M. Navarro García, D. Precioso, K. Gavira O’Neill, A. Torres Barrán, D. Gordo, V. Gallego, D. Gómez-Ullate Oteiza
In this talk we present Tun-AI, a new pipeline for estimating tuna biomass aggregated at drifting Fish Aggregating Devices (dFADs), i.e., floating objects drifting in the sea surface equipped with an echo-sounder and GPS communication devices. For the first time, echo-sounder buoy data are enriched with oceanographic and position-derived features and with real catch information provided by the Spanish tropical tuna purse seine fleet, which are used to train Machine Learning models that solve different tasks relevant to fisheries operations. These improved biomass estimations could be used to enhance knowledge on species distribution or better understanding many tuna aggregation dynamics processes, and we apply them to study the aggregation behavior of tuna schools to the dFADs.
Palabras clave: Data Science, Machine Learning, Oceanography, Smoothing
Programado
Sesión Invitada RSME-SEIO. Investigación matemática aplicada a la sostenibilidad de la industria pesquera y transporte marítimo
8 de junio de 2022 16:00
A11
