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.

This dataset reports plankton species abundance from 14 sites off the Florida Panhandle Bight at the head of DeSoto Canyon, Gulf of Mexico aboard the R/V Bellows cruise BE-1317 from 2013-04-06 to 2013-04-08. Plankton samples were collected using a net with a mesh size of 25 micrometer and 0.5m diameter. This dataset reports the location, date, time, and length of tow for each sample. Plankton species were categorized as Ceratium spp., Dinophysis spp., other dinoflagellates, Chaetoceros/Bacteriastrum spp., Rhizosolenia/Guinardia spp, Eucampia/Hemiaulus spp., other chain-forming diatoms, Thalassionematales spp., Nitzschioid diatoms, other diatoms, Cyanobacteria (Trichodesmium spp.), and zooplankton. Abundances were recorded as individual counts as well as percentages of the total sample. Quantitative phytoplankton profiles were taken specifically at 5 sites (P1, P3, P5, P7, P9). For this, one-liter samples were collected from the surface and at different depths using Niskin bottles. Samples were filtered onto a 0.45 micrometer nitrocellulose filter and air-dried. A portion of each filter was mounted on an aluminum stub, sputter-coated, and examined with a JEOL JSM-6480 LV scanning electron microscope. Diatoms, coccolithophores, and armored dinoflagellates were identified to the lowest possible taxonomic category. The number of cells of each taxon in a field of view at a magnification of 1000x was recorded, with up to 700 fields-of-view examined, depending on the density of phytoplankton in the sample. The dataset includes the depth, the volume filtered, the number of cells of each taxon counted, and the calculated abundance of each taxon in cells per liter. Micrographs taken during the analysis are included.

This dataset reports plankton species relative abundances from sites off the Florida Panhandle Bight at the head of DeSoto Canyon. Plankton samples were collected from 15 offshore shelf sites from June 02 to June 04, 2013. It includes sites, date/times, length of tow, plankton samples, counts, and the percentage of total sample represented by each group. Plankton species were categorized as Ceratium spp., Dinophysis spp., other dinoflagellates, Chaetoceros/Bacteriastrum spp., Rhizosolenia/Guinardia spp, Eucampia/Hemiaulus spp., other chain-forming diatoms, Thalassionematales spp., Nitzschioid diatoms, other diatoms, Cyanobacteria (Trichodesmium spp.), and zooplankton.

This dataset includes plankton taxa and counts, gear type, tow type, net mouth diameter and mesh size. The data were collected from 1928 through 1987 from numerous vessels worldwide. The data were compiled by the Smithsonian Oceanographic Sorting Center (SOSC) and submitted to NODC in 1994.

This dataset contains plankton abundance, CTD, and water quality data collected from 18 stations during R/V Bellows cruise BE-1407 in the Gulf of Mexico from 2013-12-07 to 2013-12-08. Plankton samples were collected from 10 offshore shelf sites. This dataset reports the location, date, time, and length of tow for each sample. Plankton species were categorized as Ceratium spp., Dinophysis spp., other dinoflagellates, Chaetoceros/Bacteriastrum spp., Rhizosolenia/Guinardia spp, Eucampia/Hemiaulus spp., other chain-forming diatoms, Thalassionematales spp., Nitzschioid diatoms, other diatoms, Cyanobacteria (Trichodesmium spp.), and zooplankton. Abundances were recorded as individual counts as well as percentages of the total sample. Water column profiles were collected at 18 stations and the data includes CTD, dissolved oxygen, oxygen saturation, Chlorophyll-a, and Color Dissolved Organic Matter (CDOM) fluorescence and turbidity measurements.