Journal article

Automating the assessment of biofouling in images using expert agreement as a gold standard

Nathaniel J Bloomfield, Susan Wei, Bartholomew A Woodham, Peter Wilkinson, Andrew P Robinson



Biofouling is the accumulation of organisms on surfaces immersed in water. It is of particular concern to the international shipping industry because it increases fuel costs and presents a biosecurity risk by providing a pathway for non-indigenous marine species to establish in new areas. There is growing interest within jurisdictions to strengthen biofouling risk-management regulations, but it is expensive to conduct in-water inspections and assess the collected data to determine the biofouling state of vessel hulls. Machine learning is well suited to tackle the latter challenge, and here we apply deep learning to automate the classification of images from in-water inspections to identify t..

View full abstract


Awarded by LIEF

Funding Acknowledgements

We would like to thank Jason Garwood and Steven Lane for their work developing the initial project case. We would like to thank Serena Orr, Dan McClary and Emily Jones from Ramboll New Zealand for classifying the image dataset. We would like to thank Anca Hanea for providing advice in comparing different labelling schemes, and Edith Arndt for insightful discussions on the biofouling literature. We would also like to thank Dan Kluza from the New Zealand Ministry for Primary Industries and Chris Scianni from the California State Lands Commission for providing their datasets. This research was undertaken using the LIEF HPC-GPGPU Facility hosted at the University of Melbourne. This Facility was established with the assistance of LIEF Grant LE170100200. This study was undertaken with the assistance of resources and services from the National Computational Infrastructure (NCI), which is supported by the Australian Government. NB and AR's contributions were also funded by the Centre of Excellence for Biosecurity Risk Analysis at the University of Melbourne.