Application of a machine learning approach for effective stock management of abalone (Old ID 26742)

Fisheries Research & Development Corporation
Role

Principal Investigator

Description

Determining the number and size distribution of abalone present at various stages of production is critical information for effective stock management. Currently the Australian abalone aquaculture industry spends in the order of $25,000 per annum, per farm, gathering this information by hand. However, the resulting data is of mediocre quality, is limited in its scope, and collecting the data causes stress to the animals which can compromise growth and survival. Automated counting and measuring of abalone will increase farm efficiency and productivity in the short term and, in the longer term, will provide an advanced platform for further R&D improvements. Artificial intelligence and machine learning has now matured to a point that accurately counting and measuring abalone is possible using this approach. This project would involve the development, training and validation of a machine learning model to identify, segment and measure quantitative abalone traits in production systems, and render the product data to be accessible and applicable for farmers.

Date

24 Jul 2020 - 31 Aug 2022

Project Type

GRANT

Keywords

Abalone (Haliotidae);Machine Learning

Funding Body

Fisheries Research & Development Corporation

Amount

115649

Project Team

Marcus Sheaves;Ickjai Lee;Kyungmi Joanne Lee;Carlo Mattone;Jason Holdsworth;Art Suwanwiwat