Underwater Acoustics

Project Overview

It is often unclear to what extent human activities have damaged ocean environments and whether or not our actions have been effective in repairing damaged habitats and restoring marine populations to their former states. Our project aims to address this issue by allowing researchers to monitor trends in sea life over long periods of time. We are working with seven years of acoustic data recorded by a detector deployed following the Deepwater Horizon Oil Spill in the Gulf of Mexico. With this information we seek to create a tool for researchers to gauge how many, how often, and what kinds of fish are passing through the area as time progresses.

Our Approach

Using the seven years worth of acoustic data, our team will continue development of a Convolutional Neural Network that can classify recorded fish noises according to species. The current legacy code base is written in MATLAB and is severely lacking in terms of documentation and code organization. We hope to fix this by eventually delivering a single, intuitive application that is accessible to researchers as well as thoroughly documenting application processes as development continues. Further goals include determining proper metrics for our CNN’s performance as well as improving the CNN according to those metrics. Dr. Sirovic has also expressed interest in eventually generalizing the current Convolutional Neural Network so that it may be used in other fields of study as well.

A Scripps Institute of Oceanography Project

This project is implemented under the guidance of Dr. Ana Sirovic, a researcher at the Marine Acoustics Lab of the Scripps Institute of Oceanography.