Exploring the promise of broadband fisheries echosounders for species discrimination with quantitative assessment of data processing effects.

It remains an open question how well the increased bandwidth afforded by broadband echosounders can improve species discrimination in fisheries acoustics. Here, an objective statistical approach was used to determine if there is information available in dual channel broadband data (45-170 kHz) to allow discrimination between in situ echoes obtained from monospecific aggregations of three species (hake, Merluccius productus: anchovy, Engraulis mordax; and krill, Euphausiia pacifica) using a remotely operated vehicle. These data were used to explore the effects of processing choices on the ability to statistically classify the broadband spectra to species. This ability was affected by processing choices including the Fourier transform analysis window size, available bandwidth, and the method and scale of data averaging. The approach to normalizing the spectra and the position of individual targets in the beam, however, had little effect. Broadband volume backscatter and single target spectra were both used to successfully classify acoustic data from these species with ∼6% greater success using volume backscatter data. Broadband data were effectively classified to species while simulated multi-frequency narrowband data were categorized at rates near chance, supporting the presumption that greater bandwidth increases the information available for the characterization and classification of biological targets.