Dataset summary Plankton and detritus are essential components of the Earth’s oceans influencing biogeochemical cycles and carbon sequestration. Climate change impacts their composition and marine ecosystems as a whole. To improve our understanding of these changes, standardized observation methods and integrated global datasets are needed to enhance the accuracy of ecological and climate models. Here, we present a global dataset for plankton and detritus obtained by two versions of the Underwater Vision Profiler 5 (UVP5). This release contains the images classified in 33 homogenized categories, as well as the metadata associated with them, reaching 3,114 profiles and ca. 8 million objects acquired between 2008-2018 at global scale. The geographical distribution of the dataset is unbalanced, with the Equatorial region (30° S - 30° N) being the most represented, followed by the high latitudes in the northern hemisphere and lastly the high latitudes in the Southern Hemisphere. Detritus is the most abundant category in terms of concentration (90%) and biovolume (95%), although its classification in different morphotypes is still not well established. Copepoda was the most abundant taxa within the plankton, with Trichodesmium colonies being the second most abundant. The two versions of UVP5 (SD and HD) have different imagers, resulting in a different effective size range to analyse plankton and detritus from the images (HD objects >600 µm, SD objects >1 mm) and morphological properties (grey levels, etc.) presenting similar patterns, although the ranges may differ. A large number of images of plankton and detritus will be collected in the future by the UVP5, and the public availability of this dataset will help it being utilized as a training set for machine learning and being improved by the scientific community. This will reduce uncertainty by classifying previously unclassified objects and expand the classification categories, ultimately enhancing biodiversity quantification. Data tables The data set is organised according to: - samples : Underwater Vision Profiler 5 profiles, taken at a given point in space and time. - objects : individual UVP images, taken at a given depth along the each profile, on which various morphological features were measured and that where then classified taxonomically in EcoTaxa. samples and objects have unique identifiers. The sample_id is used to link the different tables of the data set together. All files are Tab separated values, UTF8 encoded, gzip compressed. samples.tsv.gz - sample_id    <int>    unique sample identifier - sample_name    <text>    original sample identifier - project    <text>    EcoPart project title - lat, lon    <float>    location [decimal degrees] - datetime    <text>    date and time of start of profile [ISO 8601: YYYY-MM-DDTHH:MM:SSZ] - pixel_size    <float>    size of one pixel [mm] - uvp_model    <text>    version of the UVP: SD: standard definition, ZD: zoomed, HD: high definition samples_volume.tsv.gz Along a profile, the UVP takes many images, each of a fixed volume. The profiles are cut into 5 m depth bins in which the number of images taken is recorded and hence the imaged volume is known. This is necessary to compute concentrations. - sample_id    <int>    unique sample identifier - mid_depth_bin    <float>    middle of the depth bin (2.5 = from 0 to 5 m depth) [m] - water_volume_imaged    <float>    volume imaged = number of full images × unit volume [L] objects.tsv.gz - object_id    <int>     unique object identifier - object_name    <text>     original object identifier - sample_id    <int>     unique sample identifier - depth    <float>    depth at which the image was taken [m] - mid_depth_bin    <float>    corresponding depth bin [m]; to match with samples_volumes - taxon    <text>     original taxonomic name as in EcoTaxa; is not consistent across projects - lineage    <text>     taxonomic lineage corresponding to that name - classif_author    <text>     unique, anonymised identifier of the user who performed this classification - classif_datetime    <text>     date and time at which the classification was - group    <text>     broader taxonomic name, for which the identification is consistent over the whole dataset - group_lineage    <text>     taxonomic lineage corresponding to this broader group - area_mm2    <float>    measurements on the object, in real worl units (i.e. comparable across the whole dataset) … - major_mm    <float> - area    <float>    measurements on the objet, in [pixels] and therefore not directly comparable among the different UVP models and units - mean    <float> … - skeleton_area    <float> properties_per_bin.tsv.gz The information above allows to compute concentrations, biovolumes, and average grey level within a given depth bin. The code to do so is in `summarise_objects_properties.R`. - sample_id    <int>     unique sample identifier - depth_range    <text>     range of depth over which the concentration/biovolume are computed: (start,end], in [m] where `(` means not including, `]` means including - group    <text>     broad taxonomic group - concentration    <float>    concentration [ind/L] - biovolume    <float>    biovolume [mm3/L] - avg_grey    <float>    average grey level of particles [no unit; 0 is black, 255 is white] ODV_biovolumes.txt, ODV_concentrations.txt, ODV_grey_levels.txt This is the same information as above, formatted in a way that Ocean Data View https://odv.awi.de can read. In ODV, go to Import > ODV Spreadsheet and accept all default choices. Images The images are provided in a separate, much larger, zip file. They are stored with the format `sample_id/object_id.jpg`, where `sample_id` and `object_id` are the integer identifiers used in the data tables above.

