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”
Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 RGB images of coasts. SWED-only version
<p><strong>Doodleverse/Segmentation Zoo Res-UNet models for identifying water in Sentinel-2 RGB images of coasts.</strong></p> <p><strong>Based on SWED*** data</strong></p> <p>https://openmldata.ukho.gov.uk/</p> <p>These Residual-UNet model data are based on images of coasts and associated labels. Models have been fitted to the following types of data</p> <p>1. RGB (3 band): red, green, blue</p> <p>Classes are: {0: null, 1: water}.</p> <p>These files are used in conjunction with Segmentation Zoo*</p> <p>For each model, there are 3 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> </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` or the Segmentation Zoo* function `select_model_and_batch_process_folder.py` to segment a folder of images</p> <p> </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>'_history.npz'</strong> files contain model training metrics</p> <p> </p> <p>One additional file, BEST_MODEL.txt, contains the name of the model with the highest validation accuracy</p> <p> </p> <p>References</p> <p>* https://github.com/Doodleverse/segmentation_zoo</p> <p>** https://github.com/Doodleverse/segmentation_gym</p> <p>*** https://www.sciencedirect.com/science/article/abs/pii/S0034425722001584</p>
Sentinel-2 B02 jp2
<p>***** FRANÇAIS ****</p> <p>Fichier JP2 T31TCH_20190126T105321_B02.jp2 du produit Sentinel-2 S2A_MSIL1C_20190126T105321_N0207_R051_T31TCH_20190126T112638.SAFE</p> <p>***** ENGLISH ****</p> <p>JP2 file T31TCH_20190126T105321_B02.jp2 from the Sentinel-2 product S2A_MSIL1C_20190126T105321_N0207_R051_T31TCH_20190126T112638.SAFE</p>
MineSegSAT: An automated system to evaluate mining disturbed area extents from Sentinel-2 imagery
<p>This dataset includes segmentation maps of environmentally impacted areas of mineral extraction sites in Canada and corresponding atmospherically corrected Sentinel-2 data from 2021. </p> <p>To look at an example of how to use the uncompressed assets, see this GitHub repository here: https://github.com/macdonaldezra/MineSegSAT. </p> <p>This dataset and code accompany the paper published at ECRS 2023 which can be found on the conference website at https://doi.org/10.3390/ECRS2023-16886 or at the Arxiv link http://arxiv.org/abs/2311.01676.</p>
Usable observations over Europe: Evaluation of compositing windows for landsat and sentinel-2 time series
<p>Landsat and Sentinel-2 data archives provide ever-increasing amounts of satellite data. However, the availability of usable observations greatly varies spatially and temporally. Pixel-based compositing that generates temporally equidistant cloud-free synthetic images can mitigate temporal variability, by constructing uninterrupted time series using different compositing windows. Here, we evaluated the feasibility of using compositing windows ranging from five days to one year for 1984-2021 Landsat and 2015-2021 Sentinel 2 time series to derive uninterrupted time series across Europe. We considered separate and joint use of both data archives and analyzed the spatio-temporal availability of composites during each calendar year and pixel-specific growing season across a variety of time windows and hypothesizing data interpolation. Our results demonstrated opportunities and limitations in the available data records to support medium- and long-term analyses requiring uninterrupted time series of composites with sub-annual temporal resolution. Spatial disparities across different compositing windows provide guidance on the feasibility of workflows relying on different data densities and on the challenges in wall-to-wall analyses. The feasibility of consistent time series based on composites with sub-monthly aggregation periods was mostly limited to the combined Landsat and Sentinel-2 archives after 2015, yet in some geographies requires interpolation of up to 50% of data.</p>
Sentinel-2 reference cloud masks generated by an active learning method
<p> <strong>Reference classifications generated with Active Learning for Cloud Detection (ALCD)</strong></p> <p>This data set provides a reference cloud mask data set for 38 Sentinel-2 scenes. These reference masks have been created with the ALCD tool, developed by Louis Baetens, under the direction of Olivier Hagolle at CESBIO/CNES[1]. They were created to validate the cloud masks generated by the MAJA software [2].</p> <p>- The `Reference_dataset` directory contains 31 scenes selected in 2017 or 2018.<br> - The `Hollstein` directory contains 7 scenes that were used to validate the ALCD tool by comparison to manually generated reference images kindlyprovided by Hollstein et al[3]<br> One of these scenes is present in both directories. For the validation of MAJA, the "Hollstein" scenes were not used because of their acquisition at a time period when Sentinel-2 was not yet operational, with a degraded repetitivity of observations.</p> <p><strong># Description of the data structure</strong><br> The name of each scene directory is the name of the corresponding Sentinel-2 L1C product.<br> In the scene directory, three sub-directories can be found.