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.
1,944
datasets available to search
ShareScore release 0.9.0
Dataset results
1,944 results for “Class I”
OpenStreetMap+ Land Use / Land Cover classes and administrative regions of Europe
<p>This dataset contains 23 30m resolution raster data of continental Europe land use / land cover classes extracted from <a href="https://www.openstreetmap.org/">OpenStreetMap</a>, as well as administrative areas, and a harmonized building dataset based on OpenStreetMap and <a href="https://land.copernicus.eu/pan-european/high-resolution-layers/imperviousness#:~:text=The%20imperviousness%20products%20capture%20the,over%20long%20periods%20of%20time.">Copernicus HRL Imperviousness</a> data.</p> <p>The land use / land cover classes are:</p> <ol> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:building%3Dcommercial">buildings.commercial</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:building%3Dindustrial">buildings.industrial</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:building%3Dresidential">buildings.residential</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dcemetery">cemetery</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dconstruction">construction.site</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dlandfill">dump.site (landfill)</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dfarmland">farmland</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dfarmyard">farmyard</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dforest">forest</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dgrass">grass</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:building%3Dgreenhouse">greenhouse</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dharbour">harbour</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dmeadow">meadow</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dmilitary">military</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dorchard">orchard</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dquarry">quarry</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:railway%3Drail">railway</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dreservoir">reservoir</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:highway%3Droad">road</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dsalt_pond">salt</a></li> <li><a href="https://wiki.openstreetmap.org/wiki/Tag:landuse%3Dvineyard">vineyard</a></li> </ol> <p>The land use / land cover data was generated by extracting OSM vector layers from https://download.geofabrik.de/). These were then transformed into a 30 m density raster for each feature type. This was done by first creating a 10 m raster where each pixel intersecting a vector feature was assigned the value 100. These pixels were then aggregated to 10 m resolution by calculating the average of every 9 adjacent pixels. This resulted in a 0—100 density layer for the three feature types. Although the digitized building data from OSM offers the highest level of detail, its coverage across Europe is inconsistent. To supplement the building density raster in regions where crowd-sourced OSM building data was unavailable, we combined it with Copernicus High Resolution Layers (HRL) (obtained from https://land.copernicus.eu/pan-european/ high-resolution-layers), filling the non-mapped areas in OSM with the Impervious Built-up 2018 pixel values, which was averaged to 30 m. The probability values produced by the averaged aggregation were integrated in such a way that values between 0—100 refer to OSM (lowest and highest probabilities equal to 0 and 100 respectively), and the values between 101—200 refer to Copernicus HRL (lowest and highest probability equal to 200 and 101 respectively). This resulted in a raster layer where values closer to 100 are more likely to be buildings than values closer to 0 and 200. Structuring the data in this way allows us to select the higher probability building pixels in both products by the single boolean expression: Pixel > 50 AND pixel <150.</p> <p>This dataset is part of the OpenStreetMap+ was used to pre-process the LUCAS/CORINE land use / land cover samples (https://doi.org/10.5281/zenodo.4740691) used to train machine learning models in Witjes et al., 2022 (https://doi.org/10.21203/rs.3.rs-561383/v4)</p> <p>Each layer can be viewed interactively on the Open Data Science Europe data viewer at <a href="https://maps.opendatascience.eu/?base=OpenStreetMap%20(grayscale)&layer=Copernicus-OSM%20buildings&zoom=4&eye=5000000&center=53.7139,17.0066&opacity=45">maps.opendatascience.eu</a>.</p>
Bag of pitch classes for Japanese enka songs
