Automated Fish Detection and Wildlife Tracking for Marine Energy Applications: Final Report and Review
This submission contains two technical resources produced for the U.S. Department of Energy Water Power Technologies Office (WPTO) that evaluate and advance automated methods for underwater wildlife detection, tracking, and monitoring around marine energy systems. The project analyzes how modern computer-vision and machine-learning techniques can support reductions in manual labor, improve monitoring consistency, and streamline permitting by enabling automated detection of fish in both optical and imaging-sonar data.
The work includes development and testing of You Only Look Once (YOLO), Faster Region-based Convolutional Neural Network (R-CNN), Elastic Shape Analysis (ESA), and hyper-image methods for fish detection using the Pacific Northwest National Laboratory (PNNL) EyeSea optical dataset and multiple imaging sonar datasets. It also provides a comprehensive literature review on imaging sonar performance, machine-learning approaches for object detection, and domain-adaptation strategies to support cross-site generalization.
Citation Formats
TY - DATA
AB - This submission contains two technical resources produced for the U.S. Department of Energy Water Power Technologies Office (WPTO) that evaluate and advance automated methods for underwater wildlife detection, tracking, and monitoring around marine energy systems. The project analyzes how modern computer-vision and machine-learning techniques can support reductions in manual labor, improve monitoring consistency, and streamline permitting by enabling automated detection of fish in both optical and imaging-sonar data.
The work includes development and testing of You Only Look Once (YOLO), Faster Region-based Convolutional Neural Network (R-CNN), Elastic Shape Analysis (ESA), and hyper-image methods for fish detection using the Pacific Northwest National Laboratory (PNNL) EyeSea optical dataset and multiple imaging sonar datasets. It also provides a comprehensive literature review on imaging sonar performance, machine-learning approaches for object detection, and domain-adaptation strategies to support cross-site generalization.
AU - Slater, Wencheng Katherine
A2 - Gustin, Steven
A3 - Sabo, Victoria
A4 - Noyes, Carlos
A5 - Yoder, Delano
A6 - Eaves, Samantha
A7 - Nault, Denis-Marc
DB - Open Energy Data Initiative (OEDI)
DP - Open EI | National Laboratory of the Rockies
DO -
KW - MHK
KW - Marine
KW - Hydrokinetic
KW - energy
KW - power
KW - automated fish detection
KW - imaging sonar
KW - YOLO
KW - R-CNN
KW - ESA
KW - elasric shape analysis
KW - hyper-image
KW - object tracking
KW - literature review
KW - PNNL EyeSea
KW - optical dataset
KW - wildlife tracking
KW - You Only Look Once
KW - computer-vision
KW - machine-learning
LA - English
DA - 2025/12/08
PY - 2025
PB - Booz Allen Hamilton Inc.
T1 - Automated Fish Detection and Wildlife Tracking for Marine Energy Applications: Final Report and Review
UR - https://data.openei.org/submissions/8753
ER -
Slater, Wencheng Katherine, et al. Automated Fish Detection and Wildlife Tracking for Marine Energy Applications: Final Report and Review. Booz Allen Hamilton Inc. , 8 December, 2025, MHKDR. https://mhkdr.openei.org/submissions/675.
Slater, W., Gustin, S., Sabo, V., Noyes, C., Yoder, D., Eaves, S., & Nault, D. (2025). Automated Fish Detection and Wildlife Tracking for Marine Energy Applications: Final Report and Review. [Data set]. MHKDR. Booz Allen Hamilton Inc. . https://mhkdr.openei.org/submissions/675
Slater, Wencheng Katherine, Steven Gustin, Victoria Sabo, Carlos Noyes, Delano Yoder, Samantha Eaves, and Denis-Marc Nault. Automated Fish Detection and Wildlife Tracking for Marine Energy Applications: Final Report and Review. Booz Allen Hamilton Inc. , December, 8, 2025. Distributed by MHKDR. https://mhkdr.openei.org/submissions/675
@misc{OEDI_Dataset_8753,
title = {Automated Fish Detection and Wildlife Tracking for Marine Energy Applications: Final Report and Review},
author = {Slater, Wencheng Katherine and Gustin, Steven and Sabo, Victoria and Noyes, Carlos and Yoder, Delano and Eaves, Samantha and Nault, Denis-Marc},
abstractNote = {This submission contains two technical resources produced for the U.S. Department of Energy Water Power Technologies Office (WPTO) that evaluate and advance automated methods for underwater wildlife detection, tracking, and monitoring around marine energy systems. The project analyzes how modern computer-vision and machine-learning techniques can support reductions in manual labor, improve monitoring consistency, and streamline permitting by enabling automated detection of fish in both optical and imaging-sonar data.
The work includes development and testing of You Only Look Once (YOLO), Faster Region-based Convolutional Neural Network (R-CNN), Elastic Shape Analysis (ESA), and hyper-image methods for fish detection using the Pacific Northwest National Laboratory (PNNL) EyeSea optical dataset and multiple imaging sonar datasets. It also provides a comprehensive literature review on imaging sonar performance, machine-learning approaches for object detection, and domain-adaptation strategies to support cross-site generalization. },
url = {https://mhkdr.openei.org/submissions/675},
year = {2025},
howpublished = {MHKDR, Booz Allen Hamilton Inc. , https://mhkdr.openei.org/submissions/675},
note = {Accessed: 2026-09-08}
}
Details
Data from Dec 8, 2025
Last updated Aug 17, 2026
Submitted Aug 17, 2026
Organization
Booz Allen Hamilton Inc.
Contact
Denis-Marc Nault