<br> - `Classification`<br> - `Samples`<br> - `Statistics`</p> <p><strong># Description of the files</strong><br> - `Classification/classification_map.tif` --- the main product, which is the classified scene. 7 classes are available. Each one is represented with a different integer.<br> 0: no_data.<br> 1: not used.<br> 2: low clouds.<br> 3: high clouds.<br> 4: clouds shadows.<br> 5: land.<br> 6: water.<br> 7: snow.</p> <p>- `Classification/confidence_enhanced.tif` --- enhanced confidence map of the classification. The values are between 0 and 255 (coded on 1 bit).<br> The original confidence map is, for each pixel, the proportion of votes for the majority class as the classification map has been created via a Random Forest algorithm.<br> A median filter has been applied to this confidence map. Finally, the value was saved on 1 bit, leading to the value being between 0 and 255.</p> <p>- `Classification/contours.png` --- the contours of the classes from the classification map, overlayed on the scene. The color code depends on each class.<br> Green: low and high clouds. Yellow: cloud shadows. Blue: water. Purple: snow.</p> <p>- `Classification/used_parameters.json` --- the parameters that were used to classify the scene. It includes the tile code, the cloudy and clear dates, along with their product reference.</p> <p>- `Samples/` --- this directory contains all the shapefiles, one per class.</p> <p>- `Statistics/k_fold_summary.json` --- results of the 10-fold cross-validation on the scene.<br> 5 metrics are computed, in the order given in the "metrics_names". "all_metrics" is a list of the 10 folds, with the 5 metrics in the correct order for each fold.<br> "means" and "stds" are the means and standard deviations of the 10 folds.</p> <p><br> <strong># References</strong></p> <p>[1] Baetens, L.; Desjardins, C.; Hagolle, O. Validation of Copernicus Sentinel-2 Cloud Masks Obtained from MAJA, Sen2Cor, and FMask Processors Using Reference Cloud Masks Generated with a Supervised Active Learning Procedure. <em>Remote Sens.</em> <strong>2019</strong>, <em>11</em>, 433.</p> <p>[2] A multi-temporal method for cloud detection, applied to FORMOSAT-2, VENµS, LANDSAT and SENTINEL-2 images, O Hagolle, M Huc, D. Villa Pascual, G Dedieu, Remote Sensing of Environment 114 (8), 1747-1755, 2010</p> <p>[3] Hollstein, A.; Segl, K.; Guanter, L.; Brell, M.; Enesco, M. Ready-to-Use Methods for the Detection of Clouds, Cirrus, Snow, Shadow, Water and Clear Sky Pixels in Sentinel-2 MSI Images. Remote Sens. 2016, 8, 666</p>
SD4EO: AI-based synthetic satellite Sentinel-2 images of cities and building coverture (RGB+NIR bands)
<p>This dataset has been created as part of the deliverables for ESA’s <a href="https://eo4society.esa.int/projects/sd4eo/">SD4EO project</a>. It consists of synthetic versions of Sentinel-2 images in urban areas. These images were synthetically generated using schematic representations from Open Street Maps as a guide to create AI-based conditioned diffusion model images in the visible and near-infrared spectrum, along with coverage masks for non-residential buildings and the set of residential buildings combined with the former.</p> <p>At least five synthetic variants were generated for each of the eleven cities:</p> <ul> <li>Paris (11 variants)</li> <li>Toulouse (9 variants)</li> <li>Poitiers (8 variants)</li> <li>Bordeaux (6 variants)</li> <li>Limoges (9 variants)</li> <li>Clermont-Ferrand (5 variants)</li> <li>Troyes (6 variants)</li> <li>Le Mans (14 variants)</li> <li>Angers (7 variants)</li> <li>Madrid (15 variants)</li> <li>Niort (6 variants)</li> </ul> <p>The file names within the ZIP archives follow a very simple schema:</p> <p>`assembled_` + city name + usage or band indicator + variant + PNG extension / NC extension</p> <p>Each of the four types of images has a different indicator or band:</p> <ul> <li>`_RGB_` for images encoding visible spectrum signals</li> <li>`_NIR_` for images generated for the near-infrared band</li> <li>`_full_allbuildingmask` for the coverage pixel mask of all building types in floating point</li> <li>`_full_nonresidentialmask` for the coverage pixel mask of non-residential buildings in floating point</li> <li>if we have no indicator, then it is a netCDF file with a labelled xarray that merges RGB+NIR as the original Sentinel-2 spectral bands in full original range</li> </ul> <p>NOTE: This 5th version corrects a minor bug in 3rd version of this dataset. If you want to access to version 4 (with non-already assembled patches), it is also available in the right side control version list.</p> <p>The SD4EO Project is funded by the ESA’s FutureEO programme under contract no. 4000142334/23/I-DT and supervised by ESA Φ-lab.</p>
Mapping of glacial lakes using Sentinel-1 and Sentinel-2 data and a random forest classifier: Strengths and challenges
<p>The water body detection and mapping algorithm named 'glakemap' that I designed was aimed at specifically mapping glacial lakes across alpine regions where their detection and mapping are challenged by many factors such as shadows, cloud cover, turbidity, and ice surface. The algorithm uses Copernicus Sentinel-1 and -2 satellites data and machine learning model (random forest) in an integrated manner to automatically classify glacial lakes from other surface features. In specific, the algorithm takes Sentinel-1 and -2 satellites data as the main inputs. It calculates radar backscatter and Normalised Difference Water Indices (NDWIs) using these datasets, respectively. The radar backscatter and NDWIs products (images) are segmented using a set of rules producing many polygons including lake polygons. Lake polygons are then automatically separated/retained using the random forest model which is trained using features relevant to lakes.</p> <p>The dataset is also available at https://www.mountcryo.org/</p>
