This dataset contains the calibration/validation (CalVal) database for the OPERA DSWx-S1 product. The CalVal database is a zip file of an Amazon Web Services S3 bucket containing classification items that enable algorithm calibration and validation of OPERA products. The CalVal database contains a Reference Document that further describes the structure and usage of the database, as well as a Validation Results document. Example notebooks demonstrating how to read the database tables, query for specific items, and download corresponding data files are available through the CalVal GitHub repository here: https://github.com/OPERA-Cal-Val/calval-database

This database was generated by AGENIUM Space in the framework of the CORTEX project (https://esacortexproject.agenium-space.com/) funded by ESA.

The database was created using Sentinel-2 images distributed through the Copernicus open access hub (https://www.copernicus.eu/en, https://scihub.copernicus.eu/) and AIS (Automatic Identification System) data. Sentinel-2 images are all L1C products acquired in Danish sovereign waters in 2019. Danish government made available the AIS (Automatic Identification System) data around Denmark from 2009 until now ( https://www.dma.dk/SikkerhedTilSoes/Sejladsinformation/AIS/Sider/default.aspx ). More specifically, 14 tiles were selected, each of them with a cloud coverage below 10% according to the cloud mask products.

Three DBs are provided. Their description is given in S2-Ships-DB-description.pdf document attached to the DB.

This work is funded by a contract in the framework of the EO SCIENCE FOR SOCIETY PERMANENTLY OPEN CALL FOR PROPOSALS EOEP-5 BLOCK 4 issued by the European Space Agency.

This image dataset: "Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part II", is the second part of the image dataset for train and validate deep learning models.

This part contains only the training and validation images for No Oil and Lookalike.

the dataset comprises Sentinel-1 SAR images in Sigma0, in decibels (db), along with their ground truth. The images are 2048x2048x2, also the ground truth is 2048x2048; all of them are in TIFF format.

The files are organized in the following manner:

• 01_Train_Val_No_Oil_Images: There are 685 images of oil-free Sentinel-1 SAR Sigma0 images in the database.
• 01_Train_Val_No_Oil_mask: There are 685 images in this dataset that represent the ground truth of the Sentinel-1 SAR Sigma0 images in db of the oil-free scenes. In these images, the foreground has a value of 1, and the background has a value of 0. Because the focus of this dataset is on oil spills, the ground truth of oil-free images is assigned a value of 0.
• 01_Train_Val_Lookalike_images: The database contains 685 Sentinel-1 SAR Sigma0 images that correspond to oil-like surfaces, also known as look-alikes.
• 01_Train_Val_Lookalike_mask: It includes 685 images that correspond to the ground truth of the Sentinel-1 SAR Sigma0 images in the database of the look-alike images, where the foreground has a value of 1 and the background has a value of 0. Since the focus was on oil spills, the value of the ground truth of the look-alike images is only 0.

Each corresponding ground truth has the same number as its respective image. For instance, the image of an oil spill has a corresponding number of 0001, as well as its ground truth.

The complete dataset consists of three parts:

Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part I. (10.5281/zenodo.8346860)

Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part II. (10.5281/zenodo.8253899)

Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part III. (10.5281/zenodo.13761290)

