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.
181
datasets available to search
ShareScore release 0.7.1
Dataset results
181 results for “SENTINEL-2”
Agricultural land use (raster) : National-scale crop type maps for Germany from combined time series of Sentinel-1, Sentinel-2 and Landsat data (2017 to 2021)
<p>The dataset contains maps of the main classes of agricultural land use (dominant crop types and other land use types) in Germany, which are produced annually at the Thünen Institute beginning with the year 2017 on the basis of satellite data. The maps cover the entire open landscape, i.e., the agriculturally used area (UAA) and e.g., uncultivated areas. The map was derived from time series of Sentinel-1, Sentinel-2, Landsat 8 and additional environmental data. Map production is based on the methods described in <a href="https://doi.org/10.1016/j.rse.2021.112831">Blickensdörfer et al. (2022)</a>.</p> <p>All optical satellite data were managed, pre-processed and structured in an analysis-ready data (ARD) cube using the open-source software <a href="https://force-eo.readthedocs.io/en/latest/">FORCE </a>- Framework for Operational Radiometric Correction for Environmental monitoring (Frantz, D., 2019), in which SAR and environmental data were integrated.</p> <p>The map extent covers all areas in Germany that are defined in the respective year as cropland, grassland, small woody features, heathland, peatland or unvegetated areas according to ATKIS Basis-DLM (Geobasisdaten: © GeoBasis-DE / BKG, 2020). </p> <p>Version v201:<br>Post-processing of the maps included a sieve filter as well as a ruleset for the reduction of non-plausible areas using the Basis-DLM and the digital terrain model of Germany (Geobasisdaten: © GeoBasis-DE / BKG, 2015).</p> <p>Version v202:<br>Additional post-processing was performed to detect and mask additional non-plausible areas that were not adequately covered by the first post-processing (e.g., areas with sparse vegetation, montane forests) based on the „Ökosystematlas Deutschland“ (© Statistisches Bundesamt, Deutschland, 2024). As a consequence, the current version includes a new class “Small woody features on other land”. Furthermore, the class "permanent grassland" was refined. Each pixel that was classified as "cultivated grassland" in at least five years (between 2017 and 2022) was translated to "permanent grassland" in the annual maps.</p> <p>The maps are available as cloud optimized GeoTiffs, which makes downloading the full dataset optional. All data can directly be accessed in QGIS, R, Python or any supported software of your choice using the provided URL to the datasets (right click on the respective data set --> “copy link address”). By doing so the entire map area or only the regions of interest can be accessed. QGIS legend files for data visualization can be downloaded separately.</p> <p>Class-specific accuracies for each year are provided in the respective tables. We provide this dataset "as is" without any warranty regarding the accuracy or completeness and exclude all liability. </p> <p> </p> <p><strong>References:<br></strong><br><em>Blickensdörfer, L., Schwieder, M., Pflugmacher, D., Nendel, C., Erasmi, S., & Hostert, P. (2022). Mapping of crop types and crop sequences with combined time series of Sentinel-1, Sentinel-2 and Landsat 8 data for Germany. Remote Sensing of Environment, 269, 112831.</em></p> <p><em>BKG, Bundesamt für Kartographie und Geodäsie (2015). Digitales Geländemodell Gitterweite 10 m. DGM10. https://sg.geodatenzentrum.de/web_public/gdz/dokumentation/deu/dgm10.pdf (last accessed: 28. April 2022).</em></p> <p><em>BKG, Bundesamt für Kartographie und Geodäsie (2020). Digitales Basis-Landschaftsmodell. </em><br><em>https://sg.geodatenzentrum.de/web_public/gdz/dokumentation/deu/basis-dlm.pdf (last accessed: 28. April 2022).</em></p> <p><em>Frantz, D. (2019). FORCE—Landsat + Sentinel-2 Analysis Ready Data and Beyond. Remote Sensing, 11, 1124.</em></p> <p><em>Statistisches Bundesamt, Deutschland (2024). Ökosystematlas Deutschland <br>https://oekosystematlas-ugr.destatis.de/ (last accessed: 08.02.2024).</em></p> <p>___________________________________________________________________________<br>National-scale crop type maps for Germany from combined time series of Sentinel-1, Sentinel-2 and Landsat data (2017 to 2021) © 2024 by Schwieder, Marcel; Tetteh, Gideon Okpoti; Blickensdörfer, Lukas; Gocht, Alexander; Erasmi, Stefan; licensed under CC BY 4.0. </p> <p>Funding was provided by the German Federal Ministry of Food and Agriculture as part of the joint project “Monitoring der biologischen Vielfalt in Agrarlandschaften” (<a href="https://www.agrarmonitoring-monvia.de/en/">MonViA</a>, Monitoring of biodiversity in agricultural landscapes).</p> <p>The study was financially supported by the European Environment Agency and the European Union’s Horizon Europe Research and Innovation programme under Grant Agreement No 101060423 (LAMASUS).</p>
