Skip to main content

Autonomously Collected Benthic Imagery for Substrate Prediction, Lake Michigan 2020-2021

Dates

Publication Date
Start Date
2020-08-06
End Date
2021-09-15

Citation

Geisz, J.K., Wernette, P.A., Esselman, P.C., and Morris, J.M., 2024, Autonomously Collected Benthic Imagery for Substrate Prediction, Lake Michigan 2020-2021: U.S. Geological Survey data release, https://doi.org/10.5066/P9N32CV7.

Summary

These data consist of down-looking images of Lake Michigan benthos, collected in 2020 and 2021 with an autonomous underwater vehicle (AUV). Information about each image (i.e., latitude, longitude, depth from surface, altitude, roll, pitch, yaw, and creation time) can be found in the associated csv file. Substrate type was divided into 9 classes based on the Coastal and Marine Ecological Classification Standard (CMECS) and each image was assigned a substrate class by at least 3 trained labelers.

Contacts

Point of Contact :
Peter C Esselman
Originator :
Joseph K Geisz, Phillipe A Wernette, Peter C Esselman, Jennifer M Morris
Metadata Contact :
Joseph K Geisz
Publisher :
U.S. Geological Survey
SDC Data Owner :
Great Lakes Science Center
USGS Mission Area :
Ecosystems
Distributor :
U.S. Geological Survey - ScienceBase

Attached Files

Click on title to download individual files attached to this item.

Granule.zip 171.81 MB application/zip
Bedrock.zip 673.4 MB application/zip
Pebble.zip 1.65 GB application/zip
Gravelly.zip 1.78 GB application/zip
SlightlyGravelly.zip 2 GB application/zip
6.25 GB application/zip
12.16 GB application/zip
16.28 GB application/zip
23.97 GB application/zip
21.07 GB application/x-zip-compressed
Info.csv 1.22 MB text/csv

Purpose

These images are a ground-truth dataset for training machine learning algorithms to automatically assign substrate type to images. Such algorithms significantly reduce manual labeling time. Knowledge of substrate type across Lake Michigan is useful for estimating fish and other species abundance as certain species prefer different substrate habitat. Labeled images paired with latitude and longitude information can serve as ground-truth for mapping large extents of lakebed. Great Lakes managers can then use this information to make decisions about stocking, trawling locations, and more.

Additional Information

Identifiers

Type Scheme Key
DOI https://www.sciencebase.gov/vocab/category/item/identifier doi:10.5066/P9N32CV7

Item Actions

View Item as ...

Save Item as ...

View Item...