An underwater observation dataset for fish classification and fishery assessment

Erin McCann, Liling Li, Kevin Pangle, Jesse Eickholt

Research output: Contribution to journalArticlepeer-review


Using Dual-Frequency Identification Sonar (DIDSON), fishery acoustic observation data was collected from the Ocqueoc River, a tributary of Lake Huron in northern Michigan, USA. Data were collected March through July 2013 and 2016 and included the identification, via technology or expert analysis, of eight fish species as they passed through the DIDSON’s field of view. A set of short DIDSON clips containing identified fish was curated. Additionally, two other datasets were created that include visualizations of the acoustic data and longer DIDSON clips. These datasets could complement future research characterizing the abundance and behavior of valued fishes such as walleye (Sander vitreus) or white sucker (Catostomus commersonii) or invasive fishes such as sea lamprey (Petromyzon marinus) or European carp (Cyprinus carpio). Given the abundance of DIDSON data and the fact that a portion of it is labeled, these data could aid in the creation of machine learning tools from DIDSON data, particularly for invasive sea lamprey which are amply represented and a destructive invader of the Laurentian Great Lakes.

Original languageEnglish
JournalScientific Data
StatePublished - Oct 9 2018


Dive into the research topics of 'An underwater observation dataset for fish classification and fishery assessment'. Together they form a unique fingerprint.

Cite this