The Results of Amery Ice Shelf Supraglacial Lake Dection and Surveying Using ICESat-2 and Sentinel-2
<p>This is the first release of the results and verification used for the submitted paper:</p> <p><strong>Zhang et al., 2024: </strong>Automatically Detection and Surveying Supraglacial Lakes Using Machine Learning from ICESat-2 and Sentinel-2 Data</p>
Yield data from field measurements and satellite imagery from Sentinel-2 for three consecutive years
<p>Data From: Kayad A, Sozzi M, Gatto S, Marinello F, Pirotti F. Monitoring Within-Field Variability of Corn Yield using Sentinel-2 and Machine Learning Techniques. <em>Remote Sensing</em>. 2019; 11(23):2873. https://doi.org/10.3390/rs11232873</p> <ul> <li>Yield values as point data</li> <li>Interpolated kriging yield data</li> <li>Satellite imagery</li> </ul>
SEN2VENµS, a dataset for the training of Sentinel-2 super-resolution algorithms
<p><strong>1 Description</strong></p> <p><strong>SEN2VENµS</strong> is an open dataset for the super-resolution of Sentinel-2 images by leveraging simultaneous acquisitions with the VENµS satellite. The dataset is composed of 10m and 20m cloud-free surface reflectance patches from Sentinel-2, with their reference spatially-registered surface reflectance patches at 5 meters resolution acquired on the same day by the VENµS satellite. This dataset covers 29 locations with a total of 132 955 patches of 256x256 pixels at 5 meters resolution, and can be used for the training of super-resolution algorithms to bring spatial resolution of 8 of the Sentinel-2 bands down to 5 meters.</p> <p><strong>Changelog with respect to version 1.0.0</strong> (https://zenodo.org/records/6514159)</p> <ul> <li>All patches are now stored in indivual geoTiFF files with proper geo-referencing, regrouped in zip files per site and per category,</li> <li>The dataset now includes 20 meter resolution SWIR bands B11 and B12 from Sentinel-2 (L2A from Theia). Note that there is no HR reference for those bands, since the VENµS sensor has no SWIR band.</li> </ul> <p><strong>2 Files organization</strong></p> <p>The dataset is composed of separate sub-datasets embedded in separate zip files, one for each site, as described in table <a href="#org5e17b56">1</a>. Note that there might be slight variations in number of patches and number of pairs with respect to version 1.0.0, due do incorrect count of samples in previous version (an empty tensor was still accounted for).</p> <p>Table 1: Number of patches and pairs for each site, along with VENµS viewing zenith angle</p> <table> <tbody> <tr> <th>Site</th> <th>Number of patches</th> <th>Number of pairs</th> <th>VENµS Zenith Angle</th> </tr> </tbody> <tbody> <tr> <td>FR-LQ1</td> <td>4888</td> <td>18</td> <td>1.795402</td> </tr> <tr> <td>NARYN</td> <td>3813</td> <td>24</td> <td>5.010906</td> </tr> <tr> <td>FGMANAUS</td> <td>129</td> <td>4</td> <td>7.232127</td> </tr> <tr> <td>MAD-AMBO</td> <td>1442</td> <td>18</td> <td>14.788115</td> </tr> <tr> <td>ARM</td> <td>15859</td> <td>39</td> <td>15.160683</td> </tr> <tr> <td>BAMBENW2</td> <td>9018</td> <td>34</td> <td>17.766533</td> </tr> <tr> <td>ES-IC3XG</td> <td>8822</td> <td>34</td> <td>18.807686</td> </tr> <tr> <td>ANJI</td> <td>2312</td> <td>14</td> <td>19.310494</td> </tr> <tr> <td>ATTO</td> <td>2258</td> <td>9</td> <td>22.048651</td> </tr> <tr> <td>ESGISB-3</td> <td>6057</td> <td>19</td> <td>23.683871</td> </tr> <tr> <td>ESGISB-1</td> <td>2891</td> <td>12</td> <td>24.561609</td> </tr> <tr> <td>FR-BIL</td> <td>7105</td> <td>30</td> <td>24.802892</td> </tr> <tr> <td>K34-AMAZ</td> <td>1384</td> <td>20</td> <td>24.982675</td> </tr> <tr> <td>ESGISB-2</td> <td>3067</td> <td>13</td> <td>26.209776</td> </tr> <tr> <td>ALSACE</td> <td>2653</td> <td>16</td> <td>26.877071</td> </tr> <tr> <td>LERIDA-1</td> <td>2281</td> <td>5</td> <td>28.524780</td> </tr> <tr> <td>ESTUAMAR</td> <td>911</td> <td>12</td> <td>28.871947</td> </tr> <tr> <td>SUDOUE-5</td> <td>2176</td> <td>20</td> <td>29.170244</td> </tr> <tr> <td>KUDALIAR</td> <td>7269</td> <td>20</td> <td>29.180855</td> </tr> <tr> <td>SUDOUE-6</td> <td>2435</td> <td>14</td> <td>29.192055</td> </tr> <tr> <td>SUDOUE-4</td> <td>935</td> <td>7</td> <td>29.516127</td> </tr> <tr> <td>SUDOUE-3</td> <td>5363</td> <td>14</td> <td>29.998115</td> </tr> <tr> <td>SO1</td> <td>12018</td> <td>36</td> <td>30.255978</td> </tr> <tr> <td>SUDOUE-2</td> <td>9700</td> <td>27</td> <td>31.295256</td> </tr> <tr> <td>ES-LTERA</td> <td>1701</td> <td>19</td> <td>31.971764</td> </tr> <tr> <td>FR-LAM</td> <td>7299</td> <td>22</td> <td>32.054056</td> </tr> <tr> <td>SO2</td> <td>738</td> <td>22</td> <td>32.218481</td> </tr> <tr> <td>BENGA</td> <td>5857</td> <td>28</td> <td>32.587334</td> </tr> <tr> <td>JAM2018</td> <td>2564</td> <td>18</td> <td>33.718953</td> </tr> </tbody> </table> <p> </p> <p>Each site zip file contains a subfolder with the site name. This subfolder contains secondary zip files for each date, following this naming convention as the pair <code>id</code>: <code>{site_name}_{acquisition_date}_{mgrs_tile}</code>. For each date, 5 zip files are available, as shown in table <a href="#org504e2aa">2</a>.Each zip file contain subfolder <code>{bands}/{resolution}/</code> in which one GeoTiFF file per patch is stored, with the following naming convention: <code>{site_name}_{idx}_{acquisition_date}_{mgr_tile}_{bands}_{resolution}.tif</code>. Pixel values are encoded as 16 bits signed integers and should be converted back to floating point surface reflectance by dividing each and every value by 10 000 upon reading.