WHUS2-CD+ dataset for sentinel-2 cloud detection validation
<p>WHUS2-CD+ is a cloud validation detection dataset for Sentinel-2A images. WHUS2-CD+ contains 36 manually labeled cloud masks at 10m resolution and corresponding Sentinel-2A images evenly distributed over China mainland.</p> <p>If you use this dataset for your research, please cite us accordingly:</p> <p>#Reference: </p> <p>[1] J. Li, Z. Wu, Z. Hu, C. Jian, S. Luo, L. Mou, X. Zhu, and M. Molinier, "A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features," in IEEE Transactions on Geoscience and Remote Sensing, 2021. <a href="https://doi.org/10.1109/TGRS.2021.3069641">https://doi.org/10.1109/TGRS.2021.3069641</a>.</p> <p>[2] Z. Wu, J. Li, Y. Wang, Z. Hu and M. Molinier, "Self-Attentive Generative Adversarial Network for Cloud Detection in High Resolution Remote Sensing Images," in IEEE Geoscience and Remote Sensing Letters, vol. 17, no. 10, pp. 1792-1796, Oct. 2020. <a href="https://doi.org/10.1109/LGRS.2019.2955071">https://doi.org/10.1109/LGRS.2019.2955071</a>.</p> <p>The training and testing list is (The challenging senes are marked in bold):</p> <table> <tbody> <tr> <td>Training set</td> </tr> <tr> <td>S2A_MSIL1C_20190714T043711_N0208_R033_T46TFN_20190714T073938</td> </tr> <tr> <td>S2A_MSIL1C_20191219T040151_N0208_R004_T47SQU_20191219T055033</td> </tr> <tr> <td>S2A_MSIL1C_20190630T045701_N0207_R119_T45SWC_20190630T080543</td> </tr> <tr> <td>S2A_MSIL1C_20191215T042151_N0208_R090_T46RGV_20191215T065406</td> </tr> <tr> <td>S2A_MSIL1C_20180930T044701_N0206_R076_T45SXR_20180930T074413</td> </tr> <tr> <td>S2A_MSIL1C_20200317T024541_N0209_R132_T51TWM_20200317T053350</td> </tr> <tr> <td>S2A_MSIL1C_20180816T053641_N0206_R005_T44TKK_20180816T093424</td> </tr> <tr> <td>S2A_MSIL1C_20191023T040821_N0208_R047_T47TQF_20191023T074550</td> </tr> <tr> <td>S2A_MSIL1C_20180824T031541_N0206_R118_T50TKL_20180824T061636</td> </tr> <tr> <td>S2A_MSIL1C_20191118T025011_N0208_R132_T50RMN_20191118T071843</td> </tr> <tr> <td>S2A_MSIL1C_20190916T023551_N0208_R089_T50RQS_20190916T042547</td> </tr> <tr> <td>S2A_MSIL1C_20190819T031541_N0208_R118_T49SFU_20190819T065332</td> </tr> <tr> <td>S2A_MSIL1C_20190815T051651_N0208_R062_T44TPN_20190815T090034</td> </tr> <tr> <td>S2A_MSIL1C_20200410T022551_N0209_R046_T51TXG_20200410T042047</td> </tr> <tr> <td>S2A_MSIL1C_20191002T025551_N0208_R032_T50TQQ_20191002T054113</td> </tr> <tr> <td>S2A_MSIL1C_20180429T032541_N0206_R018_T49SCV_20180429T062304</td> </tr> <tr> <td>S2A_MSIL1C_20200506T024551_N0209_R132_T51UWS_20200506T043639</td> </tr> <tr> <td>S2A_MSIL1C_20200325T034531_N0209_R104_T47RQL_20200325T065315</td> </tr> <tr> <td>S2A_MSIL1C_20190928T031541_N0208_R118_T49RBJ_20190928T061248</td> </tr> <tr> <td>S2A_MSIL1C_20180827T032541_N0206_R018_T48RYV_20180827T062627</td> </tr> <tr> <td>S2A_MSIL1C_20200222T030731_N0209_R075_T49QEE_20200222T060244</td> </tr> <tr> <td>S2A_MSIL1C_20180722T030541_N0206_R075_T49RFP_20180722T060550</td> </tr> <tr> <td>S2A_MSIL1C_20180729T025551_N0206_R032_T49RGL_20180729T055945</td> </tr> <tr> <td>S2A_MSIL1C_20200506T024551_N0209_R132_T50SPE_20200506T052918</td> </tr> <tr> <td>Testing set</td> </tr> <tr> <td>S2A_MSIL1C_20180930T030541_N0206_R075_T49QDD_20180930T060706</td> </tr> <tr> <td>S2A_MSIL1C_20191105T023901_N0208_R089_T51STR_20191105T054744</td> </tr> <tr> <td>S2A_MSIL1C_20190812T032541_N0208_R018_T48RXU_20190812T070322</td> </tr> <tr> <td>S2A_MSIL1C_20190602T021611_N0207_R003_T52TES_20190602T042019</td> </tr> <tr> <td>S2A_MSIL1C_20190328T033701_N0207_R061_T49TCF_20190328T071457</td> </tr> <tr> <td>S2A_MSIL1C_20191001T050701_N0208_R019_T45TXN_20191002T142939</td> </tr> <tr> <td>S2A_MSIL1C_20200416T042701_N0209_R133_T46SFE_20200416T074050</td> </tr> <tr> <td>S2A_MSIL1C_20200528T050701_N0209_R019_T44SPC_20200528T082127</td> </tr> <tr> <td><strong>S2A_MSIL1C_20210207T023851_N0209_R089_T52UCU_20210207T040210</strong></td> </tr> <tr> <td><strong>S2A_MSIL1C_20210126T052111_N0209_R062_T44SNE_20210126T063836</strong></td> </tr> <tr> <td><strong>S2A_MSIL1C_20210102T054231_N0209_R005_T43SFB_20210102T065941</strong></td> </tr> <tr> <td><strong>S2A_MSIL1C_20201206T041141_N0209_R047_T47SMV_20201206T053320</strong></td> </tr> </tbody> </table>
Sentinel-2 L1C and L2A pixel samples for band regression
