Find research datasets worth reusing
Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.
4
datasets available to search
ShareScore release 0.9.0
Dataset results
4 results for “Flowcam”
LifeWatch observatory data: phytoplankton annotated trainingset by FlowCam imaging in the Belgian Part of the North Sea
<h1>Training dataset </h1> <p>The images were collected in the framework of the Belgian Lifewatch Research Infrastructure. During multidisciplinary campaigns, a number of fixed stations in the Belgian Part of the North Sea (BPNS) are visited on a monthly (onshore stations) or seasonal (offshore stations) basis. Samples are taken using a 55µm mesh size Apstein net and fixed in Lugol's iodine solution. In the lab, the samples are processed using a VS-4 FlowCAM model at 4X magnification targeting a particle size range of 55-300µm. The identification of the image data is done with the use of a CNN and followed by a manual validation step. Since May 2017, this dataset has provided micro- and phytoplankton observations, mainly covering diatoms, dinoflagellates and cilliates, for the Belgian Part of the North Sea (BPNS).</p> <p> </p> <p>This dataset comprises a trainings datasplit of 337,514 images distributed across 95 classes, with each class containing a minimum of 100 and a maximum of 10,000 images. The goal of this dataset is to be able to facilitate model training, here we have organized the data into a standard split, with 80% allocated for training, 10% for validation, and another 10% for testing purposes. This dataset structure ensures a balanced representation and supports scientific rigor in subsequent analyses.</p> <h1>Technical details </h1> <h2>Data preprocessing </h2> <p>Raw FlowCam output data is fully processed using in-house datapipelines, the VisualSpreadsheet software is only used for data acquisition during the lab run of the sample. Raw images and binary images are never saved during the FlowCam run, we only work on the image collages saved at the end of the run. Single images are cut from these collages using each image coordinates width and height pulled from the .lst file using in-house python code. The background of the images is not removed. These images are then predicted and annotated in-house at VLIZ.</p> <h2>Data splitting </h2> <p>The training dataset is 80% used for training, 10% for validation and 10% for prediction. </p> <h2>Classes, labels and annotations</h2> <p>The dataset comprises 337,514 images distributed across 95 classes, with each class containing a minimum of 100 and a maximum of 10,000 images. Taxonomic coverage of the dataset comprises mainly of diatoms, dinoflagellates and cilliates, but to a lesser extent also zooplankton and other protists.</p> <h2>Parameters </h2> <p>The images are read using cv2.imread and the values are used as parameters.</p> <p><strong>Metadata Parameter Descriptions:</strong></p> <ul> <li> <p><strong>image_path</strong>: The relative path to the image file showing the plankton or particle, usually structured by taxon or project folder.</p> </li> <li> <p><strong>sample_datetime</strong>: The exact date and time (in YYYY-MM-DD HH:MM:SS.sss format) when the sample was acquired using the imaging instrument.</p> </li> <li> <p><strong>flowcam_version</strong>: The software or hardware version of the FlowCAM instrument used to capture the image and process the sample.</p> </li> <li> <p><strong>station</strong>: The sampling location code where the image was taken. These station codes typically refer to predefined geographic or monitoring points in the field.</p> </li> <li> <p><strong>accepted_label</strong>: The final validated taxonomic label (e.g., genus or species) assigned to the organism or particle in the image, often based on expert review.</p> </li> <li> <p><strong>accepted_aphia_id</strong>: The unique identifier (AphiaID) corresponding to the accepted taxonomic label in the <strong>World Register of Marine Species (WoRMS)</strong> database, which ensures standardized taxonomic reference.</p> </li> <li> <p><strong>original_reference_id</strong>: A unique identifier (often a UUID) assigned to the image or sample in the original classification system (e.g., EcoTaxa), useful for traceability and linking back to the source record.</p> </li> </ul> <h2>Data sources </h2> <p>Images are collected during the monthly monitoring of phytoplankton communities in the Belgian Part of the North Sea during the LifeWatch multidisciplinary campaigns by FlowCam VS-4 benchmodel (Fluid Imaging Technologies, Yarmouth, Maine, U.S.A.).</p> <h2>Data quality </h2> <p>All images are predicted and subsequently manually validated to ensure the quality of the trainingset.</p> <h2>Image resolution </h2> <p>The size range imaged is 55-300µm. Images are acquired using a Sony XCD SC90 digital gray-scale camera. Images are during training of CNN resized to 100px by 100px.