</p> <p>Table 2: Naming convention for zip files associated to each date.</p> <table> <tbody> <tr> <th>File</th> <th>Content</th> </tr> </tbody> <tbody> <tr> <td><code>{id}_05m_b2b3b4b8.zip</code></td> <td>5m patches (\(256\times256\) pix.) for S2 B2, B3, B4 and B8 (from VENµS)</td> </tr> <tr> <td><code>{id}_10m_b2b3b4b8.zip</code></td> <td>10m patches (\(128\times128\) pix.) for S2 B2, B3, B4 and B8 (from Sentinel-2)</td> </tr> <tr> <td><code>{id}_05m_b5b6b7b8a.zip</code></td> <td>5m patches (\(256\times256\) pix.) for S2 B5, B6, B7 and B8A (from VENµS)</td> </tr> <tr> <td><code>{id}_20m_b5b6b7b8a.zip</code></td> <td>20m patches (\(64\times64\) pix.) for S2 B5, B6, B7 and B8A (from Sentinel-2)</td> </tr> <tr> <td><code>{id}_20m_b11b12.zip</code></td> <td>20m patches (\(64\times64\) pix.) for S2 B11 and B12 (from Sentinel-2)</td> </tr> </tbody> </table> <p> </p> <p>Each file comes with a master <code>index.csv</code> CSV (Comma Separated Values) file, with one row for each pair sampled in the given site. Columns are named after the <code>{bands}_{resolution}</code> pattern, and contains the full path to the corresponding GeoTiFF wihin the corresponding zip file:</p> <p><code>{site}_{acquisition_date}_{mgrs_tile}_{bands}_{resolution}.zip/{bands}/{resolution}/{site}_{idx}_{acquisition_date}_{mgrs_tile}_{bands}_{resolution}.tif</code></p> <p><strong>3 Licencing</strong></p> <p><strong>3.1 Sentinel-2 patches</strong></p> <p><strong>3.1.1 Copyright</strong></p> <p>Value-added data processed by CNES for the Theia data centre www.theia-land.fr using Copernicus products. The processing uses algorithms developed by Theia's Scientific Expertise Centres. Note: Copernicus Sentinel-2 Level 1C data is subject to this license: <a href="https://theia.cnes.fr/atdistrib/documents/TC_Sentinel_Data_31072014.pdf">https://theia.cnes.fr/atdistrib/documents/TC_Sentinel_Data_31072014.pdf</a></p> <p><strong>3.1.2 Licence</strong></p> <p>Files <code>*_b2b3b4b8_10m.tif</code>, <code>*_b5b6b7b8a_20m.tif</code> and <code>*_b11b12_20m.tif</code> are distributed under the the original licence of the Sentinel-2 Theia L2A products, which is the Etalab Open Licence Version 2.0 <sup><a href="#fn.2">2</a></sup>.</p> <p><strong>3.2 VENµS patches</strong></p> <p><strong>3.2.1 Copyright</strong></p> <p>Value-added data processed by CNES for the Theia data centre www.theia-land.fr using VENµS satellite imagery from CNES and Israeli Space Agency. The processing uses algorithms developed by Theia's Scientific Expertise Centres.</p> <p>3.2.2 <strong>Licence</strong></p> <p>Files <code>*_b2b3b4b8_05m.tif</code> and <code>*_b5b6b7b8a_05m.tif</code> are distributed under the original licence of the VENµS products, which is Creative Commons BY-NC 4.0 <sup><a href="#fn.3">3</a></sup>.</p> <p><strong>3.3 Remaining files</strong></p> <p>All remaining files are distributed under the Creative Commons BY 4.0 <sup><a href="#fn.4">4</a></sup> licence.</p> <p><strong>4 Note to users</strong></p> <p>Note that even if the VenµS2 dataset is sorted by sites and by pairs, we strongly encourage users to apply the full set of machine learning best practices when using it : random keeping separate pairs (or even sites) for testing purpose, and randomization of patches accross sites and pairs in the training and validation sets.</p> <p><strong>5 Citing</strong></p> <p>Please cite the following data paper (preprint, submitted to <em>MDPI Data</em>) and zenodo link when publishing work derived from this dataset:</p> <p>Michel, J.; Vinasco-Salinas, J.; Inglada, J.; Hagolle, O. SEN2VENµS, a Dataset for the Training of Sentinel-2 Super-Resolution Algorithms. <em>Data</em> <strong>2022</strong>, <em>7</em>, 96. https://doi.org/10.3390/data7070096</p> <p><a href="https://zenodo.org/deposit/6514159">10.5281/zenodo.14603764</a></p> <p><strong>Footnotes:</strong></p> <p><sup><a href="#fnr.1">1</a></sup></p> <p><a href="https://pytorch.org/">https://pytorch.org/</a></p> <p><sup><a href="#fnr.2">2</a></sup></p> <p><a href="https://theia.cnes.fr/atdistrib/documents/Licence-Theia-CNES-Sentinel-ETALAB-v2.0-en.pdf">https://theia.cnes.fr/atdistrib/documents/Licence-Theia-CNES-Sentinel-ETALAB-v2.0-en.pdf</a></p> <p><sup><a href="#fnr.3">3</a></sup></p> <p><a href="https://creativecommons.org/licenses/by-nc/4.0/">https://creativecommons.org/licenses/by-nc/4.0/</a></p> <p><sup><a href="#fnr.4">4</a></sup></p> <p><a href="https://creativecommons.org/licenses/by/4.0/">https://creativecommons.org/licenses/by/4.0/</a></p>
