Digital imaging techniques in otolith data capture, analysis and interpretation

Fisher, Mark; Hunter, Ewan

doi:10.3354/meps12531

Cited by 16 publications

(8 citation statements)

References 87 publications

(113 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In their recent rewiew, Fisher and Hunter [31] found that digital image analysis systems provided little improvement in cost-effectiveness over manual otolith analysis. Although machine learning systems were included in their study, no modern deep learning convolutional network was considered.…”

Section: Discussionmentioning

confidence: 99%

Automatic interpretation of otoliths using deep learning

et al. 2018

View full text Add to dashboard Cite

The age structure of a fish population has important implications for recruitment processes and population fluctuations, and is a key input to fisheries-assessment models. The current method of determining age structure relies on manually reading age from otoliths, and the process is labor intensive and dependent on specialist expertise. Recent advances in machine learning have provided methods that have been remarkably successful in a variety of settings, with potential to automate analysis that previously required manual curation. Machine learning models have previously been successfully applied to object recognition and similar image analysis tasks. Here we investigate whether deep learning models can also be used for estimating the age of otoliths from images. We adapt a pre-trained convolutional neural network designed for object recognition, to estimate the age of fish from otolith images. The model is trained and validated on a large collection of images of Greenland halibut otoliths. We show that the model works well, and that its precision is comparable to documented precision obtained by human experts. Automating this analysis may help to improve consistency, lower cost, and increase the extent of age estimation. Given that adequate data are available, this method could also be used to estimate age of other species using images of otoliths or fish scales.

show abstract

Section: Discussionmentioning

confidence: 99%

Automatic interpretation of otoliths using deep learning

et al. 2018

View full text Add to dashboard Cite

show abstract

“…The latter is perhaps of particular interest, as it demonstrates that a deep learning can obtain an accuracy comparable to human curators. This is in contrast to Fisher and Hunter (2018), who reviewed traditional machine learning approaches, and concluded that they provided no substantial advantage over human curation.…”

Section: Emulating Basic Human Expertisementioning

confidence: 72%

Machine intelligence and the data-driven future of marine science

Malde

Handegard

Eikvil

et al. 2019

ICES Journal of Marine Science

View full text Add to dashboard Cite

Oceans constitute over 70% of the earth's surface, and the marine environment and ecosystems are central to many global challenges. Not only are the oceans an important source of food and other resources, but they also play a important roles in the earth's climate and provide crucial ecosystem services. To monitor the environment and ensure sustainable exploitation of marine resources, extensive data collection and analysis efforts form the backbone of management programmes on global, regional, or national levels. Technological advances in sensor technology, autonomous platforms, and information and communications technology now allow marine scientists to collect data in larger volumes than ever before. But our capacity for data analysis has not progressed comparably, and the growing discrepancy is becoming a major bottleneck for effective use of the available data, as well as an obstacle to scaling up data collection further. Recent years have seen rapid advances in the fields of artificial intelligence and machine learning, and in particular, so-called deep learning systems are now able to solve complex tasks that previously required human expertise. This technology is directly applicable to many important data analysis problems and it will provide tools that are needed to solve many complex challenges in marine science and resource management. Here we give a brief review of recent developments in deep learning, and highlight the many opportunities and challenges for effective adoption of this technology across the marine sciences.

show abstract

“…The paired ear bones develop chemical and morphological signatures (Grønkjaer 2016). Calcium carbonate is incrementally accreted to the primordium of each otolith as the fish grows (Fisher and Hunter 2018), thereby recording characteristics of a fish's life history and external environment. CO 2 -acidification of seawater results in less carbonate ions (CO 3 2− ) available to form calcium carbonate (CaCO 3 ), and more hydrogen ions (H + ) decreasing the saturation state of CaCO 3 , which should decrease skeletal accretion.…”

Section: Introductionmentioning

confidence: 99%

Warming, not CO2-acidified seawater, alters otolith development of juvenile Antarctic emerald rockcod (Trematomus bernacchii)

et al. 2021

View full text Add to dashboard Cite

The combustion of fossil fuels is currently causing rapid rates of ocean warming and acidification worldwide. Projected changes in these parameters have been repeatedly observed to stress the physiological limits and plasticity of many marine species from the molecular to organismal levels. High latitude oceans are among the fastest changing ecosystems; therefore, polar species are projected to be some of the most vulnerable to climate change. Antarctic species are particularly sensitive to environmental change, having evolved for millions of years under stable ocean conditions. Otoliths, calcified structures found in a fish’s inner ear used to sense movement and direction, have been shown to be affected by both warming and CO2-acidified seawater in temperate and tropical fishes but there is no work to date on Antarctic fishes. In this study, juvenile emerald rockcod (Trematomus bernacchii) were exposed to projected seawater warming and CO2-acidification for the year 2100 over 28 days. Sagittal otoliths were analyzed for changes in area, perimeter, length, width and shape. We found ocean warming increased the growth rate of otoliths, while CO2-acidified seawater and the interaction of warming and acidification did not have an effect on otolith development. Elevated temperature also altered the shape of otoliths. If otolith development is altered under future warming scenarios, sensory functions such as hearing, orientation, and movement may potentially be impaired. Changes in these basic somatic abilities could have broad implications for the general capabilities and ecology of early life stages of Antarctic fishes.

show abstract

Digital imaging techniques in otolith data capture, analysis and interpretation

Cited by 16 publications

References 87 publications

Automatic interpretation of otoliths using deep learning

Automatic interpretation of otoliths using deep learning

Machine intelligence and the data-driven future of marine science

Warming, not CO2-acidified seawater, alters otolith development of juvenile Antarctic emerald rockcod (Trematomus bernacchii)

Contact Info

Product

Resources

About