The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices
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 new 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.
Complete Metadata
| @type | dcat:Dataset |
|---|---|
| accessLevel | public |
| bureauCode |
[
"019:20"
]
|
| contactPoint |
{
"fn": "Theodore Nowak",
"@type": "vcard:Contact",
"hasEmail": "mailto:theodore.nowak@pnnl.gov"
}
|
| dataQuality |
true
|
| description | 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 new 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. |
| distribution |
[
{
"@type": "dcat:Distribution",
"title": "Detection Methodology Publication",
"format": "70024",
"accessURL": "https://doi.org/10.1002/lom3.70024",
"mediaType": "application/octet-stream",
"description": "Publication describing the methodology used in developing an automated detection pipeline that filters noise from acoustic camera imagery and performs object detection to identify possible targets. Methods described were used to extract targets of interest from the associated dataset."
},
{
"@type": "dcat:Distribution",
"title": "Data Collection Publication",
"format": "HTML",
"accessURL": "https://dx.doi.org/10.1007/s12237-014-9767-8",
"mediaType": "text/html",
"description": "Publication containing the results of the original video data collection campaign"
},
{
"@type": "dcat:Distribution",
"title": "PNNL-TUNAMELT Github Repository",
"format": "HTML",
"accessURL": "https://github.com/tsnowak/pnnl-tunamelt",
"mediaType": "text/html",
"description": "Software tools for working with the PNNL-TUNAMELT dataset and a baseline automated detection pipeline."
},
{
"@type": "dcat:Distribution",
"title": "PNNL-TUNAMELT.tar.gz",
"format": "gz",
"accessURL": "https://mhkdr.openei.org/files/633/PNNL-TUNAMELT.tar.gz",
"mediaType": "application/gzip",
"description": "The PNNL-TUNAMELT dataset and labels"
}
]
|
| identifier | https://data.openei.org/submissions/8622 |
| issued | 2025-06-01T06:00:00Z |
| keyword |
[
"Acoustic Camera",
"Collision Risk",
"Computer Vision",
"Dataset",
"Environmental Monitoring",
"GitHub",
"Imaging Sonar",
"MHK",
"MHK Monitoring",
"PNNL-TUNAMELT",
"acoustic camera video frames",
"automated detection",
"code",
"marine energy devices",
"software tools",
"tidal turbine"
]
|
| landingPage | https://mhkdr.openei.org/submissions/633 |
| license | https://creativecommons.org/licenses/by/4.0/ |
| modified | 2026-02-13T19:51:21Z |
| programCode |
[
"019:009"
]
|
| projectLead | Samantha Eaves |
| projectNumber | FY25 AOP 232611 |
| projectTitle | Triton Initiative |
| publisher |
{
"name": "Pacific Northwest National Laboratory",
"@type": "org:Organization"
}
|
| spatial |
"{"type":"Polygon","coordinates":[[[-123.048011,44.90977562946043],[-67.04510311639692,44.90977562946043],[-67.04510311639692,48.078225],[-123.048011,48.078225],[-123.048011,44.90977562946043]]]}"
|
| title | The PNNL-TUNAMELT Dataset for Automated Detection Around Marine Energy Devices |