Sentinel-2 Sample Data
<p>This repository contains 5 Sentinel-2 Level-2A (12 bands) images that are part of the BigEarthNet Dataset (Sumbul et al. 2019, https://bigearth.net/). The images in this dataset focus on coastal areas.</p> <p>The image data for each scene and band were upscaled to a common ground sample distance of 10m per pixel using linear interpolation. Furthermore, all bands of each scence were combined into a single NumPy array and stored into separate .npy binary files. Data processing was performed by Linus Scheibenreif, University of St. Gallen.</p> <p>The data can be easily read in with Python using the following code snippet:</p> <p><code>import os</code><br><code>import numpy as np</code></p> <p><code>data = []</code><br><code>for filename in os.listdir('data/'):</code><br><code> if filename.endswith('.npy'):</code><br><code> data.append(np.load(open(os.path.join('data', filename), 'rb'),</code><br><code> allow_pickle=True))</code><br><code>data = np.array(data)</code></p> <p>This repository also contains the file coastal_labels.json, which contains polygons for labels grassland, forest, water and sand, using the YOLO format.</p> <p>This dataset is provided mainly for teaching purposes under the Creative Commons Attribution 4.0 International licence. BigEarthNet data are provided under the Community Data License Agreement (Permissive, Version 1.0).</p> <p>Michael Mommert, Stuttgart University of Applied Sciences, 2025-03-07</p>
Global Landside Clustering of Aquaculture Ponds Distribution Acquired from Dense Time-Series Sentinel-2 Images by Google Earth Engine
<p>This dataset reveals the global distribution pattern of landside clustering aquaculture ponds (LCAP) from a spatial perspective for the first time. It was derived from 4,015,054 tiles of the 10-m Sentinel-2 time-series images collected throughout 2020. The total area of global LCAP was estimated at 55,337.03 km2. Accuracy verification revealed that the Omission Error and Commission Error of the data is 7.51% and 16.69% respectively. We provide this dataset in <em>ESRI</em> <em>shapefile </em>format (.zip), which can be opened by <em>ArcGIS. </em>We invite you to download and utilize this dataset and recommend citing the following two references.</p>
SD4EO - Physically Based Rendering images of crop fields (Sentinel-2 B2B3B4B8B11 & Sentinel-1 SAR)
<p>This dataset contains part of the results of the SD4EO project, including images corresponding to the use case of crop fields identification. The dataset contains images that have been simulated corresponding to different sensors of the Sentinel 1 and Sentinel 2 satellites and regarding 9 different types of crops. Each image in the dataset includes pixel-level labels for each element present in the image, ensuring perfect accuracy due to the synthetic nature of the images. This eliminates common errors in manual or semi-automatic labeling processes.</p> <p><strong>Multispectral images included</strong></p> <p>Sentinel 1: SAR (Synthetic Aperture Radar) images.<br>Sentinel 2: Images from bands 2, 3, 4, 8, and 11.</p> <p><strong>Image labeling</strong></p> <div> <table> <tbody> <tr> <td> <p><strong>Crop</strong></p> </td> <td> <p><strong>R</strong></p> </td> <td> <p><strong>G</strong></p> </td> <td> <p><strong>B</strong></p> </td> </tr> <tr> <td> <p>Alfalfa or lucerne</p> </td> <td> <p>47</p> </td> <td> <p>255</p> </td> <td> <p>0</p> </td> </tr> <tr> <td> <p>Barley</p> </td> <td> <p>35</p> </td> <td> <p>192</p> </td> <td> <p>0</p> </td> </tr> <tr> <td> <p>Fallow and bare soil</p> </td> <td> <p>25</p> </td> <td> <p>135</p> </td> <td> <p>0</p> </td> </tr> <tr> <td> <p>Oats</p> </td> <td> <p>118</p> </td> <td> <p>178</p> </td> <td> <p>105</p> </td> </tr> <tr> <td> <p>Other grain leguminous</p> </td> <td> <p>38</p> </td> <td> <p>79</p> </td> <td> <p>29</p> </td> </tr> <tr> <td> <p>Peas</p> </td> <td> <p>44</p> </td> <td> <p>217</p> </td> <td> <p>70</p> </td> </tr> <tr> <td> <p>Sunflower</p> </td> <td> <p>78</p> </td> <td> <p>123</p> </td> <td> <p>68</p> </td> </tr> <tr> <td> <p>Vetch</p> </td> <td> <p>33</p> </td> <td> <p>58</p> </td> <td> <p>28</p> </td> </tr> <tr> <td> <p>Wheat</p> </td> <td> <p>130</p> </td> <td> <p>255</p> </td> <td> <p>102</p> </td> </tr> </tbody> </table> </div> <p><br><strong>Image name convention</strong></p> <p>The name convention follows the next schema of fields, separated by the character “_”</p> <p>- ID number</p> <p>- Meters per pixel resolution</p> <p>- Month</p> <p>- Type of image (Sentinel 2 band, Sentinel 1 SAR or labels): B2B3B4, B8, B11, SAR, labels</p> <p><strong>Image formats</strong></p> <p>TIFF format is used to save each band with floating point precision in the original range of the satellite images.