<p>This dataset contains pixels sampled from Sentinel-2 images. 198 scenes on the period going from early 2016 to the end of 2020 from 128 different MGRS tiles were used.</p> <p>For each acquisition, the data was obtained at 2 processing levels: 1C<br> (from PEPS, CNES' mirror of Sentinel data) and 2A (from Theia's<br> catalogue), the latter having been produced by the MAJA processor.</p> <p>For each acquisition, 100,000 pixels where sampled. Only non-saturated<br> pixels were selected, regardless of their cloud or shadow status. Pixel<br> positions were selected on the 20m resolution grid. For each 20m pixel<br> position, the following information was recorded:<br> - whether the pixel was detected as a cloud or a shadow (without<br> distinction of these 2 states),<br> - the reflectance in the 20m bands for levels 1C and 2A,<br> - the reflectance of the 4 corresponding pixels of each of the 10m<br> resolution bands for levels 1C and 2A,<br> - the reflectance at the 20m pixel position of the 60m resolution bands<br> after bicubic resampling for level 1C.<br> - the solar and viewing angles for each pixel.</p> <p>For each sampled scene, a CSV file with the name TILE_DATE_samples.csv (for example T05KRA_20171124_samples.csv) is provided.</p> <p>Each row in the file corresponds to a pixel. The columns provide the following variables:<br> - An integer used as unique identifier of the pixel in the file.<br> - The tile name in TIJXYZ format.<br> - The date in YYYMMDD format.<br> - The coverage: the percentage of the tile covered by the relative orbit of the acquisition.<br> - The x and y integer coordinates of the 20m. resolution pixel in the array.<br> - The reflectances of the 4 10 m resolution pixels corresponding to the 20 m. resolution pixels. The columns are named using the format Level_Band_i with Level being L1C or L2A, and i in {1, 2, 3, 4}. For the band, we keep the ESA (L1C) and Theia (L2A) respective nomenclatures, so we have L1C_B02_1 but L2A_B2_1.<br> - The reflectances of the 20 m resolution bands with columns named Level_Band and the same band name conventions, so we have L1C_B05 and L2A_B5.<br> - The reflectances of the L1C 60m resolution bands resampled to the 20m grid. The 3 columns are named L1C_B01, L1C_B09, L1C_B10.<br> - The reflectances of all the bands (10m and 20m resolution bands for L1C and L2A and the 60 m resolution bands for L1C) resampled to a 60 m resolution grid. The columns are named for instance L1C_B02_60 or L2A_B7_60.<br> - The solar Zenith and Azimuth angles: sun_zen, sun_az:<br> - The sensor Zenith and Azimuth angles split into even and odd detectors (inc_even_zen, inc_odd_zen, inc_even_az, inc_odd_az). The angles values are not recorded (empty value) for the detector to which the pixel does not belong to.<br> - A binary value (CLM) for the cloud and cloud shadow mask (0 if the pixel is clear, 1 if it is a cloud or a cloud shadow). This information is retrieved from the L2A masks.</p> <p>The list of column names is the following:<br> - tile<br> - date<br> - coverage<br> - x<br> - y<br> - L1C_B02_0<br> - L1C_B02_1<br> - L1C_B02_2<br> - L1C_B02_3<br> - L1C_B03_0<br> - L1C_B03_1<br> - L1C_B03_2<br> - L1C_B03_3<br> - L1C_B04_0<br> - L1C_B04_1<br> - L1C_B04_2<br> - L1C_B04_3<br> - L1C_B08_0<br> - L1C_B08_1<br> - L1C_B08_2<br> - L1C_B08_3<br> - L1C_B05<br> - L1C_B06<br> - L1C_B07<br> - L1C_B8A<br> - L1C_B11<br> - L1C_B12<br> - L1C_B01<br> - L1C_B09<br> - L1C_B10<br> - L2A_B2_0<br> - L2A_B2_1<br> - L2A_B2_2<br> - L2A_B2_3<br> - L2A_B3_0<br> - L2A_B3_1<br> - L2A_B3_2<br> - L2A_B3_3<br> - L2A_B4_0<br> - L2A_B4_1<br> - L2A_B4_2<br> - L2A_B4_3<br> - L2A_B8_0<br> - L2A_B8_1<br> - L2A_B8_2<br> - L2A_B8_3<br> - L2A_B5<br> - L2A_B6<br> - L2A_B7<br> - L2A_B8A<br> - L2A_B11<br> - L2A_B12<br> - sun_zen<br> - sun_az<br> - inc_even_zen<br> - inc_odd_zen<br> - inc_even_az<br> - inc_odd_az<br> - L1C_B02_60<br> - L1C_B03_60<br> - L1C_B04_60<br> - L1C_B08_60<br> - L1C_B05_60<br> - L1C_B06_60<br> - L1C_B07_60<br> - L1C_B8A_60<br> - L1C_B11_60<br> - L1C_B12_60<br> - L2A_B2_60<br> - L2A_B3_60<br> - L2A_B4_60<br> - L2A_B8_60<br> - L2A_B5_60<br> - L2A_B6_60<br> - L2A_B7_60<br> - L2A_B8A_60<br> - L2A_B11_60<br> - L2A_B12_60<br> - CLM</p> <p>The list of available CSV files is the following:</p> <p>- T05KRA_20171124_samples.csv<br> - T05KRA_20180329_samples.csv<br> - T05KRA_20180523_samples.csv<br> - T05KRA_20190408_samples.csv<br> - T05KRA_20191129_samples.csv<br> - T05KRA_20200402_samples.csv<br> - T05KRA_20200601_samples.csv<br> - T05KRA_20200805_samples.csv<br> - T05KRA_20201203_samples.csv<br> - T06KTF_20160324_samples.csv<br> - T06KTF_20171010_samples.csv<br> - T06KTF_20180627_samples.csv<br> - T06KTF_20181224_samples.csv<br> - T06KTF_20200616_samples.csv<br> - T06KTF_20200924_samples.csv<br> - T11SPC_20180918_samples.csv<br> - T11SPC_20180928_samples.csv<br> - T11SPC_20181013_samples.csv<br> - T11SPC_20181112_samples.csv<br> - T14SPF_20170321_samples.csv<br> - T14SQE_20170308_samples.csv<br> - T14SQE_20190402_samples.csv<br> - T14SQF_20180405_samples.csv<br> - T14SQF_20190420_samples.csv<br> - T18TUR_20180509_samples.csv<br> - T18TVS_20191026_samples.csv<br> - T18TXS_20171018_samples.csv<br> - T18UVU_20190703_samples.csv<br> - T18UVU_20190827_samples.csv<br> - T18UWU_20190327_samples.csv<br> - T18UXU_20200210_samples.csv<br> - T18UXV_20191013_samples.csv<br> - T18UYV_20191217_samples.csv<br> - T19LHH_20200925_samples.csv<br> - T19LHJ_20190723_samples.csv<br> - T19LHJ_20200218_samples.csv<br> - T19TCL_20170811_samples.csv<br> - T19TCL_20201103_samples.csv<br> - T20LKP_20171001_samples.csv<br> - T20LKP_20191125_samples.csv<br> - T20LLQ_20180901_samples.csv<br> - T20NNP_20190807_samples.csv<br> - T20PPC_20191103_samples.csv<br> - T21NYG_20191002_samples.csv<br> - T21NZG_20180714_samples.csv<br> - T22KHA_20