Classification of Southern Ocean krill and icefish echoes using random forests

Niall G. Fallon, Sophie Fielding, Paul G. Fernandes

Research output: Contribution to journalArticle

3 Citations (Scopus)
6 Downloads (Pure)

Abstract

Target identification remains a challenge for acoustic surveys of marine fauna. Antarctic krill, Euphausia superba, are typically identified through a combination of expert scrutiny of echograms and analysis of differences in mean volume backscattering strengths (SV; dB re 1 m−1) measured at two or more echosounder frequencies. For commonly used frequencies, however, the differences for krill are similar to those for many co-occurring fish species that do not possess swimbladders. At South Georgia, South Atlantic, one species in particular, mackerel icefish, Champsocephalus gunnari, forms pelagic aggregations, which can be difficult to distinguish acoustically from large krill layers. Mackerel icefish are currently surveyed using bottom-trawls, but the resultant estimates of abundance may be biased because of the species' semi-pelagic distribution. An acoustic estimate of the pelagic component of the population could indicate the magnitude of this bias, but first a reliable target identification method is required. To address this, random forests (RFs) were generated using acoustic and net sample data collected during surveys. The final RF classified as krill, icefish, and mixed aggregations of weak scattering fish species with an overall estimated accuracy of 95%. Minimum SV, mean aggregation depth (m), mean distance from the seabed (m), and geographic positional data were most important to the accuracy of the RF. Time-of-day and the difference between SV at 120 kHz (SV 120) and that at 38 kHz (SV 38) were also important. The RF classification resulted in significantly higher estimates of backscatter apportioned to krill when compared with widely applied identification methods based on fixed and variable ranges of SV 120–SV 38. These results suggest that krill density is underestimated when those SV-differencing methods are used for target identification. RFs are an objective means for target identification and could enhance the utility of incidentally collected acoustic data.
Original languageEnglish
Pages (from-to)1998-2008
Number of pages11
JournalICES Journal of Marine Science
Volume73
Issue number8
Early online date7 Apr 2016
DOIs
Publication statusPublished - Sep 2016

Fingerprint

krill
oceans
acoustics
taxonomy
ocean
Euphausia superba
identification method
acoustic survey
acoustic data
swim bladder
bottom trawling
fish
backscatter
methodology
scattering
Salangidae
fauna
Champsocephalus gunnari
sampling

Keywords

  • acoustics
  • fish survey
  • South Georgia
  • target identification

Cite this

Classification of Southern Ocean krill and icefish echoes using random forests. / Fallon, Niall G.; Fielding, Sophie; Fernandes, Paul G.

In: ICES Journal of Marine Science, Vol. 73, No. 8, 09.2016, p. 1998-2008.

Research output: Contribution to journalArticle

@article{fe989ca18b884689b4dfce4179f33bb2,
title = "Classification of Southern Ocean krill and icefish echoes using random forests",
abstract = "Target identification remains a challenge for acoustic surveys of marine fauna. Antarctic krill, Euphausia superba, are typically identified through a combination of expert scrutiny of echograms and analysis of differences in mean volume backscattering strengths (SV; dB re 1 m−1) measured at two or more echosounder frequencies. For commonly used frequencies, however, the differences for krill are similar to those for many co-occurring fish species that do not possess swimbladders. At South Georgia, South Atlantic, one species in particular, mackerel icefish, Champsocephalus gunnari, forms pelagic aggregations, which can be difficult to distinguish acoustically from large krill layers. Mackerel icefish are currently surveyed using bottom-trawls, but the resultant estimates of abundance may be biased because of the species' semi-pelagic distribution. An acoustic estimate of the pelagic component of the population could indicate the magnitude of this bias, but first a reliable target identification method is required. To address this, random forests (RFs) were generated using acoustic and net sample data collected during surveys. The final RF classified as krill, icefish, and mixed aggregations of weak scattering fish species with an overall estimated accuracy of 95{\%}. Minimum SV, mean aggregation depth (m), mean distance from the seabed (m), and geographic positional data were most important to the accuracy of the RF. Time-of-day and the difference between SV at 120 kHz (SV 120) and that at 38 kHz (SV 38) were also important. The RF classification resulted in significantly higher estimates of backscatter apportioned to krill when compared with widely applied identification methods based on fixed and variable ranges of SV 120–SV 38. These results suggest that krill density is underestimated when those SV-differencing methods are used for target identification. RFs are an objective means for target identification and could enhance the utility of incidentally collected acoustic data.",
keywords = "acoustics, fish survey, South Georgia, target identification",
author = "Fallon, {Niall G.} and Sophie Fielding and Fernandes, {Paul G.}",
note = "Acknowledgements The authors thank the crews, fishers, and scientists who conducted the various surveys from which data were obtained. This work was supported by the Government of South Georgia and South Sandwich Islands. Additional logistical support provided by The South Atlantic Environmental Research Institute, with thanks to Paul Brickle. PF receives funding from the MASTS pooling initiative (TheMarine Alliance for Science and Technology for Scotland), and their support is gratefully acknowledged. MASTS is funded by the Scottish Funding Council (grant reference HR09011) and contributing institutions. SF is funded by the Natural Environment Research Council, and data were provided from the British Antarctic Survey Ecosystems Long-term Monitoring and Surveys programme as part of the BAS Polar Science for Planet Earth Programme. The authors also thank the anonymous referees for their helpful suggestions on an earlier version of this manuscript.",
year = "2016",
month = "9",
doi = "10.1093/icesjms/fsw057",
language = "English",
volume = "73",
pages = "1998--2008",
journal = "ICES Journal of Marine Science",
issn = "1054-3139",
publisher = "Oxford University Press",
number = "8",

}

TY - JOUR

T1 - Classification of Southern Ocean krill and icefish echoes using random forests

AU - Fallon, Niall G.