</p> <p>PNG format is used to display each band in normalized values [0..1].</p> <table> <tbody> <tr> <td> <p><strong>Type of data</strong></p> </td> <td> <p><strong>PNG range</strong></p> </td> <td> <p><strong>TIFF range</strong></p> </td> </tr> <tr> <td> <p>B2</p> </td> <td> <p>0 - 255</p> </td> <td> <p>0 - 2000</p> </td> </tr> <tr> <td> <p>B3</p> </td> <td> <p>0 - 255</p> </td> <td> <p>0 - 2500</p> </td> </tr> <tr> <td> <p>B4</p> </td> <td> <p>0 - 255</p> </td> <td> <p>0 - 3000</p> </td> </tr> <tr> <td> <p>B8</p> </td> <td> <p>0 - 255</p> </td> <td> <p>1180 - 5736</p> </td> </tr> <tr> <td> <p>B11</p> </td> <td> <p>0 - 255</p> </td> <td> <p>859 - 5648</p> </td> </tr> <tr> <td> <p>SAR</p> </td> <td> <p>0 - 255</p> </td> <td> <p>-31.45273 - -14.23931</p> </td> </tr> </tbody> </table> <p><strong>Creation and funding</strong></p> <p>All the images have been generated using a tool developed in Unity. This tool will be soon available to enable the generation of new datasets.</p> <p>This research work has been funded by the European Space Agency (ESA) under the FutureEO program and the SD4EO project (Contract No.: 4000142334/23/I-DT), supervised by the ESA Φ-lab.</p> <p><strong>License and attribution</strong></p> <p>This dataset is licensed under a <a href="https://creativecommons.org/licenses/by/4.0/">Creative Commons Attribution 4.0 International License</a> (CC BY 4.0).</p> <p>When using the images from this dataset, please attribute them as follows: "Synthetic images created by the research group ARTEC - IRTIC - University of Valencia".</p>
The photovoltaic inventory dataset in Japan detected in Sentinel-2 imagery
Open the record for dataset details and reuse information.
Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other)
<p><em><strong>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other)</strong></em></p> <p>Images and 2-class labels for semantic segmentation of Sentinel-2 and Landsat 5-band (R+G+B+NIR+SWIR) satellite images of coasts (water, other)</p> <p><strong>Description</strong></p> <p>3649 images and 3649 associated labels for semantic segmentation of Sentinel-2 and Landsat 5-band (R+G+B+NIR+SWIR) satellite images of coasts. The 2 classes are 1=water, 0=other. 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, near-infrared, and short-wave infrared bands only</p> <p>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>Two data sources have been combined</p> <p><strong>Dataset 1</strong></p> <p>* 579 image-label pairs from the following data release**** https://doi.org/10.5281/zenodo.7344571<br> * Labels have been reclassified from 4 classes to 2 classes.<br> * 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 2 classes.<br> * These images and labels have been made using the Doodleverse software package, Doodler*.</p> <p><strong>Dataset 2</strong></p> <ul> <li>3070 image-label pairs from the Sentinel-2 Water Edges Dataset (SWED)***** dataset, https://openmldata.ukho.gov.uk/, described by Seale et al. (2022)******</li> <li>A subset of the original SWED imagery (256 x 256 x 12) and labels (256 x 256 x 1) have been chosen, based on the criteria of more than 2.5% of the pixels represent water</li> </ul> <p><strong>File descriptions</strong></p> <ul> <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> labels.zip, a zipped folder containing the 1-band label images</li> <li> nir.zip, a zipped folder containing the 1-band near-infrared (NIR) images</li> <li> swir.zip, a zipped folder containing the 1-band shorttwave infrared (SWIR) images</li> <li> overlays.zip, a zipped folder containing a semi-transparent overlay of the color-coded label on the image (red=1=water, blue=0=other)</li> <li> resized_images.zip, RGB images resized to 512x512x3 pixels</li> <li> resized_labels.zip, label images resized to 512x512x1 pixels</li> <li> resized_nir.zip, NIR images resized to 512x512x1 pixels</li> <li> resized_swir.zip, SWIR images resized to 512x512x1 pixels</li> </ul> <p>References</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.e2021EA002085https://doi.org/10.1029/2021EA002085. See https://github.com/Doodleverse/dash_doodler.</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>***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, https://doi.org/10.5066/P91NP87I. See https://coasttrain.github.io/CoastTrain/ for more information</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>*****Seale, C., Redfern, T., Chatfield, P. 2022. Sentinel-2 Water Edges Dataset (SWED) https://openmldata.ukho.gov.uk/</p> <p>******Seale, C., Redfern, T., Chatfield, P., Luo, C. and Dempsey, K., 2022. Coastline detection in satellite imagery: A deep learning approach on new benchmark data. Remote Sensing of Environment, 278, p.113044.</p>
Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 5-band (RGB+NIR+SWIR) images of coasts.