<p>This dataset is comprised of 827 songs, curated from the following publications:</p> <p>(a) Y. Goto (ed.), Grand Collection of Enka Songs by Female Singers 5th Ed. (in Japanese), Zen-on Music Co., 2016.<br> (b) Y. Goto (ed.), Grand Collection of Enka Songs by Male Singers 5th Ed. (in Japanese), Zen-on Music Co., 2016.</p> <p>Upon the use of this work, we kindly ask to explicitly cite/mention this paper, where the dataset was first used:</p> <p>[1] Eita Nakamura, Kentaro Shibata, Ryo Nishikimi, Kazuyoshi Yoshii, “Unsupervised melody style conversion,” Proc. 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 196-200, May 2019.</p> <p>** Data **</p> <p>EnkaDataBagOfPitchClasses.tsv</p> <p>Each line represents a song.</p> <p>The first column indicates the song's location in the publications. For example, EnkaF-030_p027 indicates the 30th song on page 27 by a female artist in (a).</p> <p>From the second column to the 13th column, the numbers represent the counts for pitch classes from C to B. Tied notes were merged and counted only once.</p>
The benchmark datasets for Multi-class Change Detection (MCD)
<p>Change detection (CD) provides a research basis for environmental monitoring, urban expansion and reconstruction as well as disaster assessment, by identifying the changes of ground objects in different time periods. Traditional CD focused on the binary change detection (BCD), focusing solely on the change and no-change regions. Due to the dynamic progress of earth observation satellite techniques, the spatial resolution of remote sensing images continues to increase, multi-class change detection (MCD) which can reflect more detailed land change has become a hot research direction in the field of CD.<strong> </strong></p> <p>We have collected the current open source benchmark datasets in the MCD of remote sensing imagery , in order to facilitate the sharing of the latest research datasets in the MCD field. Users can access the relevant MCD datasets through the links in the files.</p> <p>Source:</p> <p>Q. Zhu, X. Guo, Ziqi Li, D. Li*, “A review of Multi-class Change Detection for Remote Sensing Imagery” Geo-spatial information science, 2022</p>
Channeling: a new class of dissolution in complex porous media
<p>ModelAandBGeometries.7z contains the original 12,000 x 12,000 pixel geometries created for Models A and B in Menke et al. 2022 PNAS. They were subsequently binned by 12 in each direction and padded by 2 on all sides to get the 1,004 x 1,004 pixel geometries input into GeoChemFoam. The original location and radius of each bead is supplied in the .hdf5 file as 'rad', 'x_coor', and y_coor'. </p> <p>ModelA_Pe##_K##.hdf5 and ModelB_Pe##_K##.hdf5 contain all of the simulation results for each flow and reaction scenario. This includes porosity, permeability, time_s, concentration, velocity, pores, grains, throats, and moments for all output timesteps. Pore2 & throat2 denote analyses with the fully dissolved section of the model excluded. </p> <p>The model (GeoChemFoam) used to run these dissolution scenarios can be downloaded with tutorials at https://github.com/GeoChemFoam/. The script used to make the micromodel geometries can be found at https://github.com/hannahmenke/PNAS2022.</p>
Edge length of land use classes aggregated from Corine 2012 in 100 - 5000 meter radius areas around Landklif study plots
<p>Based on CORINE land cover data 2012, we aggregated the original land use classes into 8 classes: urban, agriculture, grassland, broad-leaved forest, coniferous forest, mixed forest, natural/seminatural vegetation, and water (see clc_legend.txt). Based on this new land use classification, we calculated the edge length of landuse patches (total length of edges between different habitat in meter) for 100 - 5000 meters (100-1000 meters with 100 meter interval, 1000 - 5000 meter with 500 meter interval) buffer area around LandKlif plots.</p> <p>LandKlif is funded by the Bavarian State Ministry of Science and the Arts within the Bavarian Climate Research Network (bayklif). Within the five year funding period of bayklif, five interdisciplinary senior research associations and five junior research groups are be financed with a total sum of 18 million Euro. LandKliF, as one of the five interdisciplinary senior research associations, addresses the effects of climate change on biodiversity and ecosystem services in semi-natural, agricultural and urban landscapes.</p>
Edge length of land use classes aggregated from Corine 2018 in 100 - 5000 meter radius areas around Landklif study plots
<p><span>Based on CORINE land cover data 2018, we aggregated the original land use classes into 8 classes: urban, agriculture, grassland, broad-leaved forest, coniferous forest, mixed forest, natural/seminatural vegetation, and water (see clc_legend.txt). Based on this new land use classification, we calculated the edge length of landuse patches (total length of edges between different habitat in meter) for 100 - 5000 meters (100-1000 meters with 100 meter interval, 1000 - 5000 meter with 500 meter interval) buffer area around LandKlif plots</span>.</p> <p>LandKlif is funded by the Bavarian State Ministry of Science and the Arts within the Bavarian Climate Research Network (bayklif). Within the five year funding period of bayklif, five interdisciplinary senior research associations and five junior research groups are be financed with a total sum of 18 million Euro. LandKliF, as one of the five interdisciplinary senior research associations, addresses the effects of climate change on biodiversity and ecosystem services in semi-natural, agricultural and urban landscapes.</p>
