Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data
Abstract
Adult American eels (Anguilla rostrata) are vulnerable to hydropower turbine mortality during outmigration from growth habitat in inland waters to the ocean where they spawn. Imaging sonar is a reliable and proven technology for monitoring of fish passage and migration; however, there is no efficient automated method for eel detection. We designed a deep learning model for automated detection of adult American eels from sonar data. The method employs convolution neural network (CNN) to distinguish between 14 images of eels and non-eel objects. Prior to image classification with CNN, background subtraction and wavelet denoising were applied to enhance sonar images. The CNN model was first trained and tested on data obtained from a laboratory experiment, which yielded overall accuracies of >98% for image-based classification. Then, the model was trained and tested on field data that were obtained near the Iroquois Dam located on the St. Lawrence River; the accuracy achieved was commensurate with that of human experts.
- Authors:
-
[1];
[1];
[2]
- Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Electric Power Research Inst. (EPRI), Palo Alto, CA (United States)
- Publication Date:
- Research Org.:
- Electric Power Research Inst. (EPRI), Palo Alto, CA (United States); Pacific Northwest National Lab. (PNNL), Richland, WA (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Renewable Power Office. Water Power Technologies Office
- OSTI Identifier:
- 1808592
- Alternate Identifier(s):
- OSTI ID: 1811666
- Report Number(s):
- DOE-EPRI-8341; PNNL-SA-149057
Journal ID: ISSN 2072-4292
- Grant/Contract Number:
- EE0008341; AC05-76RL01830
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Remote Sensing
- Additional Journal Information:
- Journal Volume: 13; Journal Issue: 14; Related Information: https://www.mdpi.com/2072-4292/13/14/2671/s1; Journal ID: ISSN 2072-4292
- Publisher:
- MDPI
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 13 HYDRO ENERGY; American eel; imaging sonar; image classification; fish identification; deep learning; convolutional neural network
Citation Formats
Zang, Xiaoqin, Yin, Tianzhixi, Hou, Zhangshuan, Mueller, Robert P., Deng, Zhiqun Daniel, and Jacobson, Paul T. Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data. United States: N. p., 2021.
Web. doi:10.3390/rs13142671.
Zang, Xiaoqin, Yin, Tianzhixi, Hou, Zhangshuan, Mueller, Robert P., Deng, Zhiqun Daniel, & Jacobson, Paul T. Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data. United States. https://doi.org/10.3390/rs13142671
Zang, Xiaoqin, Yin, Tianzhixi, Hou, Zhangshuan, Mueller, Robert P., Deng, Zhiqun Daniel, and Jacobson, Paul T. Wed .
"Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data". United States. https://doi.org/10.3390/rs13142671. https://www.osti.gov/servlets/purl/1808592.
@article{osti_1808592,
title = {Deep Learning for Automated Detection and Identification of Migrating American Eel Anguilla rostrata from Imaging Sonar Data},
author = {Zang, Xiaoqin and Yin, Tianzhixi and Hou, Zhangshuan and Mueller, Robert P. and Deng, Zhiqun Daniel and Jacobson, Paul T.},
abstractNote = {Adult American eels (Anguilla rostrata) are vulnerable to hydropower turbine mortality during outmigration from growth habitat in inland waters to the ocean where they spawn. Imaging sonar is a reliable and proven technology for monitoring of fish passage and migration; however, there is no efficient automated method for eel detection. We designed a deep learning model for automated detection of adult American eels from sonar data. The method employs convolution neural network (CNN) to distinguish between 14 images of eels and non-eel objects. Prior to image classification with CNN, background subtraction and wavelet denoising were applied to enhance sonar images. The CNN model was first trained and tested on data obtained from a laboratory experiment, which yielded overall accuracies of >98% for image-based classification. Then, the model was trained and tested on field data that were obtained near the Iroquois Dam located on the St. Lawrence River; the accuracy achieved was commensurate with that of human experts.},
doi = {10.3390/rs13142671},
journal = {Remote Sensing},
number = 14,
volume = 13,
place = {United States},
year = {Wed Jul 07 00:00:00 EDT 2021},
month = {Wed Jul 07 00:00:00 EDT 2021}
}
Free Publicly Available Full Text
Publisher's Version of Record
Other availability
Search WorldCat to find libraries that may hold this journal
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.
Works referenced in this record:
Zur Theorie der orthogonalen Funktionensysteme: Erste Mitteilung
journal, September 1910
- Haar, Alfred
- Mathematische Annalen, Vol. 69, Issue 3
Mortality of downstream migrating European eel at power stations can be low when turbine mortality is eliminated by protection measures and safe bypass routes are available
journal, July 2019
- Økland, Finn; Havn, Torgeir B.; Thorstad, Eva B.
- International Review of Hydrobiology, Vol. 104, Issue 3-4
Deep learning
journal, May 2015
- LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey
- Nature, Vol. 521, Issue 7553
Learning representations by back-propagating errors
journal, October 1986
- Rumelhart, David E.; Hinton, Geoffrey E.; Williams, Ronald J.