<p><em><strong>Doodleverse/Segmentation Zoo Res-UNet models for 2-class (water, other) segmentation of Sentinel-2 and Landsat-7/8 5-band (RGB+NIR+SWIR) images of coasts.</strong></em></p> <p>These Residual-UNet model data are based on RGB+NIR+SWIR (red, green, blue, near infrared and shortwave infrared) images of coasts and associated labels.</p> <p>Models have been created using Segmentation Gym* using the following dataset**: <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263</a></p> <p>Classes: {0=other, 1=water}</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 2-class labels for semantic segmentation of Sentinel-2 and Landsat RGB, NIR, and SWIR satellite images of coasts (water, other) (v1.0) [Data set]. Zenodo. <a href="https://doi.org/10.5281/zenodo.7384263">https://doi.org/10.5281/zenodo.7384263</a></p>
Assessment of the performance of the atmospheric correction algorithm MAJA for Sentinel-2 surface reflectance estimates
<p>Data associated to the paper "Assessment of the performance of the atmospheric correction algorithm MAJA for Sentinel-2 surface reflectance estimates", Colin, J. et al.</p> <p>Contact: jerome.colin[at]cnrs.fr<br> CESBIO Lab, Toulouse, France</p> <p>Content:<br> - APU_all_sites: APU plots for all the ACIX-II sites<br> - Maja_L2A_noadj_notopo: MAJA Level-2A subsets used to compare against ACIX-II reference reflectances for all sites and time steps<br> - quicklooks_all_sites: quicklooks for all sites</p> <p> </p>
Keypoints Method for Recognition of Ship Wake Components in Sentinel-2 Images by Deep Learning
<p>The dataset used in the study consists of imagery capturing ship wake patterns. It is a manually curated dataset specifically created for the purpose of training and evaluating the wake component detection model. The dataset contains a collection of image chips, each focusing on a specific ship wake instance.</p> <p>The imagery in the dataset is acquired from satellite sensors, specifically on Sentinel-2 satellite imagery. Sentinel-2 provides multispectral data with high spatial resolution, allowing for detailed analysis of ship wake patterns. The dataset includes images captured on B8 spectral band, enabling the exploration of the wake detection model's performance under various spectral conditions. These images have been pre-processed (by scaling+CLAHE) to highlight ocean surface features.</p> <p>Each image chip in the dataset is annotated with keypoint locations representing specific wake components, such as the ship wake vertex, the ending of the turbulent wake, and the ending of Kelvin arms. These annotations serve as ground truth labels for training and evaluating the wake component detection model. </p> <p>Additionally, the dataset includes samples with variations in environmental conditions, such as different sea states, lighting conditions, and wake complexities. This variability allows for a comprehensive evaluation of the model's generalization capability and robustness across diverse scenarios.</p>
Tampered Sentinel-2 images
<p>A simple Sentinel-2 images dataset for forgery detection. </p>
WHUS2-CRv a global thin cloud removal dataset for Sentinel-2 images——Train part
<p>The training parts of WHUS2-CRv dataset in which the paired cloud and cloud-free Sentinel-2 images are from different regions of the world. The types of land cover are rich and the acquisition dates of the experimental data cover a long time period (from 2015 to 2020) and all seasons.</p> <p>The validation and testing parts can be found on: <a href="https://doi.org/10.5281/zenodo.8035349">https://doi.org/10.5281/zenodo.8035349</a></p> <p>If you use this dataset for your research, please cite us accordingly:</p> <p>#Reference: </p> <p>[1]J. Li, Z. W, Z. Hu, J. Z, M. Li, L. Mo and M. Molinier, “Thin cloud removal in optical remote sensing images based on generative adversarial networks and physical model of cloud distortion,” ISPRS J. Photogramm. Remote Sens., vol. 166, pp. 373-389, Aug. 2020,<a href="http://doi.org/10.1016/j.isprsjprs.2020.06.021">http://doi.org/10.1016/j.isprsjprs.2020.06.021</a>.</p> <p>[2]J. Li, Z. Wu, Z. Hu, Z. Li, Y. Wang, and M. Molinier, “Deep learning based thin cloud removal fusing vegetation red edge and short wave infrared spectral information for Sentinel-2A imagery,” Remote Sens., vol. 13, no. 1, p. 157, Jan. 2021, <a href="http://doi.org/10.3390/rs13010157">http://doi.org/10.3390/rs13010157</a>.</p> <p>[3]J. Li, Y. Zhang, Q. Sheng, Z. Wu, B. Wang, Z. Hu, G. Shen, M. Schmitt, M. Molinier, “Thin Cloud Removal Fusing Full Spectral and Spatial Features for Sentinel-2 Imagery,” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 15, pp. 8759-8775, 2022, <a href="http://10.1109/JSTARS.2022.3211857">http://doi.org/10.1109/JSTARS.2022.3211857</a>.</p>
A burned area database from Sentinel-2 imagery (2016-2022) for Madagascar, southern Mozambique, Eswatini and eastern South Africa
