spread and exploitation. This has generated significant interest in assessing its exploitation and monitoring its spread. Acoustic methods have been widely used for underwater vegetation mapping; however our study is the first in this area and the first to use broadband technology in this region. The aim of this study is to assess, for the first time, the performance of a broadband echosounder in detecting Undaria using both a method based on the height and acoustic intensity of Undaria fronds above the seafloor, and a method based on the acoustic signatures across multiple frequencies for target characterization. Supervised classifications were made in both cases using ground-truth data from diver surveys: using random forest and classification trees. The accuracies obtained for above-bottom features were higher than 75 % (kappa = 0.6); and for multi spectral response were even higher (close to 95 %, kappa = 0.89). These results prove broadband echosounders are valuable tools for underwater vegetation detection and promising for benthic habitat classification.eninfo:eu-repo/semantics/embargoedAccess1209 EstadísticaartículoRandom forestClassification treesUndaria pinnatifidaAcoustic dataBroadband signal1879-0291