Tuna-AI: tuna biomass estimation with Machine Learning models trained on oceanography and echosounder FAD data
This work addresses tuna population monitoring for fisheries management, but it appears incremental as it applies existing ML methods to new data sources.
The researchers tackled the problem of estimating tuna biomass by developing Tuna-AI, a machine learning model that uses echo-sounder and oceanographic data to predict biomass under buoys, achieving training on over 5000 set events with reported tuna catches.
Echo-sounder data registered by buoys attached to drifting FADs provide a very valuable source of information on populations of tuna and their behaviour. This value increases whenthese data are supplemented with oceanographic data coming from CMEMS. We use these sources to develop Tuna-AI, a Machine Learning model aimed at predicting tuna biomass under a given buoy, which uses a 3-day window of echo-sounder data to capture the daily spatio-temporal patterns characteristic of tuna schools. As the supervised signal for training, we employ more than 5000 set events with their corresponding tuna catch reported by the AGAC tuna purse seine fleet.