<p>This database includes georeferenced burned area at 20 m and fire dates covering the period 2016-2022 for Madagascar, southern Mozambique (Maputo, Maputo City, Gaza, Inhambane), Eswatini, and eastern South Africa (Limpopo, Mpumalanga, KwaZulu-Natal, Eastern Cape). The classification of burned areas has been done based on 165,833 Sentinel-2 scenes (2A and 2B), by applying a two-phased algorithm on the probability output of a random forest model. The product has been validated in Madagascar with long temporal reference burned area units distributed into two fire activity strata. The accuracy analysis performed for the years 2019 and 2021 revealed a Dice coefficient of ≥79%, commission errors ≤18% and omission error ≤24% with a relative bias of about -8%. Intercomparisons with other available burned area products (FireCCISFD11, FireCCISFD20, GABAM, FireCCI51, C3SBA11, MCD64) indicated a consistent performance throughout the entire period. The product is provided in shapefiles, divided into four-month periods. Each shapefile contains a field named “BurnDate” indicating the date when the burned area was detected in format YYYYMMDD. Missing values indicate areas that were not burned, while zero values represent areas that were not considered in the mapping process due to persistent pixel low quality conditions.</p>
xAI Ship Wakes in Sentinel-2 L2A images
<h2><strong>xS2Wakes: A dataset for xAI of Wakes in S-2 (L2A).</strong></h2><h3><strong>Summary</strong></h3><p>The dataset is derived from Sentinel-2 Level-2A (L2A) satellite images and focuses on the marine domain over Danish fjords. It provides a comprehensive collection of ship wakes and background clutter (referred to as "no_<i>wake</i>_crop") for remote sensing applications. The dataset has undergone post-processing through the Contrast Limited Adaptive Histogram Equalization (CLAHE) algorithm with a clip limit value of 0.12 and a tile size of 16x16. The dataset comprises four spectral bands: B2, B3, B4, and B8.</p><h3><strong>Importance and Relevance to Remote Sensing Community</strong></h3><h4>Multifaceted Applications of Wake Detection</h4><p>Ship wake detection serves as a cornerstone in a multitude of domains that are critical to both human and environmental well-being:</p><p><strong>Navigational Safety</strong>: Understanding ship wakes can provide insights into water currents and traffic patterns. This is vital for ensuring the safe passage of marine vessels, particularly in narrow straits and busy ports.</p><p><strong>Environmental Monitoring</strong>: The study of ship wakes can reveal the influence of vessels on aquatic ecosystems. For instance, excessive wake turbulence can lead to coastal erosion and can disrupt marine habitats.</p><p><strong>Maritime Surveillance</strong>: Wake detection plays a crucial role in maintaining maritime security. Tracking the wakes of vessels can help in identifying illegal activities such as smuggling or unauthorized fishing.</p><h3><strong>Specifications</strong></h3><ul><li><strong>Data Source</strong>: Sentinel-2 L2A</li><li><strong>Region of Interest</strong>: Danish fjords</li><li><strong>Classes</strong>: Wake, No-Wake</li><li><strong>Number of Samples</strong>:<ul><li>Wake: 123</li><li>No-Wake: 150</li></ul></li><li><strong>Spectral Bands</strong>: B2 (Blue), B3 (Green), B4 (Red), B8 (NIR)</li><li><strong>Post-Processing</strong>: CLAHE (Clip Limit = 0.12, Tile Size = 16x16)</li><li><strong>Average Wake Chip Size</strong>: 390x351 pixels</li><li><strong>Average No-Wake Chip Size</strong>: 380x390 pixels</li></ul><h3><strong>Wake Detection and Analysis</strong></h3><h4>Traditional Methods and Their Limitations</h4><p>Traditionally, the process of ship wake detection has largely been a manual endeavor or employed simplistic statistical algorithms. Analysts would sift through satellite or aerial images to identify ship wakes, a process that is both time-consuming and prone to human error. Even automated statistical methods often lack the robustness needed to differentiate between true wakes and false positives, such as aquatic plants or natural water disturbances.</p><h4>Role of xAI (Explainable AI) in Wake Identification</h4><p>The introduction of explainable AI (xAI) techniques brings another layer of sophistication to wake analysis. While traditional machine learning models may offer high performance, they often act as "black boxes," making it difficult to understand how they arrive at a certain conclusion. In a critical domain like navigational safety or maritime surveillance, the ability to interpret and understand model decisions is indispensable. xAI methods can make these machine learning models more transparent, providing insights into their decision-making processes, which in turn can aid in fine-tuning or fully trusting the models.