The Ecological Research, Assessment and Prediction's Tidal Creeks: Sentinel Habitat Database was developed to support the National Oceanic and Atmospheric Administrations' (NOAA) Hollings Marine Laboratory (HML) Oceans and Human Health Initiative (OHHI). The goal of the program is to provide the scientific information and framework for forecasting environmental and human health risks across estuarine habitats, watersheds, and regions which includes the testing of new technologies developed by other HML OHH groups. This includes a wide range of data from tidal creek systems which are being used as the sentinel habitat for assessing and predicting the impact of coastal development on estuarine systems. Sampling has occurred in South Carolina, Georgia, North Carolina, Alabama, and Mississippi. Historical data from 1994, 1995, 2000 as well as recent data from 2005, 2006, and 2008 are included in the database. A wide range of parameters have been sampled in the estuarine tidal creek systems and their watersheds to obtain data on water quality (e.g., nutrients, pathogens, dissolved oxygen, salinity), sediment quality (e.g., characteristics, chemical contaminants), biological condition (e.g., macrobenthos, fish, organism health) , human exposure (e.g., pathogens), and watershed attributes (e.g., land cover, impervious cover, demographics). Each creek was sampled from its headwaters to its junction with a large open estuary. The creeks represented the range of land use types and human uses that occur in the Southeastern and Gulf regions, including forested, suburban, and urban watersheds. Results of these studies indicate that the amount and type of watershed development are linked to changes in creek environmental quality including increased fecal coliform levels, decreased sediment quality, changes in the kinds and abundances of biota, changes in the abundance of juvenile fish, and decreases in the abundance of shrimp that use these habitats as nurseries. These findings suggest that the shallow estuarine habitats that form the primary link with the land provide early warning of impairment and may be sentinels of ensuing harm from land-based activities. The levels of microbial and chemical contamination in these headwater environments are frequently an order of magnitude greater than that reported for deeper open water environments. Shallow or headwater tidal creeks are, in effect, the "first responders" to impacts of non-point source pollution runoff.

The Sentinel-2 mission is a land monitoring constellation of two satellites that provide high resolution optical imagery and provide continuity for the current SPOT and Landsat missions. The mission provides a global coverage of the Earth's land surface every 5 days, making the data of great use in on-going studies. L1C data are available from June 2015 globally. L2A data are available from November 2016 over Europe region and globally since January 2017.

These data have been created by the Department for Environment, Food and Rural Affairs (Defra) and Joint Nature Conservation Committee (JNCC) in order to cost effectively provide high quality, Analysis Ready Data (ARD) for a wide range of applications. The dataset contains modified Copernicus Sentinel-1 data processed into a normalised radar backscatter product on a linear scale in dB. Products acquired from ESA are Ground-Range Detected (GRD) Interferometric Wide-swath (IW) in the dual VV+VH polarisation (DV) mode, where both VV and VH polarisations are collected. Defra and JNCC data were processed on separate platforms using a common specification to produce complementary outputs up to and including the acquisition date 23/06/2023. Data acquired after that date were processed on a single platform to the same specification.

Sentinel-1 scenes processed before July 2021 have had a strip of data clipped from their northern edge to remove an artefact caused by a deprecated processing method. Details can be found in the lineage statement of the metadata for all affected scenes.