191027_samples.csv<br> - T22MGB_20201216_samples.csv<br> - T22MHB_20200803_samples.csv<br> - T22NCH_20181009_samples.csv<br> - T23KKR_20160808_samples.csv<br> - T23MKS_20200830_samples.csv<br> - T23MLS_20191219_samples.csv<br> - T23MLT_20190319_samples.csv<br> - T23MLT_20191114_samples.csv<br> - T23MLT_20200313_samples.csv<br> - T24MWU_20190916_samples.csv<br> - T24MWU_20201214_samples.csv<br> - T24MYT_20160918_samples.csv<br> - T24MYT_20200425_samples.csv<br> - T25LBL_20161214_samples.csv<br> - T25LBL_20180801_samples.csv<br> - T25LBL_20181209_samples.csv<br> - T25MBM_20171214_samples.csv<br> - T25MBN_20200113_samples.csv<br> - T25MBP_20180607_samples.csv<br> - T28PCB_20181129_samples.csv<br> - T28PDU_20181101_samples.csv<br> - T28PEV_20170405_samples.csv<br> - T28PGA_20170909_samples.csv<br> - T28PHC_20170323_samples.csv<br> - T28QCD_20160513_samples.csv<br> - T28QFD_20171002_samples.csv<br> - T28QFD_20180729_samples.csv<br> - T29SNC_20180927_samples.csv<br> - T29SPR_20201222_samples.csv<br> - T30PUT_20200522_samples.csv<br> - T30QZE_20181213_samples.csv<br> - T30QZE_20190924_samples.csv<br> - T30TTM_20181128_samples.csv<br> - T30TYM_20200126_samples.csv<br> - T31PGS_20191023_samples.csv<br> - T31QBU_20170107_samples.csv<br> - T31QCU_20170308_samples.csv<br> - T31QEU_20180330_samples.csv<br> - T31SDV_20171126_samples.csv<br> - T31SFA_20180907_samples.csv<br> - T31TDL_20190903_samples.csv<br> - T31UFS_20170814_samples.csv<br> - T31UGT_20171229_samples.csv<br> - T32PLS_20200919_samples.csv<br> - T32ULD_20161224_samples.csv<br> - T32ULE_20181124_samples.csv<br> - T32UMD_20190224_samples.csv<br> - T33KWP_20190729_samples.csv<br> - T33TUJ_20201007_samples.csv<br> - T36SXB_20191127_samples.csv<br> - T36SYB_20180317_samples.csv<br> - T36SYB_20200902_samples.csv<br> - T36SYB_20200907_samples.csv<br> - T36SYC_20180307_samples.csv<br> - T36SYC_20180327_samples.csv<br> - T36SYD_20170804_samples.csv<br> - T36SYD_20190111_samples.csv<br> - T37SBT_20190126_samples.csv<br> - T37SBU_20161122_samples.csv<br> - T37SBU_20201022_samples.csv<br> - T38KMB_20170817_samples.csv<br> - T38KNU_20200228_samples.csv<br> - T38KPE_20191026_samples.csv<br> - T38TNL_20180328_samples.csv<br> - T39KTU_20201126_samples.csv<br> - T40KCB_20160805_samples.csv<br> - T40KCB_20170323_samples.csv<br> - T40KCB_20170820_samples.csv<br> - T40KCB_20171123_samples.csv<br> - T40KCB_20200317_samples.csv<br> - T40KCB_20200829_samples.csv<br> - T42FVL_20180319_samples.csv<br> - T42FVL_20180729_samples.csv<br> - T42FVL_20201208_samples.csv<br> - T42FWL_20170405_samples.csv<br> - T42FWL_20200812_samples.csv<br> - T43QHA_20170315_samples.csv<br> - T43QHA_20180213_samples.csv<br> - T43QHV_20181110_samples.csv<br> - T43TCG_20200925_samples.csv<br> - T43TEG_20181227_samples.csv<br> - T43TEG_20201017_samples.csv<br> - T43TFH_20190516_samples.csv<br> - T44QLG_20181016_samples.csv<br> - T44TKM_20180408_samples.csv<br> - T44TLM_20181214_samples.csv<br> - T44TLN_20171224_samples.csv<br> - T44TLN_20190123_samples.csv<br> - T44TLN_20190128_samples.csv<br> - T45QWE_20200305_samples.csv<br> - T45QXG_20170316_samples.csv<br> - T45QXG_20190510_samples.csv<br> - T45QYF_20190721_samples.csv<br> - T45RXH_20190110_samples.csv<br> - T45RYH_20181002_samples.csv<br> - T45RYH_20201105_samples.csv<br> - T45RYJ_20190316_samples.csv<br> - T45RYK_20190105_samples.csv<br> - T45RYK_20190301_samples.csv<br> - T46QBM_20190117_samples.csv<br> - T46QBM_20190201_samples.csv<br> - T46QCL_20161213_samples.csv<br> - T46QCL_20191014_samples.csv<br> - T46RBN_20181118_samples.csv<br> - T46RCN_20181118_samples.csv<br> - T46RCN_20200127_samples.csv<br> - T46RCQ_20200117_samples.csv<br> - T47QRB_20200221_samples.csv<br> - T47QRB_20201117_samples.csv<br> - T47QRC_20170820_samples.csv<br> - T47QRC_20180318_samples.csv<br> - T47QRC_20200302_samples.csv<br> - T47QRC_20201217_samples.csv<br> - T48PVQ_20170814_samples.csv<br> - T48PVU_20170521_samples.csv<br> - T48PWA_20181222_samples.csv<br> - T48PWB_20180928_samples.csv<br> - T48PWR_20200525_samples.csv<br> - T48QTE_20201227_samples.csv<br> - T49MFM_20181031_samples.csv<br> - T49MFN_20200109_samples.csv<br> - T49REQ_20190418_samples.csv<br> - T49RFP_20200318_samples.csv<br> - T49RGN_20170525_samples.csv<br> - T49TCF_20171004_samples.csv<br> - T49TCF_20190502_samples.csv<br> - T49TCF_20191228_samples.csv<br> - T49TCF_20201013_samples.csv<br> - T50RKT_20200429_samples.csv<br> - T50RMS_20170706_samples.csv<br> - T50RMT_20200819_samples.csv<br> - T50RMU_20200804_samples.csv<br> - T50RNV_20190606_samples.csv<br> - T51RTQ_20161011_samples.csv<br> - T51RTQ_20161230_samples.csv<br> - T51RTQ_20170429_samples.csv<br> - T51RTQ_20171205_samples.csv<br> - T51RTQ_20180728_samples.csv<br> - T51RTQ_20200831_samples.csv<br> - T51STR_20160504_samples.csv<br> - T51STR_20171021_samples.csv<br> - T51STR_20180728_samples.csv<br> - T51STR_20200801_samples.csv<br> - T51STR_20201020_samples.csv<br> - T55HCB_20191003_samples.csv<br> - T55HCB_20200311_samples.csv<br> - T55HDA_20180513_samples.csv<br> - T58KCC_20180527_samples.csv<br> - T58KEB_20170906_samples.csv<br> - T58KGA_20180531_samples.csv<br> - T58KGC_20170529_samples.csv<br> - T58KHB_20171018_samples.csv</p>
Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 7-band (RGB+NIR+SWIR+NDWI+MNDWI) images of coasts.
