IATTC staff publish new study developing new method to predict purse-seine set type

Management of large-scale tuna
purse-seine fisheries often involves consideration of set type because the differnt set type yield different target species and bycatch species compositions, and may therefore impact those populations differently. Using machine learning methods, annual models were developed to precict set type using on a suite of operational characteristics, and catch and bycatch information, collected by onboard observers for the tropical tuna purse-seine fishery in the eastern Pacific Ocean (EPO) during 2010 yo 2019. Two types of models were developed for each year: 1) one for data from set on unassociated tuna schools (NOA) and sets on floating-object-associated tuna (OBJ); and, 2) one for all three types of sets that occur in the EPO, which includes sets on marine mammal-associated tuna. In general, the models had relatively low error rates, which indicated that such data can be used to reliably distinguish between purse-seine sets types, highlighting inherent operational and ecological differences among them in the EPO. In particular, for the 2-set type model, on average, only 3.3% of NOA sets and 4.5% of OBJ sets were misclassified. The most useful bycatch information for predicting set type included amounts of dorado, wahoo, small fish species, such a triggerfishes, and silky sharks, illustrating the importance of bycatch data collection by onboard observers, even for species of no commercial value. In the case of the two-set type model, the annual error rates for NOA and OBJ sets were not only small, but also fairly stable over the 10-year period, despite the presence of the strong 2015-2016 El Niño event. This suggests that the methodology is robust and could be used to validate set type determinations based on other criteria, such as distance to a floating object (or a fish aggregating device), and to verify data quality, more generally.