Plankton was sampled with various nets, from bottom or 500m depth to the surface, in many oceans of the world. Samples were imaged with a ZooScan. The full images were processed with ZooProcess which generated regions of interest (ROIs) around each individual object and a set of associated features measured on the object (see Gorsky et al 2010 for more information). The same objects were re-processed to compute features with the scikit-image toolbox http://scikit-image.org. The 1,451,745 resulting objects were sorted by a limited number of operators, following a common taxonomic guide, into 98 taxa, using the web application EcoTaxa http://ecotaxa.obs-vlfr.fr. For the purpose of training machine learning classifiers, the images in each class were split into training, validation, and test sets, with proportions 70%, 15% and 15%. The folder ZooScanNet_data.tar contains : taxa.csv.gz Table of the classification of each object in the dataset, with columns : - objid: unique object identifier in EcoTaxa (integer number) - taxon_level1: taxonomic name corresponding to the level 1 classification - lineage_level1: taxonomic lineage corresponding to the level 1 classification - taxon_level2: name of the taxon corresponding to the level 2 classification  - plankton: if the object is a plankton or not (boolean) - set: class of the image corresponding to the taxon (train : training, val : validation, or test) - img_path: local path of the image corresponding to the taxon (of level 1), named according to the object id features_native.csv.gz Table of metadata of each object including the different features processed by ZooProcess. All features are computed on the object only, not the background. All area/length measures are in pixels. All grey levels are in encoded in 8 bits (0=black, 255=white). With columns: - objid: unique object identifier in EcoTaxa (integer number) And 48 features: - area - mean - stddev - mode - min/max - perim. - width,height  - major,minor - circ. - feret - intden - median - skew,kurt - %area - area_exc - fractal - skelarea - slope - histcum1,2,3 - nb1,2,3 - symetrieh,symetriev - symetriehc,symetrievc - convperim,convarea - fcons - thickr:  - esd - elongation - range - centroids - sr - perimareaexc - feretareaexc - perimferet/perimmajor - circex - cdexc See the “ZooScan” sheet - OBJECT metadata, annotation and measurements - , at https://doi.org/10.5281/zenodo.14704250 for definitions. features_skimage.csv.gz Table of morphological features recomputed with skimage.measure.regionprops on the ROIs produced by ZooProcess. See http://scikit-image.org/docs/dev/api/skimage.measure.html#skimage.measure.regionprops for documentation. inventory.tsv Tree view of the taxonomy and number of images in each taxon, displayed as text. With columns : - lineage_level1: taxonomic lineage corresponding to the level 1 classification - taxon_level1: name of the taxon corresponding to the level 1 classification - n: number of objects in each taxon class          2. Second folder ZooScanNet_imgs.tar contains : imgs Directory containing images of each object, named according to the object id objid and sorted in subdirectories according to their taxon.         3. And : map.png Map of the sampling locations, to give an idea of the diversity sampled in this dataset.  

Here, we provide plankton image data that was sorted with the web applications EcoTaxa and MorphoCluster. The data set was used for image classification tasks as described in Schröder et. al (in preparation) and does not include any geospatial or temporal meta-data. Plankton was imaged using the Underwater Vision Profiler 5 (Picheral et al. 2010) in various regions of the world's oceans between 2012-10-24 and 2017-08-08. This data publication consists of an archive containing  "training.csv" (list of 392k training images for classification, validated using EcoTaxa), "validation.csv" (list of 196k validation images for classification, validated using EcoTaxa), "unlabeld.csv" (list of 1M unlabeled images), "morphocluster.csv" (1.2M objects validated using MorphoCluster, a subset of "unlabeled.csv" and "validation.csv") and the image files themselves. The CSV files each contain the columns "object_id" (a unique ID), "image_fn" (the relative filename), and "label" (the assigned name). The training and validation sets were sorted into 65 classes using the web application EcoTaxa (http://ecotaxa.obs-vlfr.fr). This data shows a severe class imbalance; the 10% most populated classes contain more than 80% of the objects and the class sizes span four orders of magnitude. The validation set and a set of additional 1M unlabeled images were sorted during the first trial of MorphoCluster (https://github.com/morphocluster). The images in this data set were sampled during RV Meteor cruises M92, M93, M96, M97, M98, M105, M106, M107, M108, M116, M119, M121, M130, M131, M135, M136, M137 and M138, during RV Maria S Merian cruises MSM22, MSM23, MSM40 and MSM49, during the RV Polarstern cruise PS88b and during the FLUXES1 experiment with RV Sarmiento de Gamboa. The following people have contributed to the sorting of the image data on EcoTaxa: Rainer Kiko, Tristan Biard, Benjamin Blanc, Svenja Christiansen, Justine Courboules, Charlotte Eich, Jannik Faustmann, Christine Gawinski, Augustin Lafond, Aakash Panchal, Marc Picheral, Akanksha Singh and Helena Hauss In Schröder et al. (in preparation), the training set serves as a source for knowledge transfer in the training of the feature extractor. The classification using MorphoCluster was conducted by Rainer Kiko. Used labels are operational and not yet matched to respective EcoTaxa classes.