Sentinel-1 is a spaceborne Synthetic Aperture Radar (SAR) imaging system and mission from the European Space Agency and the European Commission. The mission launched and began collecting imagery in 2014. The Sentinel-1 RTC data in this collection is an analysis ready product derived from the Ground Range Detected (GRD) Level-1 products produced by ESA. Radiometric Terrain Correction (RTC) accounts for terrain variations that affect both the position of a given point on the Earth"s surface and the brightness of the radar return. With the ability to see through cloud and smoke cover, and because it does not rely on solar illumination of the Earth"s surface, Sentinel-1 is able to collect useful imagery in most weather conditions, during both day and night. This data is good for wide range of land and maritime applications, from mapping floods, to deforestation, to oil spills, and more. Key Properties Geographic Coverage: Global - approximately 80° North to 80° SouthTemporal Coverage: 10/10/2014 – PresentSpatial Resolution: 10 x 10 meterRevisit Time*: ~6-daysProduct Type: Ground Range Detected (GRD)Product Level: Radiometrically terrain corrected (RTC) and analysis readyFrequency Band: C-bandInstrument Mode: Interferometric Wide Swath Mode (IW)Source Data Coordinate System: Universal Transverse Mercator (UTM) WGS84Service Coordinate System: Web Mercator Auxiliary Sphere WGS84 (EPSG:3857)Analysis: Optimized for analysisBands/Polarizations: BandPolarizationDescriptionPixel Spacing (m)1VV: vertical transmit, vertical receiveTerrain-corrected gamma naught values of signal transmitted with vertical polarization and received with vertical polarization with radiometric terrain correction applied.102VH: vertical transmit, horizontal receiveTerrain-corrected gamma naught values of signal transmitted with vertical polarization and received with horizontal polarization with radiometric terrain correction applied.10 Usage Information and Best Practices Processing TemplatesThis layer includes a number of preconfigured processing templates (raster function templates) to provide on-the-fly data rendering and calculations for visualization and analysis. Each processing template includes labels and descriptions to characterize the intended usage. This may include for visualization, for analysis, or for both visualization and analysis.Below is a list of available processing templates:NameDescriptionSentinel-1 RGB dB with DRARGB color composite of VV,VH,VV-VH in dB scale with a dynamic stretch applied for visualization onlySentinel-1 RGB dBRGB color composite of VV,VH,VV-VH in dB scale for visualization and some numerical analysisSentinel-1 RTC VV PowerVV data in Power scale for numerical analysisSentinel-1 RTC VH PowerVH data in Power scale for numerical analysisSentinel-1 RTC VV AmplitudeVV data in Amplitude scale for numerical analysisSentinel-1 RTC VH AmplitudeVH data in Amplitude scale for numerical analysisSentinel-1 RTC VV dBVV data in dB scale for visualization and some numerical analysisSentinel-1 RTC VV dB with DRAVV data in dB scale with a dynamic stretch applied for visualization onlySentinel-1 RTC VH dBVH data in dB scale for visualization and some numerical analysisSentinel-1 RTC VH dB with DRAVH data in dB scale with a dynamic stretch applied for visualization only VisualizationThe default rendering is False Color (VV, VH, VV-VH) in dB scale for Visualization.There are a number of on-the-fly renderings/processing templates designed specifically for data visualization.By default, the most recent scenes from the Sentinel-1 archive are prioritized and dynamically fused into a single mosaicked image layer. To discover and isolate specific images for visualization in Map Viewer, try using the Image Collection Explorer. AnalysisIn order to leverage the optimization for analysis, the capability must be enabled by you ArcGIS organization administrator. More information on enabling this feature can be found in the ‘Regional data hosting’ section of this help doc.Optimized for analysis means this layer does not have size constraints for analysis and it is recommended for multisource analysis with other layers optimized for analysis. See this group for a complete list of imagery layers optimized for analysis.Using the "None" processing template option as input to analysis provides all bands with raw pixel values and is recommended for many use cases. Otherwise, only processing templates that include a "for analysis" designation should be used as input to analysis.The appropriate scale factors are dynamically applied to the imagery in this layer, providing scientific floating point Surface Reflectance pixel values.Prior to running analysis, users should always provide some form of data selection with either a layer filter (e.g. for a specific date range, cloud cover percent, mission, etc.) or by selecting specific images. To discover and isolate specific images for analysis in Map Viewer, try using the Image Collection Explorer. ApplicationsThe RTC product can be used for a wide range of applications, including:Land cover classification such as forests, wetlands, water bodies, urban areas, and agricultural landChange detection such as deforestation and urban growthNatural hazard monitoring such as floodsOceanography such as oil spill monitoring and ship detection GeneralIf you are new to Sentinel-1 imagery, the Sentinel-1 Explorer provides a good introductory user experience for working with this imagery layer. For more information, see this Quick Start Guide or this Detailed Tutorial.Prior to Dec 23, 2021, the mission included two satellites, Sentinel-1A and Sentinel-1B. On Dec 23, 2021, Sentinel-1B experienced a power anomaly resulting in permanent loss of data transmission. In January 2025, Sentinel-1C replaced Sentinel-1B and returned to the mission to full collection capacity. Data SourceSentinel-1 imagery is credited to the European Space Agency (ESA) and the European Commission. The imagery in this layer is sourced from the Microsoft Planetary Computer Open Data Catalog.

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.