<p>Doodleverse/Segmentation Zoo Res-UNet models for 4-class (water, whitewater, sediment and other) segmentation of Sentinel-2 and Landsat-7/8 7-band (RGB+NIR+SWIR+NDWI+MNDWI) images of coasts.</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>
Sentinel-2 based maps of irrigated fields in Vojvodina, Serbia
<p>This dataset consists of classified irrigated fields of the three most irrigated crops in Vojvodina (Serbia): maize, soybean, and sugar beet. Maps were generated for three years (2020, 2021, 2022), characterized by different climate conditions using Sentinel-2 satellite data and machine learning algorithms. All maps are in GIS format (.tiff) where label 0 corresponds to non-irrigated fields while label 1 corresponds to irrigated fields in Vojvodina and as if could be used for further research.</p>
Detection of slow-moving landslides from Sentinel-2 optical satellite imagery
<p>Datasets and code associated with recent ESPL publication</p> <p>"Detection of slow-moving landslides through automated satellite monitoring of surface deformation"</p> <p>The three imagery folders are zipped for convenience. The full code is included in the one .m file.</p> <p>Please get in touch with any questions.</p>
Satellite remote sensing dataset of Sentinel-2 for phenology metrics extraction from sites in Bulgaria and France
<p><strong>Site Description:</strong></p> <p>In this dataset, there are seventeen production crop fields in Bulgaria where winter rapeseed and wheat were grown and two research fields in France where winter wheat – rapeseed – barley – sunflower and winter wheat – irrigated maize crop rotation is used. The full description of those fields is in the database "In-situ crop phenology dataset from sites in Bulgaria and France" (doi.org/10.5281/zenodo.7875440).</p> <p> </p> <p><strong>Methodology and Data Description:</strong></p> <p>Remote sensing data is extracted from Sentinel-2 tiles 35TNJ for Bulgarian sites and 31TCJ for French sites on the day of the overpass since September 2015 for Sentinel-2 derived vegetation indices and since October 2016 for HR-VPP products. To suppress spectral mixing effects at the parcel boundaries, as highlighted by Meier et al., 2020, the values from all datasets were subgrouped per field and then aggregated to a single median value for further analysis.</p> <p>Sentinel-2 data was downloaded for all test sites from CREODIAS (https://creodias.eu/) in L2A processing level using a maximum scene-wide cloudy cover threshold of 75%. Scenes before 2017 were available in L1C processing level only. Scenes in L1C processing level were corrected for atmospheric effects after downloading using Sen2Cor (v2.9) with default settings. This was the same version used for the L2A scenes obtained intermediately from CREODIAS. </p> <p>Next, the data was extracted from the Sentinel-2 scenes for each field parcel where only SCL classes 4 (vegetation) and 5 (bare soil) pixels were kept. We resampled the 20m band B8A to match the spatial resolution of the green and red band (10m) using nearest neighbor interpolation. The entire image processing chain was carried out using the open-source Python Earth Observation Data Analysis Library (EOdal) (Graf et al., 2022).</p> <p>Apart from the widely used Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), we included two recently proposed indices that were reported to have a higher correlation with photosynthesis and drought response of vegetation: These were the Near-Infrared Reflection of Vegetation (NIRv) (Badgley et al., 2017) and Kernel NDVI (kNDVI) (Camps-Valls et al., 2021). We calculated the vegetation indices in two different ways: </p> <p>First, we used <strong>B08</strong> as near-infrared (NIR) band which comes in a native spatial resolution of 10 m. <strong>B08</strong> (central wavelength 833 nm) has a relatively coarse spectral resolution with a bandwidth of 106 nm.</p> <p>Second, we used <strong>B8A</strong> which is available at 20 m spatial resolution. <strong>B8A</strong> differs from B08 in its central wavelength (864 nm) and has a narrower bandwidth (21 nm or 22 nm in the case of Sentinel-2A and 2B, respectively) compared to B08.</p> <p> </p> <p>The High Resolution Vegetation Phenology and Productivity (<strong>HR-VPP</strong>) dataset from Copernicus Land Monitoring Service (CLMS) has three 10-m set products of Sentinel-2: vegetation indices, vegetation phenology and productivity parameters and seasonal trajectories (Tian et al., 2021). Both vegetation indices, Normalized Vegetation Index (NDVI) and Plant Phenology (PPI) and plant parameters, Fraction of Absorbed Photosynthetic Active Radiation (FAPAR) and Leaf Area Index (LAI) were computed for the time of Sentinel-2 overpass by the data provider. </p> <p>NDVI is computed directly from B04 and B08 and PPI is computed using Difference Vegetation Index (DVI = B08 - B04) and its seasonal maximum value per pixel. FAPAR and LAI are retrieved from B03 and B04 and B08 with neural network training on PROSAIL model simulations. The dataset has a quality flag product (QFLAG2) which is a 16-bit that extends the scene classification band (SCL) of the Sentinel-2 Level-2 products. A “medium” filter was used to mask out QFLAG2 values from 2 to 1022, leaving land pixels (bit 1) within or outside cloud proximity (bits 11 and 13) or cloud shadow proximity (bits 12 and 14). </p> <p>The <strong>HR-VPP</strong> daily raw vegetation indices products are described in detail in the user manual (Smets et al., 2022) and the computations details of PPI are given by Jin and Eklundh (2014). Seasonal trajectories refer to the 10-daily smoothed time-series of PPI used for vegetation phenology and productivity parameters retrieval with TIMESAT (Jönsson and Eklundh 2002, 2004).