Skip to content

This repository stores a machine learning model for using calibrated singe beam hydroacoustic data to determine seafloor habitat type. Outputs from the model for the Gulf of Alaska are also included. Details are in "Seabed classification in the Gulf of Alaska from acoustic surveys using deep learning" by K. Agarwal, C. Rooper and K. Williams

License

Notifications You must be signed in to change notification settings

noaa-afsc/acoustic-seafloor-habitat-classification

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Acoutic Seafloor Habitat Classification

This repository contains a ML model that can be used to determine seafloor habitat type from single beam acoustic data inputs. Specifically, the input files need to be produced by a Simrad EK60 scientific echosounder, collected at a minimum of two frequencies (38 and 120 kHz) and up to five frequencies (18,38,70,120, and 200 kHz) and be calibrated using standard calibration methods. The transducers used for this work produced equivalent beam angles as follows; 18 kHz at degrees , 38, 70, 120 and 200 kHz at 7 degrees. The output represents proportion of habitat predicted across five categories; sand, mixed_coarse, cobble, boulder, and bedrock. The model also estimates seafloor rugosity, which represents small scale variation in seafloor elevation. Full details are available in "Seabed classification in the Gulf of Alaska from acoustic surveys using deep learning" by K. Agarwal, C. Rooper, and K. Williams (in prep).

Datasets

For this project, 2017 and 2019 acoustic survey data collected by the Midwater Assessment and Conservation Engineering Program at the Alaska Fisheries Scienc Center, NOAA, were used to classify the seafloor acros the Gulf of Alaska. The model outputs are publicly available though the Zenodo open repository under the following DOI's acoustic seafloor classification model output GOA 2017 - 10.5281/zenodo.17612923 acoustic seafloor classification model output GOA 2019 - 10.5281/zenodo.17612149 A second data set that contains the 2019 survey outputs aggregated over 1 km grids is also available at Gulf of Alaska proportional seafloor habitat classification with 1 km resolution - 10.5281/zenodo.17663313

Image data are also available upon request from

https://www.ncei.noaa.gov/access/metadata/landing-page/bin/iso?id=gov.noaa.nodc:305766

Disclaimer

This repository is a scientific product and is not official communication of the National Oceanic and Atmospheric Administration, or the United States Department of Commerce. All NOAA GitHub project content is provided on an "as is" basis and the user assumes responsibility for its use. Any claims against the Department of Commerce or Department of Commerce bureaus stemming from the use of this GitHub project will be governed by all applicable Federal law. Any reference to specific commercial products, processes, or services by service mark, trademark, manufacturer, or otherwise, does not constitute or imply their endorsement, recommendation or favoring by the Department of Commerce. The Department of Commerce seal and logo, or the seal and logo of a DOC bureau, shall not be used in any manner to imply endorsement of any commercial product or activity by DOC or the United States Government.

About

This repository stores a machine learning model for using calibrated singe beam hydroacoustic data to determine seafloor habitat type. Outputs from the model for the Gulf of Alaska are also included. Details are in "Seabed classification in the Gulf of Alaska from acoustic surveys using deep learning" by K. Agarwal, C. Rooper and K. Williams

Resources

License

Code of conduct

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages