Automating the Analysis of Fish School Recognition in Echograms in the Bay of Fundy

FORCE uses hydroacoustic echosounder surveys to evaluate the impact of tidal turbines on marine animals in the Bay of Fundy. FORCE use Echoview software to read in the raw sensor data (e.g. voltages) and convert it to a visual representation. Echoview contains some algorithms to detect the bottom of the ocean. However, the FORCE hydroacoustic data is very noisy from several sources including “entrained air” pushed below the surface of the water through turbulence (i.e., eddies, vortices), and irregular surfaces on the bottom of the ocean. In order to analyze the survey data, manual post-processing is currently required to annotate the data. This manual process delays the turnaround to reporting, potential consistency and provides opportunity for inconsistency. Using a newly created automated process, data will be available for reporting in a more timely fashion, allowing for a faster reporting cycle. This project will provide OERA with the ability to automate analysis and reporting of this newly prepared data.
Using a complex series of R scripts initially designed to explore the data, rather than reporting it, the project will adjusted and updated to automate to allow for manual reporting.

Faculty Supervisor:

Stan Matwin;Evangelos Milios

Student:

Partner:

Offshore Energy Research Association of Nova Scotia

Discipline:

Computer science

Sector:

Mining; Professional, scientific and technical services

University:

Dalhousie University

Program: