10.1594/PANGAEA.724540
Gorsky, G
G
Gorsky
0000-0002-1099-8711
Ohman, Mark D
Mark D
Ohman
0000-0001-8136-3695
Picheral, Marc
Marc
Picheral
0000-0001-8172-5473
Gasparini, Stéphane
Stéphane
Gasparini
Stemmann, Lars
Lars
Stemmann
0000-0001-8935-4531
Romagnan, Jean-Baptiste
Jean-Baptiste
Romagnan
Cawood, A
A
Cawood
0000-0002-7849-0412
Pesant, Stephane
Stephane
Pesant
0000-0002-4936-5209
García-Comas, Carmen
Carmen
García-Comas
0000-0001-8054-3918
Prejge, Franck
Franck
Prejge
Time series of ZOOSCAN images and results of zooplankton samples at Villefranche from 1966 to 2003
PANGAEA
2010
Monitoring
Observatoire Océanologique de Villefranche-sur-Mer
https://ror.org/05r5y6641
1966-11-23T00:00:00/2003-12-10T00:00:00
Supplementary Publication Series of Datasets
10.1093/plankt/fbp124
76 datasets
application/zip
Creative Commons Attribution 3.0 Unported
ZooScan with ZooProcess and Plankton Identifier (PkID) software is an integrated analysis system for acquisition and classification of digital zooplankton images from preserved zooplankton samples. Zooplankton samples are digitized by the ZooScan and processed by ZooProcess and PkID in order to detect, enumerate, measure and classify the digitized objects. Here we present a semi-automatic approach that entails automated classification of images followed by manual validation, which allows rapid and accurate classification of zooplankton and abiotic objects. We demonstrate this approach with a biweekly zooplankton time series from the Bay of Villefranche-sur-mer, France. The classification approach proposed here provides a practical compromise between a fully automatic method with varying degrees of bias and a manual but accurate classification of zooplankton. We also evaluate the appropriate number of images to include in digital learning sets and compare the accuracy of six classification algorithms. We evaluate the accuracy of the ZooScan for automated measurements of body size and present relationships between machine measures of size and C and N content of selected zooplankton taxa. We demonstrate that the ZooScan system can produce useful measures of zooplankton abundance, biomass and size spectra, for a variety of ecological studies.
The collection of zooplankton was performed using vertical trait of the Juday Bogorov net (mesh size = 330 µm, opening = 0.196 m**2) from 75 m depth to surface at Point B. The samples were stored in buffered formaldehyde (4%) from the collection date to the date of digitalisation on the ZOOSCAN. The data base consists of high definition images that will be of public access in January 2011. These images were analysed using ZOOPROCESS and objects have been recognised for 9 groups of plankton (i.e. Appendicularians, Chaetognaths, Cladocerans, Doliolidas, Copepods, Decapods, Eggs, Gelatinous organisms, Pteropods) using the Plankton Identifier software with the Random Forest algorithm performed on the learning set learn_jb_200812.pid (http://hs.pangaea.de/bio/zooscan/learn_jb_200812.pid). The performance of the recognition was assessed by calculating a matrix of confusion (frequency of true positive identification). The abundance and biovolume time series given in the tables consist of the predicted copepods and total plankton organisms (9 groups).
Supplement to: Gorsky, G; Ohman, Mark D; Picheral, Marc; Gasparini, Stéphane; Stemmann, Lars; Romagnan, Jean-Baptiste; Cawood, A; Pesant, Stephane; García-Comas, Carmen; Prejge, Franck (2010): Digital zooplankton image analysis using the ZooScan integrated system. Journal of Plankton Research, 32(3), 285-303
7.314800000000063
43.68620000000009
Villefranche sur Mer, France