This dataset includes 2.133.324 reflectance water spectra which were manually extracted by visual observation from 30 Sentinel 2 level 1C satellite images. The spectra were extracted from deep water areas with high noise levels and sunglint. The Sentinel 2 images depicted 2 tiles of the same orbit and were collected in 2016 (2 images), 2017 (19 images) and 2018 (9 images). The images contain 13 bands, 3 with 60 m spatial resolution, 4 with 10 m spatial resolution and 6 with 20 m spatial resolution. Before the spectra extraction, the bands with spatial resolution 10 and 20 m were resampled to 60 m and then the images were cropped in order to remove the land and depict optically homogenous sea regions. A figure depicting the location of the Sentinel 2 tiles (white polygons (1,2)) and the cropped tiles (red polygons (3,4)) is included in this folder. A figure depicting example scenes from which spectra were obtained through regions of interest (rois) is included as well. The spectra are stored in .csv files. Each file is named after the name of the Sentinel 2 product which includes sensing and creation date as well the relative orbit number and tile code. The content of each file includes latitude and longitude coordinates (UTM/WGS84 projection) of each spectral signature as well as the reflectance values of the 13 Sentinel 2 bands.This dataset was created for the purpose of the study described in https://www.tandfonline.com/doi/full/10.1080/01431161.2020.1714776

In the Agricultural SandboxNL, three years (2017, 2018, 2019) of Sentinel-1A/B synthetic aperture radar (SAR) scenes are used to generate the Basisregistratie Gewaspercelen (BRP) parcel level database of The Netherlands. The database consists of parcel-level spatially averaged VV, VH and VH/VV backscatter values, corresponding standard deviation, viewing incidence angle, local incidence angle, azimuth angle, pixel count and data quality flag for each parcel. Each parcel can be identified with an unique Object ID. The database uses around 1000 Sentinel-1 images to provide time series for approximately 770,000 crop parcels over the Netherlands annually. The database can be queried for Sentinel-1 system parameter (e.g. relative orbit) or user application-specific parameters (e.g. crop type, spatial extent, time period) for individual parcel level assessment or aggregated at administrative boundaries.