- Nature, Vol. 323, Issue 6088
Automated tracking of fish in trawls using the DIDSON (Dual frequency IDentification SONar)
journal, March 2008
- Handegard, Nils Olav; Williams, Kresimir
- ICES Journal of Marine Science, Vol. 65, Issue 4
Accuracy and precision of fish-count data from a “dual-frequency identification sonar” (DIDSON) imaging system
journal, January 2006
- Holmes, John A.; Cronkite, George M. W.; Enzenhofer, Hermann J.
- ICES Journal of Marine Science, Vol. 63, Issue 3
Passage survival of European and American eels at Francis and propeller turbines
journal, September 2019
- Heisey, Paul G.; Mathur, Dilip; Phipps, Joanne L.
- Journal of Fish Biology, Vol. 95, Issue 5
Evaluating the Effect of Dam Removals on Yellow‐Phase American Eel Abundance in a Northeastern U.S. Watershed
journal, April 2018
- Turner, Sara M.; Chase, Bradford C.; Bednarski, Michael S.
- North American Journal of Fisheries Management, Vol. 38, Issue 2
Transform-based image enhancement algorithms with performance measure
journal, March 2001
- Agaian, S. S.; Panetta, K.; Grigoryan, A. M.
- IEEE Transactions on Image Processing, Vol. 10, Issue 3
A review of artificial neural network models for ambient air pollution prediction
journal, September 2019
- Cabaneros, Sheen Mclean; Calautit, John Kaiser; Hughes, Ben Richard
- Environmental Modelling & Software, Vol. 119
DeepFish: Accurate underwater live fish recognition with a deep architecture
journal, April 2016
- Qin, Hongwei; Li, Xiu; Liang, Jian
- Neurocomputing, Vol. 187
Backpropagation Applied to Handwritten Zip Code Recognition
journal, December 1989
- LeCun, Y.; Boser, B.; Denker, J. S.
- Neural Computation, Vol. 1, Issue 4
Population Decline of the American Eel: Implications for Research and Management
journal, September 2000
- Haro, Alex; Richkus, William; Whalen, Kevin
- Fisheries, Vol. 25, Issue 9
ImageNet classification with deep convolutional neural networks
journal, May 2017
- Krizhevsky, Alex; Sutskever, Ilya; Hinton, Geoffrey E.
- Communications of the ACM, Vol. 60, Issue 6
Did a “perfect storm” of oceanic changes and continental anthropogenic impacts cause northern hemisphere anguillid recruitment reductions?
journal, April 2015
- Miller, Michael J.; Feunteun, Eric; Tsukamoto, Katsumi
- ICES Journal of Marine Science, Vol. 73, Issue 1
Realtime classification of fish in underwater sonar videos
journal, January 2016
- Bothmann, Ludwig; Windmann, Michael; Kauermann, Göran
- Journal of the Royal Statistical Society: Series C (Applied Statistics), Vol. 65, Issue 4
A deep learning algorithm using CT images to screen for Corona virus disease (COVID-19)
journal, February 2021
- Wang, Shuai; Kang, Bo; Ma, Jinlu
- European Radiology, Vol. 31, Issue 8
Classifying Sonar Images: Can a Computer-Driven Process Identify Eels?
journal, December 2008
- Mueller, Anna-Maria; Mulligan, Tim; Withler, Peter K.
- North American Journal of Fisheries Management, Vol. 28, Issue 6
Improving European Silver Eel ( Anguilla anguilla ) downstream migration by undershot sluice gate management at a small-scale hydropower plant
journal, September 2017
- Egg, Leonhard; Mueller, Melanie; Pander, Joachim
- Ecological Engineering, Vol. 106
Inter-Observer Bias in Fish Classification and Enumeration Using Dual-frequency Identification Sonar (DIDSON): A Pacific Lamprey Case Study
journal, January 2017
- Keefer, Matthew L.; Caudill, Christopher C.; Johnson, Eric L.
- Northwest Science, Vol. 91, Issue 1
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
Wavelet analysis of bathymetric sidescan sonar data for the classification of seafloor sediments in Hopvågen Bay - Norway
journal, January 2002
- Atallah, L.; Probert Smith, P. J.; Bates, C. R.
- Marine Geophysical Researches, Vol. 23, Issue 5/6
Automatic land cover classification of geo-tagged field photos by deep learning
journal, May 2017
- Xu, Guang; Zhu, Xuan; Fu, Dongjie
- Environmental Modelling & Software, Vol. 91
Automated detection of COVID-19 cases using deep neural networks with X-ray images
journal, June 2020
- Ozturk, Tulin; Talo, Muhammed; Yildirim, Eylul Azra
- Computers in Biology and Medicine, Vol. 121
Applications for deep learning in ecology
journal, July 2019
- Christin, Sylvain; Hervet, Éric; Lecomte, Nicolas
- Methods in Ecology and Evolution, Vol. 10, Issue 10