Centre for research-based innovation in marine acoustic abundance estimation and backscatter classification

Informations

Funding country

Norway

Acronym

CRIMAC

URL

-

Start date

1/1/2020

End date

12/31/2028

Budget

11,808,000 EUR

Fundings

Abstract

CRIMAC will improve and automate the interpretation of data and images from modern broadband acoustics on research vessels and fishing boats by using cruises and experimental field research, artificial intelligence, drones and inspection technology. The primary objective of the SFI is to advance the frontiers in fisheries acoustic methodology and associated optical methods, and to apply such methods to 1) surveys for marine organisms, 2) fisheries, 3) aquaculture and 4) the energy sector. What are and how do the various parts of marine organisms contribute to broadband backscatter? Complex broadband frequency responses from marine organisms are explored through various numerical models and methods for signal processing. The acoustic properties of mesopelagic fish are important for improving global abundance estimates, and effects of shear viscosity on resonance and target strength of mesopelagic (Khodabandeloo et al., 2021c) and estimation of swimbladder shape (Khodabandeloo et al., 2022) have been published. A software library documenting the signal processing stages of the Simrad EK80 broadband sonar has been developed. The library will be published under an open source license. This is used to control the quality of the Institute of Marine Research's acoustic processing tools, and it is used by CodeLab in their work towards the energy sector. "Leakage" of energy between frequencies has been studied (Khodabandeloo et al., 2021a), and this has been used to update the procedures for the collection of broadband data for scientific missions. What are the broadband frequency responses of marine organisms and other scatterers? Broad band data from mackerel, herring and demersal fish, from probes and ship-based echo sounders, from research vessels and fishing vessels have been collected. These observations are used to build CRIMAC's library for validated targets. Measuring the size of fish is important for the fishing industry, the fish farming industry and for scientific surveys, and we are working with various strategies to estimate length from the broadbanded signal. A net-pen experiment has been carried out on salmon with no access to air for filling their swim bladders, and the broadband signal is monitored over time. Three master theses have been completed based on this experiment (Rong, 2022). Work on the calibration of echo sounders is an important component, and procedures for calibrating broadband echo sounders with different calibration spheres have started. Can machine learning techniques reliably and accurately categorize acoustic backscatter? Modern machine learning algorithms can be used on large volumes on historical acoustic data, and datasets from long time series of acoustic surveys have been established. We have investigated how different preprocessing algorithms affect the performance of the algorithms (Ordoñez et al., 2022). Various algorithms to improve the performance of machine learning algorithms for acoustic species classification have been tested, including semi-supervised algorithms (Choi et al., 2021b). Different echosounder frequencies are used by the algorithms to classify species, and a master's thesis has reviewed which frequencies are important (Holager, 2022). How to utilize acoustic sensors on autonomous platforms, assess uncertainty and utilize the effect of behaviour on acoustic backscatter? The introduction of autonomous or remotely controlled platforms provides an efficient way to deploy acoustic sensors. The platforms can either be driven independently or together with ships. They can be deployed for several objectives, including scout vessels for fishing operations and to extend RV-based acoustic surveys. The kayak drone developed by HI (Totland and Johnsen, 2022) and the Sounder platform developed by Kongsberg will be used in the centre. Different approaches to using these platforms will be explored, including different static and adaptive experimental setups.