Sentinel-1 SAR-image mosaics S1sar are derived from data provided by Sentinel-1A and -1B-satellites. The value of pixel is statistic (mean, maximum, minimum or standard deviation) of radar gamma0 backscatter of VV- or VH-polarizations in decibels (dB). Following mosaics are produced: s1m_grd_vv_mean: The mean gamma0 backscatter in dB of VV-polarized data of mosaicking period. s1m_grd_vv_max: The maximum gamma0 backscatter in dB of VV-polarized data of mosaicking period. s1m_grd_vv_min: The minimum gamma0 backscatter in dB of VV-polarized data of mosaicking period. s1m_grd_vv_std: The standard deviation of gamma0 backscatter in dB of VV-polarized data of mosaicking period. s1m_grd_vh_mean: The mean gamma0 backscatter in dB of VH-polarized data of mosaicking period. s1m_grd_vh_max: The maximum gamma0 backscatter in dB of VH-polarized data of mosaicking period. s1m_grd_vh_min: The minimum gamma0 backscatter in dB of VH-polarized data of mosaicking period. s1m_grd_vh_std: The standard deviation of gamma0 backscatter in dB of VH-polarized data of mosaicking period. Images with Product type “GRD” and Sensor mode “IW” of descending orbit are used in mosaicking process. The mosaics are in TM35Fin coordinate system (EPSG 3067) with 20 m pixel size. Mosaicking period is 11 days, so that the middle day of the mosaic is the 6th, 16th or 26th day of the month, and they are made throughout the year. The file format of mosaic is Cloud-Optimized-Geotiff. The gamma0 backscatter has been scaled with multiplier 100 and stored as 16-bit signed integer but since end of May 2019 scaling has been discontinued so the gamma0 backscatter is saved as float numbers. Mosaics are produced using ESA SNAP-software, including steps Apply-Orbit-File, Remove-GRD-Border-Noise, ThermalNoiseRemoval, Calibration, SliceAssembly, Multilook, Terrain-Flattening, Terrain-Correction and LinearToFromdB. The mosaics as available from the interfaces of NSDC which are: WMS (Geoserver): https://data.nsdc.fmi.fi/geoserver/wms WCS (Geoserver): https://data.nsdc.fmi.fi/geoserver/wcs S3-bucket: Mosaics are also available using URL, like http://pta.data.lit.fmi.fi/sen1/s1m_grd_pol_stat/s1m_grd_startdate-enddate_stat_pol_R20m.tif pol: vv or vh stat: mean, max, min or std startdate: the start date of mosaic, the 1st, 11th or 21st day of the month enddate: the end date of the mosaic, the 11th, 21st, or 31th (or 21+10th day which can be 1st or 2nd etc depending on month) The start and end dates must cover period of 11 days, e.g. 20190401-29190411 or 20180621-20180701. Viewing service FMI Sentinel catalog (https://pta.fmi.fi/) has mosaics as well as individual images. These S1sar-mosaics are produced by Finnish Meteorological Institute (FMI), and they were developed as part of sub program “Distribution and Processing of Satellite Imagery” of "Geospatial Platform of Finnish Public Administration"-program (2017-2019). The license for FMI's open datasets is Creative Commons Attribution 4.0 International. Sentinel-1 SAR-kuvamosaiikit S1sar tehdään Sentinel-1A ja -1B satelliittien synteettisen apertuurin tutkan tuottamista kuvista. Mosaiikin pikselin arvo on tutkan tuottaman VV- tai VH-polarisaation gamma0-takaisinsironnan keskiarvo, minimi, maksimi tai hajonta desibeleinä (dB). Seuraavat mosaiikit tuotetaan kultakin mosaikointiajanjaksolta: s1m_grd_vv_mean: VV-polarisoituneen gamma0-takaisinsironnan keskiarvo mosaikointiajanjaksolta desibeleinä (dB). s1m_grd_vv_max: VV-polarisoituneen gamma0-takaisinsironnan maksimiarvo mosaikointiajanjaksolta desibeleinä (dB). s1m_grd_vv_min: VV-polarisoituneen gamma0-takaisinsironnan minimiarvo mosaikointiajanjaksolta desibeleinä (dB). s1m_grd_vv_std: VV-polarisoituneen gamma0-takaisinsironnan hajonta mosaikointiajanjaksolta desibeleinä (dB). s1m_grd_vh_mean: VH-polarisoituneen gamma0-takaisinsironnan keskiarvo mosaikointiajanjaksolta desibeleinä (dB). s1m_grd_vh_max: VH-polarisoituneen gamma0-takaisinsironnan maksimiarvo mosaikointiajanjaksolta desibeleinä (dB). s1m_grd_vh_min: VH-polarisoituneen gamma0-takaisinsironnan miminiarvo mosaikointiajanjaksolta desibeleinä (dB). s1m_grd_vh_std: VH-polarisoituneen gamma0-takaisinsironnan hajonta mosaikointiajanjaksolta desibeleinä (dB). Mosaikoinnissa käytetyt kuvat ovat laskevan radan "GRD"-tuotteen ja "IW"-sensorimoodin kuvia. Mosaiikit tuotetaan TM35Fin-koordinaatistossa pikselikoon ollessa 20 metriä läpi vuoden. Mosaikointiajanjakso on 1 päivää, siten että mosaiikin keskimmäisin päivä on kuukauden 6., 16. tai 26. päivä. Tiedostoformaatti on Cloud-Optimized-Geotiff. Gamma0-takaisinsironta on skaalattu kertomalla kertoimella 100 ja tallennettu käyttäen 16-bit signed integer tallennusmuotoa, paitsi toukokuun lopun 2019 jälkeen jolloin skaalauksesta on luovuttu ja takaisinsironta on tallennettu reaalilukuina. Mosaiikkien tuottamiseen on käytetty Euroopan Avaruusjärjestön SNAP-ohjelmistoa ja sen funktioita Apply-Orbit-File, Remove-GRD-Border-Noise, ThermalNoiseRemoval, Calibration, SliceAssembly, Multilook, Terrain-Flattening, Terrain-Correction ja LinearToFromdB. Mosaiikit on saatavilla Kansallisen satelliittidatakeskuksen käyttöliittymistä jotka ovat WMS (Geoserver): https://data.nsdc.fmi.fi/geoserver/wms WCS (Geoserver): https://data.nsdc.fmi.fi/geoserver/wcs S3-bucket: Mosaiikit on myös saatavissa käyttäen URL-osoitetta kuten http://pta.data.lit.fmi.fi/sen1/s1m_grd_pol_stat/s1m_grd_startdate-enddate_stat_pol_R20m.tif jossa pol: vv tai vh stat: mean, max, min tai std startdate: mosaiikin ajanjakson aloituspäivä, kuukauden 1., 11. tai 21. päivä enddate: mosaiikin ajanjakson viimeinen päivä, kuukauden 11., 21. tai 31. (tai seuraavan kuukauden alku riippuen montako päivää kuukaudessa on) päivä Aloitus- ja viimeinen päivä kattaa 11 päivää siten että keskimmäisin päivä on 6., 16. tai 26. päivä, esimerkiksi 20190401-29190411 tai 20180621-20180701. Katselupalvelussa FMI Sentinel catalog (https://pta.fmi.fi/) on nähtävillä sekä S1sar-mosaiikit että yksittäiset prosessoidut kuvat. Nämä Sentinel-1 kuvamosaiikit tuottaa Ilmatieteen laitos, ja ne on kehitetty osana Paikkatietoalusta-hankkeen (2017-2019) Satelliittidatan jakelu ja prosessointi-osahanketta. IL:n avoimien aineistojen käyttäjälisenssi on Creative Commons Attribution 4.0 International.

