Physical, nutrients, and plankton data were collected using plankton net and bottle casts in the South Pacific Ocean from 01 August 1961 to 09 September 1965. Data were submitted by the Instituto Del Mar Del Peru; Callao. Plankton data include both zooplankton and phytoplankton.

Thirty-nine plankton samples were collected at the Drift Station "Arlis II" at the north of Greenland in the Arctic Ocean during the period from June to December, 1964. From the samples thirty-two species of copepods were identified, of which Calanus glacialis, C. hyperboreus, Microcalanus pygmaeus, Spinocalanus abyssalis, Metridia longa and Oithona similis were major components. The maximum plankton biomass throughout the period was observed in July when C. hyperboreus was predominant. The plankton population during day season (light season from June to August) was characterized by abundance of C. hyperboreus, M. pygmaeus and O. similis, while the population during night season (dark season from September to December) was characterized by abundance of M. pygmaeus and O. similis. Developmental stages of C. hyperboreus were collected in bulk in summer, suggesting that this species was breeding under the permanent ice floe.

Data presented here are subset of a larger plankton imagery data set collected in the subtropical Straits of Florida from 2014-05-28 to 2014-06-14. Imagery data were collected using the In Situ Ichthyoplankton Imaging System (ISIIS-2) as part of a NSF-funded project to assess the biophysical drivers affecting fine-scale interactions between larval fish, their prey, and predators. This subset of images was used in the inaugural National Data Science Bowl (www.datasciencebowl.com) hosted by Kaggle and sponsored by Booz Allen Hamilton. Data were originally collected to examine the biophysical drivers affecting fine-scale (spatial) interactions between larval fish, their prey, and predators in a subtropical pelagic marine ecosystem. Image segments extracted from the raw data were sorted into 121 plankton classes, split 50:50 into train and test data sets, and provided for a machine learning competition (the National Data Science Bowl). There was no hierarchical relationships explicit in the 121 plankton classes, though the class naming convention and a tree-like diagram (see file "Plankton Relationships.pdf") indicated relationships between classes, whether it was taxonomic or structural (size and shape). We intend for this dataset to be available to the machine learning and computer vision community as a standard machine learning benchmark. This “Plankton 1.0” dataset is a medium-size dataset with a fair amount of complexity where image classification improvements can still be made.

The project was a multi-year observation of zooplankton during the spring bloom period in a subarctic embayment. A small vessel belonging to the University of Alaska Juneau Center for Fisheries and Ocean Sciences was used to collect the data. Collections were made twice weekly using a CalVET net and a 1-m NIO Net. The CalVET net had 165 micrometer mesh, the NIO net had 500 micrometer mesh. Three to 4 stations were sampled in the bay and adjacent inlet.