</p> <h2>Spatial coverage </h2> <p>The data comes from a number of fixed stations in the Belgian Part of the North Sea (BPNS). </p> <p>Nine stations onshore are visited monthly:</p> <table> <tbody> <tr> <td><strong>Station</strong></td> <td><strong>Longitude</strong></td> <td><strong>Latitude</strong></td> </tr> <tr> <td>130</td> <td>2.90535</td> <td>51.27055</td> </tr> <tr> <td>780</td> <td>3.057283</td> <td>51.471367</td> </tr> <tr> <td>330</td> <td>2.809083</td> <td>51.434117</td> </tr> <tr> <td>230</td> <td>2.85035</td> <td>51.308683</td> </tr> <tr> <td>710</td> <td>3.138283</td> <td>51.441217</td> </tr> <tr> <td>215</td> <td>2.61075</td> <td>51.274867</td> </tr> <tr> <td>ZG02</td> <td>2.500717</td> <td>51.33515</td> </tr> <tr> <td>120</td> <td>2.702483</td> <td>51.186083</td> </tr> <tr> <td>700</td> <td>3.221017</td> <td>51.377</td> </tr> </tbody> </table> <p>Eight additional offshore stations are visited seasonally:</p> <table> <tbody> <tr> <td><strong>Station</strong></td> <td><strong>Longitude</strong></td> <td><strong>Latitude</strong></td> </tr> <tr> <td>LW01</td> <td>2.256</td> <td>51.568667</td> </tr> <tr> <td>LW02</td> <td>2.556</td> <td>51.8</td> </tr> <tr> <td>435</td> <td>2.790333</td> <td>51.580667</td> </tr> <tr> <td>W07bis</td> <td>3.012517</td> <td>51.588033</td> </tr> <tr> <td>W08</td> <td>2.35</td> <td>51.458333</td> </tr> <tr> <td>W09</td> <td>2.7</td> <td>51.75</td> </tr> <tr> <td>W10</td> <td>2.416667</td> <td>51.683333</td> </tr> <tr> <td>421</td> <td>2.45</td> <td>51.4805</td> </tr> </tbody> </table> <h2> </h2> <h2>Temporal coverage </h2> <p>The monitoring was initiated in May 2017 and has been running continuously every month.</p> <h2>Contact information </h2> <p>For technical questions about training dataset, you can contact wout.decrop@vliz.be. </p> <p> </p> <p> </p> <p> </p> <p> </p>
LifeWatch observatory data: phytoplankton annotated image library by FlowCam imaging for the Belgian part of the North Sea.
<p>In the framework of the Lifewatch marine observatory a number of fixed stations in the Belgian Part of the North Sea (BPNS) are sampled for phytoplankton monitoring. Samples are processed using a VS-4 FlowCAM model at 4X magnification, size range imaged is 55-300µm. The identification of the image data is done with the use of a classifier and followed by a manual validation step. These dataset comprises the full annotated image dataset which can be sampled for training of convolutional neural networks.</p>
Microplankton counts from discrete water column samples using flow imaging microscopy (FlowCam) from Lakes Fryxell and Hoare, McMurdo Dry Valleys, Antarctica (2007-2011)
This data package consists of microplankton counts from discrete water column samples collected at various depths in Lake Fryxell and Lake Hoare in the McMurdo Dry Valleys region of Antarctica. Samples were collected and preserved during the austral summer-autumn transition in 2007-2008 and in addition to routine McMurdo Dry Valley Long Term Ecological Research (LTER) core limnological sampling in November and December of 2008, 2010, and 2011. Data were imaged using flow cytometry (FlowCam VS-IV) and classified with statistical image-based software (Visual Spreadsheet, v4.17.14). These data include haptorian ciliates, filamentous cyanobacteria, and coccoidal algae particle counts per milliliter that were automatically classified from user-built libraries and statistical filters based on the morphological characterizations of the plankton.
Haptorian ciliate measurements from discrete water column samples using flow imaging microscopy (FlowCam) from Lakes Fryxell and Hoare, McMurdo Dry Valleys, Antarctica (2007-2020)
This data package consists of particle diameter and biovolume data for haptorian ciliates classified from discrete water column samples collected at various depths in Lake Fryxell and Lake Hoare in the McMurdo Dry Valleys region of Antarctica. Samples were collected and preserved between November 2007 and January 2020 in Lake Fryxell and between November 2007 and March 2008 in Lake Hoare. Samples were collected and analyzed as part of the McMurdo Dry Valleys Long Term Ecological Research (LTER) core limnological sampling. Data were imaged using flow cytometry (FlowCam VS-IV) and imaged particles were classified with statistical image-based software (Visual Spreadsheet, v4.17.14). Diameter and biovolume was generated for each particle using FlowCam’s area-based diameter (ABD) algorithm.
ScienceDex guides
Understand access before you commit
These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.
Allen Brain Atlas
Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.
Annotated Behaviour and Observability Dataset (ABODe)
ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.
DANDI Archive for NWB datasets
DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.
International Brain Laboratory public data
The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.
OpenNeuro
OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.