This database comprises 26 Sentinel-2 images, totaling 258 ship exemplars. The images are generated using vessel detection reports provided by analysts from Collecte Localisation Satellites (CLS). Each Sentinel-2 image is accompanied by its land mask and a CSV file that includes the position of detected vessels along with their characteristics, such as length and heading.

This image dataset: "Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part III", is the third part of the image dataset for train and validate deep learning models for oil spill detection and segmentation.

This part contains the test images.

The dataset comprises Sentinel-1 SAR images in Sigma0, in decibels (db), along with their ground truth. The images are 2048x2048x2, also the ground truth is 2048x2048; all of them are in TIFF format.

The files are organized in the following manner:

• Images: Sentinel-1 SAR images in Sigma0 in decibels.
  • Lookalike: There are 150 images corresponding to look-alike surfaces
  • No oil: There are 150 oil free images
  • Oil: There are 150 oil spill images
• Mask: Gorund truth masks images for each Sentinel-1 SAR images
  • Lookalike: There are 150 images corresponding to the ground truth for look-alike images
  • No oil: There are 150 images to corresponds oil free ground truth images
  • Oil: There are 150 images for the ground truth for oil spill images

Each corresponding ground truth has the same number as its respective image. For instance, the image of an oil spill has a corresponding number of 0001, as well as its ground truth.

The complete dataset consists of three parts:

Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part I. (10.5281/zenodo.8346860)

Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part II. (10.5281/zenodo.8253899)

Sentinel-1 SAR Oil spill image dataset for train, validate, and test deep learning models. Part III. (10.5281/zenodo.13761290)

For more R code examples please also refer to the GSIF tutorial at http://gsif.isric.org. (PDF)

Independent predictive factors of sentinel lymph node metastasis according to the multiple logistic regression analysis (n = 608*).