</p> <p>HR-VPP data was downloaded through the WEkEO Copernicus Data and Information Access Services (DIAS) system with a Python 3.8.10 harmonized data access (HDA) API 0.2.1. Zonal statistics [’min’, ’max’, ’mean’, ’median’, ’count’, ’std’, ’majority’] were computed on non-masked pixel values within field boundaries with rasterstats Python package 0.17.00.</p> <p> </p> <p>The Start of season date (SOSD), end of season date (EOSD) and length of seasons (LENGTH) were extracted from the annual Vegetation Phenology and Productivity Parameters (<strong>VPP</strong>) dataset as an additional source for comparison. These data are a product of the Vegetation Phenology and Productivity Parameters, see (https://land.copernicus.eu/pan-european/biophysical-parameters/high-resolution-vegetation-phenology-and-productivity/vegetation-phenology-and-productivity) for detailed information.</p> <p> </p> <p><strong>File Description:</strong></p> <p>4 datasets:</p> <p>1_senseco_data_S2_B08_Bulgaria_France; 1_senseco_data_S2_B8A_Bulgaria_France; 1_senseco_data_HR_VPP_Bulgaria_France; 1_senseco_data_phenology_VPP_Bulgaria_France</p> <p>3 metadata:</p> <p>2_senseco_metadata_S2_B08_B8A_Bulgaria_France; 2_senseco_metadata_HR_VPP_Bulgaria_France; 2_senseco_metadata_phenology_VPP_Bulgaria_France</p> <p> </p> <p>The dataset files “1_senseco_data_S2_B8_Bulgaria_France” and “1_senseco_data_S2_B8A_Bulgaria_France” concerns all vegetation indices (EVI, NDVI, kNDVI, NIRv) data values and related information, and metadata file “2_senseco_metadata_S2_B08_B8A_Bulgaria_France” describes all the existing variables. Both “1_senseco_data_S2_B8_Bulgaria_France” and “1_senseco_data_S2_B8A_Bulgaria_France” have the same column variable names and for that reason, they share the same metadata file “2_senseco_metadata_S2_B08_B8A_Bulgaria_France”.</p> <p>The dataset file “1_senseco_data_HR_VPP_Bulgaria_France” concerns vegetation indices (NDVI, PPI) and plant parameters (LAI, FAPAR) data values and related information, and metadata file “2_senseco_metadata_HRVPP_Bulgaria_France” describes all the existing variables. </p> <p>The dataset file “1_senseco_data_phenology_VPP_Bulgaria_France” concerns the vegetation phenology and productivity parameters (LENGTH, SOSD, EOSD) values and related information, and metadata file “2_senseco_metadata_VPP_Bulgaria_France” describes all the existing variables.</p> <p> </p> <p><strong>Bibliography</strong></p> <p>G. Badgley, C.B. Field, J.A. Berry, Canopy near-infrared reflectance and terrestrial photosynthesis, Sci. Adv. 3 (2017) e1602244. https://doi.org/10.1126/sciadv.1602244.</p> <p>G. Camps-Valls, M. Campos-Taberner, Á. Moreno-Martínez, S. Walther, G. Duveiller, A. Cescatti, M.D. Mahecha, J. Muñoz-Marí, F.J. García-Haro, L. Guanter, M. Jung, J.A. Gamon, M. Reichstein, S.W. Running, A unified vegetation index for quantifying the terrestrial biosphere, Sci. Adv. 7 (2021) eabc7447. https://doi.org/10.1126/sciadv.abc7447.</p> <p>L.V. Graf, G. Perich, H. Aasen, EOdal: An open-source Python package for large-scale agroecological research using Earth Observation and gridded environmental data, Comput. Electron. Agric. 203 (2022) 107487. https://doi.org/10.1016/j.compag.2022.107487.</p> <p>H. Jin, L. Eklundh, A physically based vegetation index for improved monitoring of plant phenology, Remote Sens. Environ. 152 (2014) 512–525. https://doi.org/10.1016/j.rse.2014.07.010.</p> <p>P. Jonsson, L. Eklundh, Seasonality extraction by function fitting to time-series of satellite sensor data, IEEE Trans. Geosci. Remote Sens. 40 (2002) 1824–1832. https://doi.org/10.1109/TGRS.2002.802519.</p> <p>P. Jönsson, L. Eklundh, TIMESAT—a program for analyzing time-series of satellite sensor data, Comput. Geosci. 30 (2004) 833–845. https://doi.org/10.1016/j.cageo.2004.05.006.</p> <p>J. Meier, W. Mauser, T. Hank, H. Bach, Assessments on the impact of high-resolution-sensor pixel sizes for common agricultural policy and smart farming services in European regions, Comput. Electron. Agric. 169 (2020) 105205. https://doi.org/10.1016/j.compag.2019.105205.</p> <p>B. Smets, Z. Cai, L. Eklund, F. Tian, K. Bonte, R. Van Hoost, R. Van De Kerchove, S. Adriaensen, B. De Roo, T. Jacobs, F. Camacho, J. Sánchez-Zapero, S. Else, H. Scheifinger, K. Hufkens, P. Jönsson, HR-VPP Product User Manual Vegetation Indices, 2022.</p> <p>F. Tian, Z. Cai, H. Jin, K. Hufkens, H. Scheifinger, T. Tagesson, B. Smets, R. Van Hoolst, K. Bonte, E. Ivits, X. Tong, J. Ardö, L. Eklundh, Calibrating vegetation phenology from Sentinel-2 using eddy covariance, PhenoCam, and PEP725 networks across Europe, Remote Sens. Environ. 260 (2021) 112456. https://doi.org/10.1016/j.rse.2021.112456.</p>
Sentinel-2 Wind Turbine Images with Spin and Spin Quality Labels
<p>Reproduction Data for training a classifier on the Sentinel-2 Band Offset for motion detection.</p>
Validation of the satellite-estimated sedimentation rates in reservoirs using 10-m Sentinel-2 satellites and water level data
<p><strong>Overview</strong>: The database contains data used for the validation of satellite-based sedimentation rates in eight reservoirs across the central and western United States using 10-m Sentinel-2 imagery and in-situ level data. Additional validation of the results from combining Sentinel-2 imagery with simulated 27-day Sentinel-3 altimetry levels is also included.</p> <p> </p> <p><strong>This dataset includes</strong>:</p> <ol> <li>Satellite-derived area-level duplets</li> <li>Bathymetry curves from satellite-based estimates</li> <li>Bathymetry curves from survey data</li> <li>Validation</li> </ol>
The T-REX Trial: Tailored Regional External Beam Radiotherapy in Clinically Node-negative Breast Cancer Patients With 1-2 Sentinel Node Macrometastases.
ClinicalTrials.gov study NCT05634889. IPD Sharing: YES. Countries: 2. Publications: 1.
Usable observations over Europe: Evaluation of compositing windows for landsat and sentinel-2 time series
Open the record for dataset details and reuse information.
