Bianca M. Owen

Bianca M. Owen

Auto-generated profile, based on publicly available information

Bianca M. Owen

Centre for Sustainable Aquatic Ecosystems, Harry Butler Institute Murdoch University Murdoch Western Australia Australia

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 June 2022 in Limnology and Oceanography: Methods
Verified
Journal Article
Open access
BOBianca M. Owen
Bianca M. Owen
CHChris S. Hallett
Chris S. Hallett
JCJeffrey J. Cosgrove
Jeffrey J. Cosgrove
James R TweedleyJames R Tweedley
James R Tweedley
NMNavid Moheimani
Navid Moheimani
Accurate and detailed reporting of methods is essential for scientific progress, yet it is widely accepted that authors across all scientific fields tend to provide insufficient methods detail. Given the recent proliferation of automated and semi‐automated technologies for data collection, to address this widespread issue the details needed for interpretation and reproducibility for each specific technique first need to be identified. A systematic literature review assessed the comprehensiveness of method details reported by 116 peer‐reviewed studies published between 2017 and 2020 using the FlowCam (a widely used imaging flow cytometer) to image phytoplankton, finding all to be lacking in critical details, inhibiting reproducibility, and limiting the veracity of some findings. Through this review and three case studies, we identify several key method details that should be reported by FlowCam studies to ensure their findings are credible, comparable, and replicable and illustrate the wide‐reaching implications for not doing so. Future studies using FlowCam for phytoplankton analyses should ensure clear reporting of all relevant details relating to the FlowCam unit, sample preparation, run settings, post‐processing of images, and the considered use of only verified measurement outputs. A methods reporting template is presented as a guideline intended to enhance the quality, interpretability, and repeatability of future FlowCam papers. The pervasiveness of inadequacies in FlowCam methods reporting identified here highlights how vital it is for users of any automated or semi‐automated scientific technologies to have a clear understanding of the impact of all method details on their findings, and to report these details adequately.

15 November 2025 in Limnology and Oceanography: Methods
Verified
Journal Article
Open access
BOBianca M. Owen
Bianca M. Owen
JTJames R. Tweedley
James R. Tweedley
NMNavid R. Moheimani
Navid R. Moheimani
CHChris S. Hallett
Chris S. Hallett
JCJeffrey J. Cosgrove
Jeffrey J. Cosgrove
LSLeopold P. O. Silberstein
Leopold P. O. Silberstein
Machine learning has opened the door for the automated sorting (classification) of images, holograms and acoustic backscatters of individual plankton, invertebrates, fish and marine mammals. However, this field is complicated by decades of paradoxically promising reports of classifier performance that do not correlate with real‐world uptake of this technology in aquatic sciences. Simple metrics of classifier performance are essential for optimizing, evaluating and comparing machine learning classifiers, but a wide variety of metrics and calculation variants have been proposed. Several characteristics of species count data influence metric behavior: severe imbalance and variance, zero‐inflation, high class numbers and contamination with non‐target classes. This study explores the hidden complexity of classifier performance metrics for species count data using synthetic datasets and simulated classifier outputs. It demonstrates how these data characteristics can severely distort metric values, with seven of eight variants of the most common metric, Accuracy, returning near‐perfect scores (up to 98%) even when no instances are correctly classified. Clear recommendations are made for classifier evaluation pitfalls and metric variants to avoid, ultimately finding one variant of the F1‐Score (mF1) to be the most suitable single metric, with several important calculation caveats specific to species count data. Due to ambiguous terminology and inconsistent definitions, it is often impossible to identify which variant of a performance metric has been applied in classifier studies. It is vital that authors are intentional and transparent about their metric use to support the vast potential for machine learning to revolutionize the research and monitoring of aquatic environments.