Landscape composition and shannon diversity of landuse classes aggregated from corine 2018 in 100 - 5000 meter radius areas around Landklif study plots
<p><span>Based on CORINE land cover data from 2018, we aggregated the original land use classes into 8 classes: urban, agriculture, grassland, Broad-leaved forest, Coniferous forest, Mixed forest, natural/seminatural vegetation, and water (see clc_legend.txt). We calculated the landscape composition (percentage of each land use type according to corine land type) for 100 - 5000 meters (100-1000 meter with 100 meter intervals, 1000 - 5000 meter with 500 meter interval) buffer area around landklif plots</span>.</p> <p>LandKlif is funded by the Bavarian State Ministry of Science and the Arts within the Bavarian Climate Research Network (bayklif). Within the five year funding period of bayklif, five interdisciplinary senior research associations and five junior research groups are be financed with a total sum of 18 million Euro. LandKliF, as one of the five interdisciplinary senior research associations, addresses the effects of climate change on biodiversity and ecosystem services in semi-natural, agricultural and urban landscapes.</p>
Improving Hypernymy Extraction with Distributional Semantic Classes
<p>In this paper, we show for the first time how distributionally-induced semantic classes can be helpful for extraction of hypernyms. We present a method for (1) inducing sense-aware semantic classes using distributional semantics and (2) using these induced semantic classes for filtering noisy hypernymy relations. Denoising of hypernyms is performed by labeling each semantic class with its hypernyms. On one hand, this allows us to filter out wrong extractions using the global structure of the distributionally similar senses. On the other hand, we infer missing hypernyms via label propagation to cluster terms. We conduct a large-scale crowdsourcing study showing that processing of automatically extracted hypernyms using our approach improves the quality of the hypernymy extraction both in terms of precision and recall. Furthermore, we show the utility of our method in the domain taxonomy induction task, achieving the state-of-the-art results on a benchmarking dataset.</p> <p>This particular page contains datasets related to the paper. Namely the input induced word senses, a database of hypernyms, and the output clusters of senses labeled with hypernyms -- the distributional semantic classes. The semantic classes are of two granularities, as described in the paper (coarse and fine grained). </p>
Dataset: error characteristics of a class 0.2S current transformer for publication
<p>Data for demonstrating typical error characteristics of a current transformer of the class 0.2 S. Data are used in a publication.</p>
Supporting Jupyter Python notebook for "A new class of efficient randomized benchmarking protocols"
<p>Python notebook containing the code used to generate the data for figure 2 in the appendix of "A new class of efficient randomized benchmarking protocols" (arXiv:1806.02048).</p>
Datasets for Non-Parametric Class Completeness Estimators for Collaborative Knowledge Graphs
<p><strong>Non-Parametric Class Completeness Estimators for Collaborative Knowledge Graphs</strong></p> <p>This are intermediary datasets used for the calculation of the Class Completeness Estimators on Wikidata. For more information see: https://github.com/eXascaleInfolab/cardinal/</p> <p><strong>edits_wikidatawiki-20181001-pages.csv</strong></p> <p>This is an extract from <em>wikidatawiki-20181001-pages-meta-history</em> (All pages with complete page edit history (.bz2)) found at <a href="https://dumps.wikimedia.org/wikidatawiki/">https://dumps.wikimedia.org/wikidatawiki/</a>.</p> <p>The extract was created by the following SQL query:</p> <pre> SELECT page_title, rev_comment, rev_user_text, rev_timestamp FROM revisions WHERE rev_comment LIKE '%[[Property:%]]%[[Q%' ORDER BY rev_id INTO OUTFILE 'edits_wikidatawiki-20181001-pages.csv'; </pre> <p> </p> <p><strong>wikidata-20180813-all.json.bz2.universe.noattr.gt.bz2</strong></p> <p>This is a graph-tool representation of the WikiData graph. Output of <a href="https://github.com/eXascaleInfolab/cardinal/blob/master/1_create_inmemory_graph.py">https://github.com/eXascaleInfolab/cardinal/blob/master/1_create_inmemory_graph.py</a>.</p> <p><strong>observations_wikidatawiki-20181001-pages.pickle</strong></p> <p>Extracted observations. Output of <a href="https://github.com/eXascaleInfolab/cardinal/blob/master/2_extract_observations.py">https://github.com/eXascaleInfolab/cardinal/blob/master/2_extract_observations.py</a>.</p> <p> </p> <p><strong>estimates_wikidatawiki-20181001-pages.pickle</strong></p> <p>Extracted estimates. Output of <a href="https://github.com/eXascaleInfolab/cardinal/blob/master/3_calculate_estimates.py">https://github.com/eXascaleInfolab/cardinal/blob/master/3_calculate_estimates.py</a></p> <p> </p> <p><strong>results_wikidatawiki-20181001-pages.pickle </strong></p> <p>Results. Output of <a href="https://github.com/eXascaleInfolab/cardinal/blob/master/4_draw_graphs.py">https://github.com/eXascaleInfolab/cardinal/blob/master/4_draw_graphs.py</a></p>
