The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices

In curation License 

This labeled dataset contains 107,451 acoustic camera video frames capturing marine life interactions around an underwater tidal turbine. Each frame is annotated with bounding boxes identifying marine life objects as labeled by a fish biologist. Created to support research into automated target detection around underwater turbines, this dataset aims to advance capabilities that enable the safe deployment and operation of marine energy devices. No collisions were observed with the turbine while labeling and analyzing this dataset, and a publication detailing this work will be added once available.

The video data was originally collected in 2010 around Ocean Renewable Power Company's (ORPC) tidal turbine deployment in Cobscook Bay, Maine, USA, with results published in Viehman and Zydlewski (2015) Estuaries and Coasts 38: 241?252 (linked below). Code, software tools, and a baseline automated detection approach developed for this effort are available in the PNNL-TUNAMELT GitHub repository, which also provides guidance for getting started with this dataset. For further information, please refer to the GitHub repository, the associated publication, or contact the authors.

Citation Formats

TY - DATA AB - This labeled dataset contains 107,451 acoustic camera video frames capturing marine life interactions around an underwater tidal turbine. Each frame is annotated with bounding boxes identifying marine life objects as labeled by a fish biologist. Created to support research into automated target detection around underwater turbines, this dataset aims to advance capabilities that enable the safe deployment and operation of marine energy devices. No collisions were observed with the turbine while labeling and analyzing this dataset, and a publication detailing this work will be added once available. The video data was originally collected in 2010 around Ocean Renewable Power Company's (ORPC) tidal turbine deployment in Cobscook Bay, Maine, USA, with results published in Viehman and Zydlewski (2015) Estuaries and Coasts 38: 241?252 (linked below). Code, software tools, and a baseline automated detection approach developed for this effort are available in the PNNL-TUNAMELT GitHub repository, which also provides guidance for getting started with this dataset. For further information, please refer to the GitHub repository, the associated publication, or contact the authors. AU - Nowak, Theodore A2 - Staines, Garrett A3 - Abdullai, Blerim DB - Marine and Hydrokinetic Data Repository DP - Open EI | National Renewable Energy Laboratory DO - KW - MHK KW - Computer Vision KW - Dataset KW - Acoustic Camera KW - Imaging Sonar KW - Environmental Monitoring KW - MHK Monitoring KW - Collision Risk KW - PNNL-TUNAMELT KW - automated detection KW - marine energy devices KW - acoustic camera video frames KW - tidal turbine KW - code KW - GitHub KW - software tools LA - English DA - 2025/06/01 PY - 2025 PB - Pacific Northwest National Laboratory T1 - The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices UR - https://mhkdr.openei.org/submissions/633 ER -
Export Citation to RIS
Nowak, Theodore, et al. The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices. Pacific Northwest National Laboratory, 1 June, 2025, Marine and Hydrokinetic Data Repository. https://mhkdr.openei.org/submissions/633.
Nowak, T., Staines, G., & Abdullai, B. (2025). The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices. [Data set]. Marine and Hydrokinetic Data Repository. Pacific Northwest National Laboratory. https://mhkdr.openei.org/submissions/633
Nowak, Theodore, Garrett Staines, and Blerim Abdullai. The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices. Pacific Northwest National Laboratory, June, 1, 2025. Distributed by Marine and Hydrokinetic Data Repository. https://mhkdr.openei.org/submissions/633
@misc{MHKDR_Dataset_633, title = {The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices}, author = {Nowak, Theodore and Staines, Garrett and Abdullai, Blerim}, abstractNote = {This labeled dataset contains 107,451 acoustic camera video frames capturing marine life interactions around an underwater tidal turbine. Each frame is annotated with bounding boxes identifying marine life objects as labeled by a fish biologist. Created to support research into automated target detection around underwater turbines, this dataset aims to advance capabilities that enable the safe deployment and operation of marine energy devices. No collisions were observed with the turbine while labeling and analyzing this dataset, and a publication detailing this work will be added once available.

The video data was originally collected in 2010 around Ocean Renewable Power Company's (ORPC) tidal turbine deployment in Cobscook Bay, Maine, USA, with results published in Viehman and Zydlewski (2015) Estuaries and Coasts 38: 241?252 (linked below). Code, software tools, and a baseline automated detection approach developed for this effort are available in the PNNL-TUNAMELT GitHub repository, which also provides guidance for getting started with this dataset. For further information, please refer to the GitHub repository, the associated publication, or contact the authors.}, url = {https://mhkdr.openei.org/submissions/633}, year = {2025}, howpublished = {Marine and Hydrokinetic Data Repository, Pacific Northwest National Laboratory, https://mhkdr.openei.org/submissions/633}, note = {Accessed: 2025-07-25} }

Details

Data from Jun 1, 2025

Last updated Jul 18, 2025

Submitted Jun 19, 2025

Organization

Pacific Northwest National Laboratory

Contact

Theodore Nowak

509.375.2531

Authors

Theodore Nowak

Pacific Northwest National Laboratory

Garrett Staines

Pacific Northwest National Laboratory

Blerim Abdullai

University of Illinois at Urbana-Champaign

DOE Project Details

Project Name Triton Initiative

Project Lead Samantha Eaves

Project Number FY25 AOP 232611

Share

Submission Downloads