SENTINEL-2 SATELLITE IMAGE (2015, AUGUST 7) FOR CHANGE DETECTION ON "MURGIA ALTA" - TIME T2 DATA
<p><strong>Time T2 data:</strong> Sentinel-2 image, 10 bands at 20 meters spatial resolution; 2015, August 7; subset of the "Murgia Alta" protected area; projected in WGS84/UTM33; coregistered on the time T1 data.</p>
Sentinel-2 derived Chlorophyll-a prediction maps for high-altitude lakes in the Sierra Nevada, Spain
<p>This dataset contains chlorophyll-a (ug/L) predictions for 4 high-altitude lakes in the Sierra Nevada Mountain Range, Spain. Predictions were made using a simple linear regression model with field sample chlorophyll-a as the dependent variable, and the following Sentinel-2 derived spectral index as the independent variable:</p><p>B3 - (B4+((B2-B4)*((665-560)/(665-490)))</p><p>Prediction maps are included as GeoTiffs and NetCDF files. Sentinel-2 data were atmospherically corrected using the following algorithms: </p><ul><li><a href="https://github.com/acolite/acolite/releases/tag/20221114.0">ACOLITE</a> (<a href="https://doi.org/10.1016/j.rse.2018.07.015">Vanhellemont & Ruddick, 2018</a>)</li><li><a href="https://grass.osgeo.org/grass83/manuals/i.atcorr.html">6SV</a> (<a href="https://doi.org/10.1109/36.581987">Vermote et al. 2006</a>)</li></ul><p><strong>Included Lakes and and their IDs:</strong></p><ul><li>Laguna de la Caldera (ID = P-2)</li><li>Laguna-embalse de las Yeguas (ID = D-6)</li><li>Laguna de Río Seco (ID = P-8)</li><li>Laguna Larga (ID = G-7)</li></ul>
Dataset for "Enhancing Cloud Detection in Sentinel-2 Imagery: A Spatial-Temporal Approach and Dataset"
<p>This dataset is built for time-series Sentinel-2 cloud detection and stored in Tensorflow TFRecord (refer to https://www.tensorflow.org/tutorials/load_data/tfrecord).</p> <p>Each file is compressed in 7z format and can be decompressed using Bandzip or 7-zip software.</p> <p><strong>Dataset </strong><strong> </strong><strong>Structure</strong>:</p> <p>Each filename can be split into three parts using underscores. The first part indicates whether it is designated for training or validation ('train' or 'val'); the second part indicates the Sentinel-2 tile name, and the last part indicates the number of samples in this file.</p> <p>For each sample, it includes:</p> <ol> <li>Sample ID;</li> <li>Array of time series 4 band image patches in 10m resolution, shaped as (n_timestamps, 4, 42, 42);</li> <li>Label list indicating cloud cover status for the center \(6\times6\) pixels of each timestamp;</li> <li>Ordinal list for each timestamp;</li> <li>Sample weight list (reserved);</li> </ol> <p>Here is a demonstration function for parsing the TFRecord file:</p> <pre><code>import tensorflow as tf # init Tensorflow Dataset from file name def parseRecordDirect(fname): sep = '/' parts = tf.strings.split(fname,sep) tn = tf.strings.split(parts[-1],sep='_')[-2] nn = tf.strings.to_number(tf.strings.split(parts[-1],sep='_')[-1],tf.dtypes.int64) t = tf.data.Dataset.from_tensors(tn).repeat().take(nn) t1 = tf.data.TFRecordDataset(fname) ds = tf.data.Dataset.zip((t, t1)) return ds keys_to_features_direct = { 'localid': tf.io.FixedLenFeature([], tf.int64, -1), 'image_raw_ldseries': tf.io.FixedLenFeature((), tf.string, ''), 'labels': tf.io.FixedLenFeature((), tf.string, ''), 'dates': tf.io.FixedLenFeature((), tf.string, ''), 'weights': tf.io.FixedLenFeature((), tf.string, '') } # The Decoder (Optional) class SeriesClassificationDirectDecorder(decoder.Decoder): """A tf.Example decoder for tfds classification datasets.""" def __init__(self) -> None: super().__init__() def decode(self, tid, ds): parsed = tf.io.parse_single_example(ds, keys_to_features_direct) encoded = parsed['image_raw_ldseries'] labels_encoded = parsed['labels'] decoded = tf.io.decode_raw(encoded, tf.uint16) label = tf.io.decode_raw(labels_encoded, tf.int8) dates = tf.io.decode_raw(parsed['dates'], tf.int64) weight = tf.io.decode_raw(parsed['weights'], tf.float32) decoded = tf.reshape(decoded,[-1,4,42,42]) sample_dict = { 'tid': tid, # tile ID 'dates': dates, # Date list 'localid': parsed['localid'], # sample ID 'imgs': decoded, # image array 'labels': label, # label list 'weights': weight } return sample_dict # simple function def preprocessDirect(tid, record): parsed = tf.io.parse_single_example(record, keys_to_features_direct) encoded = parsed['image_raw_ldseries'] labels_encoded = parsed['labels'] decoded = tf.io.decode_raw(encoded, tf.uint16) label = tf.io.decode_raw(labels_encoded, tf.int8) dates = tf.io.decode_raw(parsed['dates'], tf.int64) weight = tf.io.decode_raw(parsed['weights'], tf.float32) decoded = tf.reshape(decoded,[-1,4,42,42]) return tid, dates, parsed['localid'], decoded, label, weight t1 = parseRecordDirect('filename here') dataset = t1.map(preprocessDirect, num_parallel_calls=tf.data.experimental.AUTOTUNE) # </code></pre> <p><strong>Class Definition:</strong></p> <ul> <li>0: clear</li> <li>1: opaque cloud</li> <li>2: thin cloud</li> <li>3: haze</li> <li>4: cloud shadow</li> <li>5: snow</li> </ul> <p><strong>Dataset Construction:</strong></p> <p>First, we randomly generate 500 points for each tile, and all these points are aligned to the pixel grid center of the subdatasets in 60m resolution (eg. B10) for consistence when comparing with other products. <br>It is because that other cloud detection method may use the cirrus band as features, which is in 60m resolution. </p> <p>Then, the time series image patches of two shapes are cropped with each point as the center.<br>The patches of shape \(42 \times 42\) are cropped from the bands in 10m resolution (B2, B3, B4, B8) and are used to construct this dataset.<br>And the patches of shape \(348 \times 348\) are cropped from the True Colour Image (TCI, details see sentinel-2 user guide) file and are used to interpreting class labels.</p> <p>The samples with a large number of timestamps could be time-consuming in the IO stage, thus the time series patches are divided into different groups with timestamps not exceeding 100 for every group.</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.