Data set for "Cell class-specific long-range axonal projections of neurons in mouse whisker-related somatosensory cortices"
<p>Data set for: Liu Y, Bech P, Tamura K, Délez LT, Crochet S, Petersen CCH (2024) Cell class-specific long-range axonal projections of neurons in mouse whisker-related somatosensory cortices. eLife 13: RP97602. https://doi.org/10.7554/eLife.97602</p> <p>There are 3 files in this upload:</p> <p>1. The file named "2024_Liu_eLife.pdf" is the Open Access pdf of the online publication in eLife.</p> <p>2. The file named "Liu_anatomy_data_code.zip" (~35 GB) is a zipped version of a folder "Liu_anatomy_data_code" (~111 GB), which contains the anatomical data analysed in the study along with the Python codes used to generate the published figures 1-7 and their associated figure supplements. </p> <p>3. The file named "Liu_function_data_code.zip" (~10 GB) is a zipped version of a folder "Liu_function_data_code" (~35 GB), which contains the functional data analysed in the study along with the Python codes used to generate the published figure 8 and its associated figure supplement. </p> <p>After unzipping, the Python codes should run as a Jupyter notebook (anatomy .ipynb code) or Python code (function .py code) in Anaconda.</p>
3D Archaeological Greek Pottery: MDDS-2017-0299, Attic red-figure trefoil oinochoe, Class N, The Cook Class
<p><strong>This 3D dataset is related to the publication</strong>:</p> <ul> <li>Moitinho de Almeida, V. (2023). "<a href="https://www.researchgate.net/publication/353038967_Contributions_of_3D_digital_methods_and_techniques_to_the_study_of_ancient_pottery">Contributions of 3D digital methods and techniques to the study of ancient pottery</a>". In <em>Myths, Gods, and Heroes. Greek vase collections in Portugal / Mitos, Deuses e Heróis. As coleções de vasos gregos em Portugal</em>. R. Morais, R. Centeno, D. Ferreira (eds.). Câmara Municipal de Santa Maria da Feira - Museu Convento dos Lóios; Reitoria da Universidade do Porto; Faculdade de Letras da Universidade do Porto; Imprensa da Universidade de Coimbra. Pp.269-291. (ISBN: 978-989-8183-25-5)</li> </ul> <p>3D processed dataset for object 2017-0299, from the Museu de Arqueologia D. Diogo de Sousa (MDDS) in Braga, Portugal. <strong>CC BY-NC-SA 4.0 license</strong>.</p> <p>2017-0299 is an Attic red-figure trefoil <em>oinochoe</em>, Class N, The Cook Class, dating from c. 500-475 BCE and unknown provenance (Fundação Buehler Brockhaus / Museu D. Diogo de Sousa, 2020; Morais et al., 2021).</p> <p><strong>Aims</strong>: 3D digital documentation; morphological characterization; technological and functional analysis of archaeological Greek pottery.</p> <p><strong>Data acquisition</strong>: at the Museu de História Natural e da Ciência da Universidade do Porto (MHNC-UP), with a portable non-contact structured white light scanner, Breukmann smartSCAN3D-HE, equipped with stereo colour cameras at 250 mm FOV. Additional metadata included in associated spreadsheet.<br><strong>Data processing</strong>: 29 scans aligned and merged. MDDS-2017-0299_3D01.ply: non-manifold edges, self-intersections, small components, and small tunnels in the mesh automatically fixed, noise data removed; orientation and position normalised. MDDS-2017-0299_3D01-holesFilled.ply: holes filled for calculation of material density, filling volume, and centre of mass. Mesh is not watertight (inner surface not digitised due to occlusion). Additional metadata included in associated spreadsheet.</p> <p>Access to the 2017-0299 was granted by the MDDS.</p> <p>When citing this material: please include the original inventory ID (2017-0299) reference to the physical object.</p>
A Synthetic Hyperspectral Dataset for Development and Validation of Phytoplankton Size Class Retrieval Models
<p><strong>A Synthetic Hyperspectral Dataset for Development and Validation of Phytoplankton Size Class Retrieval Models.</strong></p> <p>Please refer to the following scientific paper for a description of the dataset.</p> <blockquote> <p>Holtrop, T.; Van Der Woerd, H.J. (accepted) HYDROPT: An Open-Source Framework for Fast Inverse Modelling of Multi- and Hyperspectral Observations from Oceans, Coastal and Inland Waters. <em>Remote Sens. </em><strong>2021</strong>, 13, 0.</p> </blockquote>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band NDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on 1-band NDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.5281/zenodo.7344571</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p>File descriptions</p> <p>For each model, there are 5 files with the same root name:</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><br> References</p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p> <p>** Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7344571</p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 5-band (RGB+NIR+SWIR) images of coasts.
