Images of phytoplankton used in the development of a convolutional neural network to automate phytoplankton identification
We collected >160,000 images of particles using an imaging flow cytometer (the FlowCam). Images were then identified manually using morphology to the lowest taxonomic resolution possible. Greater than half of those images were either zooplankton, detritus or could not be identified (unknown). These identified images were then used to train and test a convolutional neural network. This convolutional neural network model can then be used to make predictions on new images collected with the FlowCam, with an apparent accuracy of 86% overall.
Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government.
Find Related Datasets
Search by Tags
Click any tag below to search for similar datasets
Complete Metadata
| accessLevel | public |
|---|---|
| bureauCode |
[ "010:12" ] |
| contactPoint |
{ "fn": "James H Larson", "@type": "vcard:Contact", "hasEmail": "mailto:jhlarson@usgs.gov" } |
| description | We collected >160,000 images of particles using an imaging flow cytometer (the FlowCam). Images were then identified manually using morphology to the lowest taxonomic resolution possible. Greater than half of those images were either zooplankton, detritus or could not be identified (unknown). These identified images were then used to train and test a convolutional neural network. This convolutional neural network model can then be used to make predictions on new images collected with the FlowCam, with an apparent accuracy of 86% overall. Any use of trade, firm, or product names is for descriptive purposes only and does not imply endorsement by the U.S. Government. |
| distribution |
[ { "@type": "dcat:Distribution", "title": "Digital Data", "format": "XML", "accessURL": "https://doi.org/10.5066/P13UVPTY", "mediaType": "application/http", "description": "Landing page for access to the data" }, { "@type": "dcat:Distribution", "title": "Original Metadata", "format": "XML", "mediaType": "text/xml", "description": "The metadata original format", "downloadURL": "https://data.usgs.gov/datacatalog/metadata/USGS.6a186360b66b01fcab049f44.xml" } ] |
| identifier | http://datainventory.doi.gov/id/dataset/USGS_6a186360b66b01fcab049f44 |
| keyword |
[ "Fox River (WI)", "Great Lakes", "Illinois River (IL)", "Kabetogama Lake", "Mississippi River (WI)", "USGS:6a186360b66b01fcab049f44", "Voyageurs National Park", "algae", "biota", "cyanobacteria", "diatoms", "phytoplankton" ] |
| modified | 2026-08-18T00:00:00Z |
| publisher |
{ "name": "U.S. Geological Survey", "@type": "org:Organization" } |
| spatial | -94.8560, 42.6340, -88.0005, 48.8647 |
| theme |
[ "geospatial" ] |
| title | Images of phytoplankton used in the development of a convolutional neural network to automate phytoplankton identification |