The freeze maps were carried out over 500 m x 500 m grids (maps could be provided at a plot scale). For a given site, all acquired Sentinel-1 radar images were processed (about 15 images per month). An approach that relies on change detection in the high-resolution Sentinel-1 C-band SAR backscattered coefficients was applied to determine surface states as either frozen or unfrozen. Freeze detection is carried out for two distinct land cover classes: cereals and grasslands (LC1), vineyards and orchards (LC2). Products are in vector format (shapefile): (FREEZDETECT_{S2 Tile}_{Date}T{hour}{minute}{second}). ID_PARCEL field: plot Id. CODE_CULTU field: culture code according to the RPG 2019. CODE_GROUP field: group culture code according to the RPG 2019. PARC_TYPE field: land cover classes according to our detection algorithm (LC1 and LC2). MREFSIGMA field: reference backscattering coefficient in dB (unfrozen conditions). MEANSIGMA field: mean backscattering coefficient for the given plot at the S1 acquisition date in dB. MEANTEMP field: temperature in ⁰C from ERA5-LAND. FROZ_TYPE field: the freeze state: 0 = No detected freezing; 1 = Mild-to-Moderate freezing; 2 = Severe freezing. For LC1, if Delta defined by the difference (MREFSIGMA – MEANSIGMA) is < 3.5 dB -> unfrozen, if 3.5 dB < Delta < 4.5 dB -> mild-to-moderately frozen, if Delta >4.5 dB -> severely frozen. For LC2, if Delta is < 2.5 dB -> unfrozen, if 2.5 dB < Delta < 3.5 dB -> mild-to-moderately frozen, if Delta >3.5 dB -> severely frozen.

To solve the high-frequency sample needs of time series wetland classification, we developed a method for automatically producing global wetland samples based on 13 global and regional wetland-related datasets and millions of images from Landsat 8 OLI, MODIS, Sentinel-1 SAR GRD, and Sentinel-2 MSI sensors. Considering the consistency of types and the separability of spectra, we summarized all classification systems into three types: wetland, water body, and non-wetland.Samples are randomly selected based on the equal-area stratified sampling scheme based on the existence probability of wetlands. In order to ensure sufficient samples, we proposed global sample size of 500,000. According to the global potential wetland distribution data set, the sample size of each grid was allocated, and samples were randomly selected. Based on 13 auxiliary data sets, we first determined the sample type according to the order of water body and wetland and assigned the "non-wetland" attribute to the type of neither water body nor wetland. The 13 auxiliary data sets include GlobeLand30 (Chen et al., 2014), FROM-GLC (Yu et al., 2013), GlobCover (Arino et al., 2010), GLC_FCS30_2020 (Liu et al., 2020), Joint Research Centre Global Surface Water Survey and Mapping map (Pekel et al., 2016), Global Reservoir and Dam Database (GRanD) (Lehner et al., 2011), Global Mangrove Watch (GMW) (Bunting et al., 2018), Global Lakes and Wetlands Database (GLWD) (Lehner et al., 2004), Murray Global Intertidal Change (MGIC) (Murray et al., 2019), CAS_Wetlands (Mao et al., 2020), CA_wetlands (Wulder et al., 2018), National Land Cover Database (NLCD) (Yang et al., 2018), Global Potential Wetland Distribution Dataset (GPWD) (Hu et al., 2017).We also included 139027 Landsat 8 OLI images, 21160 MOD09A1 images, 296479 Sentinel-1 SAR images, and 4553453 Sentinel-2 MSI images globally from January 1 to December 31, 2020. We extracted minimum, maximum, mean, and median information for each band and NDVI, NDWI, MNDWI, and LSWI indexes in four sensors of global wetland samples. In order to remove this part of the noise, this study kept the water, wetland, and non-wetland samples within one standard deviation of the annual mean of each spectral band as the sample's secondary screening conditions to ensure the accuracy of samples.The number of wetland samples determined by each sensor is different. Landsat 8 has a total of 202,111 samples, including 13,176 water bodies, 54,229 wetland samples, and 134,706 non-wetland samples; MODIS has a total of 190,898 samples, including 13,436 water body samples, 50,400 wetland samples, and 127,062 non-wetland samples ; Sentinel- has a total of 185,943 samples, including 10,885 water samples, 54,224 wetland samples, and 120,834 non-wetland samples; Sentinel-2 has a total of 185,484 samples, including 11,225 water samples, 52,142 wetland samples, and 122,117 non-wetland samples.They are stored separately in four shapefiles.