</p><h4>Spectral Bands Selected</h4><p>The inclusion of four key spectral bands—B2, B3, B4, and B8—offers the scope for multi-spectral analysis. Different bands can capture varying features of water and wake textures, thereby offering a richer feature set for machine learning models. We use these spectral bands as referred to in [Liu, Yingfei, Jun Zhao, and Yan Qin. "A novel technique for ship wake detection from optical images." <i>Remote Sensing of Environment</i> 258 (2021): 112375.] </p><h4>Understanding Optical vs. SAR Imaging Modalities</h4><p>It is important to note the fundamental differences between wakes captured in Synthetic Aperture Radar (SAR) images and those in optical imagery. In SAR images, narrow-V wakes often arise due to Bragg scattering, a phenomenon that does not exist at optical wavelengths. In optical images, bright lines close to turbulent wakes are actually foams generated by the interaction between the surface horizontal flow of turbulent wakes and the surrounding background waves (Ermakov et al., 2014; Milgram et al., 1993; Peltzer et al., 1992). This can make the detection of wakes in optical images more challenging as there are usually no bright lines near turbulent wakes, and Kelvin arms may also show dark contrast. Methods that solely rely on searching for a trough and peak pair, taking the trough as the turbulent wake, would miss many actual wakes and could also result in the identification of false wakes.</p><h4>Contrast Enhancement</h4><p>The application of the CLAHE (Contrast Limited Adaptive Histogram Equalization) algorithm to this dataset allows for enhanced local contrast, enabling subtle features to become more pronounced. This significantly aids machine learning algorithms in feature extraction, thereby improving their ability to distinguish between complex patterns.</p><h4>Environment and Clutter Assessment</h4><p>In addition to wakes, the dataset contains samples labeled as "No-Wake," which include environmental clutter and clouds. These samples are crucial for training robust models that can differentiate wakes from similar-looking natural phenomena.</p>
Selective Avoidance of Sentinel Lymph Node Biopsy After Neoadjuvant Chemotherapy In HER-2 Positive/Triple Negative Breast Cancer Patients With Excellent Radiologic Response to the Breast and Axilla, P
ClinicalTrials.gov study NCT04993625. IPD Sharing: NO. Countries: 1. Publications: 1.
Training dataset for land type detection on Sentinel-2 images (annotations: build-up, rural, forest, water)
Open the record for dataset details and reuse information.
Intertidal topography at 10m Resolution Derived from Sentinel-2 Multi-Spectral Imagery for the Bengal Delta Coastline
<p>This repository contains the intertidal topography (e.g., digital elevation model) at 10m spatial resolution and the source-code of the toolbox used in deriving this dataset from Sentinel-2 Level-2A spectral imagery and a regional tidal model. The dataset covers the coastal Bangladesh and West Bengal located in the northern Bay of Bengal. The method and its performance is described in detail in the following paper - </p><p> </p><p>Khan, M.J.U.; Ansary, M.N.; Durand, F.; Testut, L.; Ishaque, M.; Calmant, S.; Krien, Y.; Islam, A.K.M.S.; Papa, F. High-Resolution Intertidal Topography from Sentinel-2 Multi-Spectral Imagery: Synergy between Remote Sensing and Numerical Modeling. Remote Sens. 2019, 11, 2888. https://doi.org/10.3390/rs11242888</p><p> </p><p>The repository has the following files and directory - </p><p> </p><p>1. `DEM_intertidal.dat`: This text file contains the extracted intertidal DEM as space separated x (column 1), y (column 2), z (column 3) points. The spatial location are given in longitude (x), latitude (y), and the vertical height (z) is given in meters (upward positive).</p><p>2. `pyIntertidalDEM.zip`: This compressed zip folder contains a snapshot of the toolbox (https://github.com/jamal919/pyIntertidalDEM/tree/f05de55d726fd4356f9fb8979a2cf0f42f0ec9b1) used to extract the instantaneous shorelines for the current version of the intertidal DEM. The code is also accessible in its most updated version from the github repository - https://github.com/jamal919/pyIntertidalDEM.</p><p>3. `README.txt`: This text file.</p><p> </p><p>The dataset is published under a Creative Commons Attribution 4.0 International license. The pyIntertidalDEM toolbox is published under a Apache License 2.0.</p>
Thin cloud removal dataset for Sentinel-2 images
<p>This is a thin cloud removal dataset for Sentinel-2A images in CR-GAN-PM[1] article. This dataset contains 20 paired thin cloud and clear Sentinel-2 images.</p> <p>If you use this dataset for your research, please cite us accordingly:</p> <p>#Reference: </p> <p>[1] J. Li, Z. W, Z. Hu, J. Z, M. Li, L. Mo and M. Molinier, “Thin cloud removal in optical remote sensing images based on generative adversarial networks and physical model of cloud distortion,” ISPRS J. Photogramm. Remote Sens., vol. 166, pp. 373–389, Aug. 2020. <a href="http://doi.org/10.1016/j.isprsjprs.2020.06.021">http://doi.org/10.1016/j.isprsjprs.2020.06.021</a>.</p> <p><br> [2] J. Li, Z. Wu, Z. Hu, Z. Li, Y. Wang, and M. Molinier, “Deep learning based thin cloud removal fusing vegetation red edge and short wave infrared spectral information for Sentinel-2A imagery,” Remote Sens., vol. 13, no. 1, p. 157, Jan. 2021. <a href="http://doi.org/10.3390/rs13010157">http://doi.org/10.3390/rs13010157</a>.</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.