AU - Fielding, Sophie

AU - Fernandes, Paul G.

N1 - Acknowledgements The authors thank the crews, fishers, and scientists who conducted the various surveys from which data were obtained. This work was supported by the Government of South Georgia and South Sandwich Islands. Additional logistical support provided by The South Atlantic Environmental Research Institute, with thanks to Paul Brickle. PF receives funding from the MASTS pooling initiative (TheMarine Alliance for Science and Technology for Scotland), and their support is gratefully acknowledged. MASTS is funded by the Scottish Funding Council (grant reference HR09011) and contributing institutions. SF is funded by the Natural Environment Research Council, and data were provided from the British Antarctic Survey Ecosystems Long-term Monitoring and Surveys programme as part of the BAS Polar Science for Planet Earth Programme. The authors also thank the anonymous referees for their helpful suggestions on an earlier version of this manuscript.

PY - 2016/9

Y1 - 2016/9

N2 - Target identification remains a challenge for acoustic surveys of marine fauna. Antarctic krill, Euphausia superba, are typically identified through a combination of expert scrutiny of echograms and analysis of differences in mean volume backscattering strengths (SV; dB re 1 m−1) measured at two or more echosounder frequencies. For commonly used frequencies, however, the differences for krill are similar to those for many co-occurring fish species that do not possess swimbladders. At South Georgia, South Atlantic, one species in particular, mackerel icefish, Champsocephalus gunnari, forms pelagic aggregations, which can be difficult to distinguish acoustically from large krill layers. Mackerel icefish are currently surveyed using bottom-trawls, but the resultant estimates of abundance may be biased because of the species' semi-pelagic distribution. An acoustic estimate of the pelagic component of the population could indicate the magnitude of this bias, but first a reliable target identification method is required. To address this, random forests (RFs) were generated using acoustic and net sample data collected during surveys. The final RF classified as krill, icefish, and mixed aggregations of weak scattering fish species with an overall estimated accuracy of 95%. Minimum SV, mean aggregation depth (m), mean distance from the seabed (m), and geographic positional data were most important to the accuracy of the RF. Time-of-day and the difference between SV at 120 kHz (SV 120) and that at 38 kHz (SV 38) were also important. The RF classification resulted in significantly higher estimates of backscatter apportioned to krill when compared with widely applied identification methods based on fixed and variable ranges of SV 120–SV 38. These results suggest that krill density is underestimated when those SV-differencing methods are used for target identification. RFs are an objective means for target identification and could enhance the utility of incidentally collected acoustic data.

AB - Target identification remains a challenge for acoustic surveys of marine fauna. Antarctic krill, Euphausia superba, are typically identified through a combination of expert scrutiny of echograms and analysis of differences in mean volume backscattering strengths (SV; dB re 1 m−1) measured at two or more echosounder frequencies. For commonly used frequencies, however, the differences for krill are similar to those for many co-occurring fish species that do not possess swimbladders. At South Georgia, South Atlantic, one species in particular, mackerel icefish, Champsocephalus gunnari, forms pelagic aggregations, which can be difficult to distinguish acoustically from large krill layers. Mackerel icefish are currently surveyed using bottom-trawls, but the resultant estimates of abundance may be biased because of the species' semi-pelagic distribution. An acoustic estimate of the pelagic component of the population could indicate the magnitude of this bias, but first a reliable target identification method is required. To address this, random forests (RFs) were generated using acoustic and net sample data collected during surveys. The final RF classified as krill, icefish, and mixed aggregations of weak scattering fish species with an overall estimated accuracy of 95%. Minimum SV, mean aggregation depth (m), mean distance from the seabed (m), and geographic positional data were most important to the accuracy of the RF. Time-of-day and the difference between SV at 120 kHz (SV 120) and that at 38 kHz (SV 38) were also important. The RF classification resulted in significantly higher estimates of backscatter apportioned to krill when compared with widely applied identification methods based on fixed and variable ranges of SV 120–SV 38. These results suggest that krill density is underestimated when those SV-differencing methods are used for target identification. RFs are an objective means for target identification and could enhance the utility of incidentally collected acoustic data.

KW - acoustics

KW - fish survey

KW - South Georgia

KW - target identification

U2 - 10.1093/icesjms/fsw057

DO - 10.1093/icesjms/fsw057

M3 - Article

VL - 73

SP - 1998

EP - 2008

JO - ICES Journal of Marine Science

JF - ICES Journal of Marine Science

SN - 1054-3139

IS - 8

ER -