<p>These Residual-UNet model data are based on 5-band RGB+NIR+SWIR (red, green, blue, near-infrared, and short-wave infrared) images of coasts and associated labels.</p> <p> </p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7344571">https://doi.org/10.5281/zenodo.7344571 </a></p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7344571">https://doi.org/10.5281/zenodo.7344571</a></p>
Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)
<p><em><strong>Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other)</strong></em></p> <p><strong>Description</strong></p> <p>579 images and 579 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Some (422) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 4 classes.</p> <p>The label images are a subset of the following data release**** <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p>Imagery comes from the following 10 sand beach sites:</p> <ol> <li>Duck, NC, Hatteras NC, USA</li> <li>Santa Cruz CA, USA</li> <li>Galveston TX, USA</li> <li>Truc Vert,France</li> <li>Sunset State Beach CA, USA</li> <li>Torrey Pines CA, USA</li> <li>Narrabeen, NSW, Australia</li> <li>Elwha WA, USA</li> <li>Ventura region, CA, USA</li> <li>Klamath region, CA USA</li> </ol> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, Blue, NIR, and SWIR bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band RGB images of varying sizes and extents</li> <li>nir.zip, a zipped folder containing the corresponding near-infrared (NIR) imagery</li> <li>swir.zip, a zipped folder containing the corresponding shortwave-infrared (SWIR) imagery</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li>resized_nir.zip, NIR images resized to 512x512x3 pixels</li> <li>resized_swir.zip, SWIR images resized to 512x512x3 pixels</li> <li>resized_labels.zip, label images resized to 512x512 pixels</li> </ol> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></p> <p>**Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>***Coast Train data release: Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, <a href="https://doi.org/10.5066/P91NP87I">https://doi.org/10.5066/P91NP87I</a>. See <a href="https://coasttrain.github.io/CoastTrain/">https://coasttrain.github.io/CoastTrain/ </a>for more information</p> <p>**** Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p>
Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other)
<p><strong>Description</strong></p> <p>1018 images and 1018 associated labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts. The 4 classes are 0=water, 1=whitewater, 2=sediment, 3=other</p> <p>These images and labels have been made using the Doodleverse software package, Doodler*. These images and labels could be used within numerous Machine Learning frameworks for image segmentation, but have specifically been made for use with the Doodleverse software package, Segmentation Gym**.</p> <p>Some (473) of these images and labels were originally included in the Coast Train*** data release, and have been modified from their original by reclassifying from the original classes to the present 4 classes.</p> <p>Imagery comes from the following 10 sand beach sites:</p> <ol> <li>Duck, NC, Hatteras NC, USA</li> <li>Santa Cruz CA, USA</li> <li>Galveston TX, USA</li> <li>Truc Vert,France</li> <li>Sunset State Beach CA, USA</li> <li>Torrey Pines CA, USA</li> <li>Narrabeen, NSW, Australia</li> <li>Elwha WA, USA</li> <li>Ventura region, CA, USA</li> <li>Klamath region, CA USA</li> </ol> <p>Imagery are a mixture of 10-m Sentinel-2 and 15-m pansharpened Landsat 7, 8, and 9 visible-band imagery of various sizes. Red, Green, and Blue bands only</p> <p><strong>File descriptions</strong></p> <ol> <li>classes.txt, a file containing the class names</li> <li>images.zip, a zipped folder containing the 3-band images of varying sizes and extents</li> <li>labels.zip, a zipped folder containing the 1-band label images</li> <li>overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (blue=0=water, red=1=whitewater, yellow=2=sediment, green=3=other)</li> <li>resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li>resized_labels.zip, label images resized to 512x512 pixels</li> </ol> <p><strong>References</strong></p> <p>*Doodler: Buscombe, D., Goldstein, E.B., Sherwood, C.R., Bodine, C., Brown, J.A., Favela, J., Fitzpatrick, S., Kranenburg, C.J., Over, J.R., Ritchie, A.C. and Warrick, J.A., 2021. Human‐in‐the‐Loop Segmentation of Earth Surface Imagery. Earth and Space Science, p.e2021EA002085<a href="https://doi.org/10.1029/2021EA002085">https://doi.org/10.1029/2021EA002085</a>. See <a href="https://github.com/Doodleverse/dash_doodler">https://github.com/Doodleverse/dash_doodler.