This dataset contains Level-3 Dynamic OPERA surface water extent product version 1. The data are validated surface water extent observations beginning April 2023. Known issues and caveats on usage are described under Documentation. The input dataset for generating each product is the Harmonized Landsat-8 and Sentinel-2A/B/C (HLS) product version 2.0. HLS products provide surface reflectance (SR) data from the Operational Land Imager (OLI) aboard the Landsat 8 satellite and the MultiSpectral Instrument (MSI) aboard the Sentinel-2A/B/C satellite. The surface water extent products are distributed over projected map coordinates using the Universal Transverse Mercator (UTM) projection. Each UTM tile covers an area of 109.8 km × 109.8 km. This area is divided into 3,660 rows and 3,660 columns at 30-m pixel spacing. Each product is distributed as a set of 10 GeoTIFF (Geographic Tagged Image File Format) files including water classification, associated confidence, land cover classification, terrain shadow layer, cloud/cloud-shadow classification, Digital elevation model (DEM), and Diagnostic layer.

The digital elevation model (DEM) provided as a layer of the DSWx-HLS product (band 10) was generated using the Copernicus DEM 30-m and Copernicus DEM 90-m models provided by the European Space Agency. The Copernicus DEM 30-m and Copernicus DEM 90-m were produced using Copernicus WorldDEM-30 © DLR e.V. 2010-2014 and © Airbus Defence and Space GmbH 2014-2018 provided under COPERNICUS by the European Union and ESA; all rights reserved. The organizations in charge of the OPERA project, the Copernicus programme, and Airbus Defence and Space GmbH by law or by delegation do not assume any legal responsibility or liability, whether express or implied, arising from the use of this DEM.

The OPERA DSWx-HLS product contains modified Copernicus Sentinel data (2023-2025).

To access the calibration/validation database for OPERA Dynamic Surface Water Extent Products, please contact podaac@podaac.jpl.nasa.gov

Proportion and positivity rate of sentinel lymph node biopsy according to Breslow categories (n = 1,073).

Dataset name

AUGMENTED SEN1-2

Year of publication

2025

Author

Shamba Chowdhury Ankana Ghosh Shreyashi Ghosh

License

CC-BY The dataset contains Copernicus data (2024). Terms and conditions apply: https://scihub.copernicus.eu/twiki/pub/SciHubWebPortal/TermsConditions/TC_Sentinel_Data_31072014.pdf

Associated publication

TBA

Links

Dataset: https://www.kaggle.com/datasets/shambac/augmented-sentinel-1-2 Paper: TBA

Dataset structure

Top level: spring, summer, fall, winter - folders corresponding to four different random ROI distributions and to the four meteorological seasons Second level: s1_i, s2_i - folders corresponding to the scenes from which the patches were cut, with s1 indicating Sentinel-1 SAR images and s2 indicating Sentinel-2 optical images

Dataset size

No. of files: 616,148 Storage: 53,699 MB

Description

The Augmented SEN1-2 dataset contains 308,074 pairs of corresponding SAR and optical image patches acquired by the Sentinel-1 and Sentinel-2 satellites, respectively. The patches are distributed across the land masses of the Earth and spread over all four meteorological seasons. This is reflected by the dataset structure. For the SAR patches 8-bit single-channel images representing the sigma nought backscatter value in dB scale are provided. For the optical patches 8-bit color images representing the bands 4, 3, and 2 are used. Along with the patches, this dataset has been augmented with heatzone data of the locations to further aid in research. If you use the dataset, please cite the associated publication mentioned above.