</a></p> <p>**Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>***Coast Train data release: Wernette, P.A., Buscombe, D.D., Favela, J., Fitzpatrick, S., and Goldstein E., 2022, Coast Train--Labeled imagery for training and evaluation of data-driven models for image segmentation: U.S. Geological Survey data release, <a href="https://doi.org/10.5066/P91NP87I">https://doi.org/10.5066/P91NP87I</a>. See <a href="https://coasttrain.github.io/CoastTrain/">https://coasttrain.github.io/CoastTrain/ </a>for more information</p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 3-band (RGB) images of coasts.</strong></em></p> <p> </p> <p>These Residual-UNet model data are based on RGB (red, green, and blue) images of coasts and associated labels.</p> <p> </p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p><strong>File descriptions</strong></p> <p>For each model, there are 5 files with the same root name:</p> <p>1. <strong>'.json' </strong>config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2.<strong> '.h5'</strong> weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3.<strong> '_modelcard.json'</strong> model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. <strong> '_model_history.npz'</strong> model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. <strong> '.png'</strong> model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p> </p> <p><strong>References</strong></p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. <a href="https://doi.org/10.1029/2022EA002332">https://doi.org/10.1029/2022EA002332</a> See: <a href="https://github.com/Doodleverse/segmentation_gym">https://github.com/Doodleverse/segmentation_gym</a></p> <p>** Buscombe, Daniel, Goldstein, Evan, Bernier, Julie, Bosse, Stephen, Colacicco, Rosa, Corak, Nick, Fitzpatrick, Sharon, del Jesús González Guillén, Anais, Ku, Venus, Paprocki, Julie, Platt, Lindsay, Steele, Bethel, Wright, Kyle, & Yasin, Brandon. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7335647">https://doi.org/10.5281/zenodo.7335647</a></p> <p> </p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 1-band MNDWI images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on 1-band MNDWI images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: https://doi.org/10.5281/zenodo.7344571</p> <p>Classes: {0=water, 1=whitewater, 2=sediment, 3=other}</p> <p>File descriptions</p> <p>For each model, there are 5 files with the same root name:</p> <p>1. '.json' config file: this is the file that was used by Segmentation Gym* to create the weights file. It contains instructions for how to make the model and the data it used, as well as instructions for how to use the model for prediction. It is a handy wee thing and mastering it means mastering the entire Doodleverse.</p> <p>2. '.h5' weights file: this is the file that was created by the Segmentation Gym* function `train_model.py`. It contains the trained model's parameter weights. It can called by the Segmentation Gym* function `seg_images_in_folder.py`. Models may be ensembled.</p> <p>3. '_modelcard.json' model card file: this is a json file containing fields that collectively describe the model origins, training choices, and dataset that the model is based upon. There is some redundancy between this file and the `config` file (described above) that contains the instructions for the model training and implementation. The model card file is not used by the program but is important metadata so it is important to keep with the other files that collectively make the model and is such is considered part of the model</p> <p>4. '_model_history.npz' model training history file: this numpy archive file contains numpy arrays describing the training and validation losses and metrics. It is created by the Segmentation Gym function `train_model.py`</p> <p>5. '.png' model training loss and mean IoU plot: this png file contains plots of training and validation losses and mean IoU scores during model training. A subset of data inside the .npz file. It is created by the Segmentation Gym function `train_model.py`</p> <p>Additionally, BEST_MODEL.txt contains the name of the model with the best validation loss and mean IoU</p> <p><br> References</p> <p>*Segmentation Gym: Buscombe, D., & Goldstein, E. B. (2022). A reproducible and reusable pipeline for segmentation of geoscientific imagery. Earth and Space Science, 9, e2022EA002332. https://doi.org/10.1029/2022EA002332 See: https://github.com/Doodleverse/segmentation_gym</p> <p>** Buscombe, Daniel. (2022). Images and 4-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, whitewater, sediment, other) (v1.0) [Data set]. Zenodo. https://doi.org/10.5281/zenodo.7344571</p> <p> </p>
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.