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. L2A data are available from November 2016 over Europe region and globally since January 2017. L2A data provide Bottom of the atmosphere (BOA) reflectance.

SpatioTemporal Asset Catalog (STAC) Item - S2C_MSIL2A_20250922T001621_N0511_R059_T60WWV_20250922T012012 in sentinel-2-l2a

SpatioTemporal Asset Catalog (STAC) Item - S2C_MSIL2A_20250922T001621_N0511_R059_T60WWE_20250922T012012 in sentinel-2-l2a

Sentinel-2 L2A 120m mosaic is a derived product, which contains best pixel values for 10-daily periods, modelled by removing the cloudy pixels and then performing interpolation among remaining values. As clouds can be missed and as there are some parts of the world which have lengthy cloudy periods, clouds might be remaining in some parts. The actual modelling script is available here.

After 2022-01-25, Sentinel-2 scenes with PROCESSING_BASELINE '04.00' or above have their DN (value) range shifted by 1000. The HARMONIZED collection shifts data in newer scenes to be in the same range as in older scenes. Sentinel-2 is a wide-swath, high-resolution, multi-spectral imaging mission supporting Copernicus Land Monitoring studies, including the …

SpatioTemporal Asset Catalog (STAC) Item - S2C_MSIL2A_20250922T001621_N0511_R059_T60WWD_20250922T012012 in sentinel-2-l2a

This collection contains Sentinel-2 Level 2A surface reflectances, which are computed for the country of Germany using the time-series based MAJA processor. During the Level 2A processing, the data are corrected for atmospheric effects and clouds and their shadows are detected. The MAJA L2A product is available online for the last 12 months. Further data are kept in the archive and are available upon request. Please see https://logiciels.cnes.fr/en/content/maja for additional information on the MAJA product. The MAJA product offers an alternative to the official ESA L2A product and has been processed with consideration of the characteristics of the Sentinel-2 mission (fast collection of time series, constant sensor perspective, and global coverage). Assumptions about the temporal constancy of the ground cover are taken into account for a robust detection of clouds and a more flexible determination of aerosol properties. As a result, an improved determination of the reflectance of sunlight at the earth's surface (pixel values of the multispectral image) is derived. Further Sentinel-2 Level 2A data computed using MAJA are available on the following website: https://theia.cnes.fr

SpatioTemporal Asset Catalog (STAC) Item - S2C_MSIL2A_20250922T001621_N0511_R059_T60WVU_20250922T012012 in sentinel-2-l2a

xS2Wakes: A dataset for xAI of Wakes in S-2 (L2A).

Summary

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_wake_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.

Importance and Relevance to Remote Sensing Community

Multifaceted Applications of Wake Detection

Ship wake detection serves as a cornerstone in a multitude of domains that are critical to both human and environmental well-being:

Navigational Safety: 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.

Environmental Monitoring: 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.

Maritime Surveillance: 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.

Specifications

• Data Source: Sentinel-2 L2A
• Region of Interest: Danish fjords
• Classes: Wake, No-Wake
• Number of Samples:
  • Wake: 123
  • No-Wake: 150
• Spectral Bands: B2 (Blue), B3 (Green), B4 (Red), B8 (NIR)
• Post-Processing: CLAHE (Clip Limit = 0.12, Tile Size = 16x16)
• Average Wake Chip Size: 390x351 pixels
• Average No-Wake Chip Size: 380x390 pixels

Wake Detection and Analysis

Traditional Methods and Their Limitations

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.

Role of xAI (Explainable AI) in Wake Identification

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.

Spectral Bands Selected

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." Remote Sensing of Environment 258 (2021): 112375.]

Understanding Optical vs. SAR Imaging Modalities

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.

Contrast Enhancement

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.

Environment and Clutter Assessment

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.

SpatioTemporal Asset Catalog (STAC) Item - S2C_MSIL2A_20250922T001621_N0511_R059_T60WVV_20250922T012012 in sentinel-2-l2a

This layer displays a global map of land use/land cover (LULC) derived from ESA Sentinel-2 imagery at 10m resolution. Each year is generated with Impact Observatory’s deep learning AI land classification model, trained using billions of human-labeled image pixels from the National Geographic Society. The global maps are produced by applying this model to the Sentinel-2 Level-2A image collection on Microsoft’s Planetary Computer, processing over 400,000 Earth observations per year.The algorithm generates LULC predictions for nine classes, described in detail below. The year 2017 has a land cover class assigned for every pixel, but its class is based upon fewer images than the other years. The years 2018-2023 are based upon a more complete set of imagery. For this reason, the year 2017 may have less accurate land cover class assignments than the years 2018-2023.Variable mapped: Land use/land cover in 2017, 2018, 2019, 2020, 2021, 2022, 2023Source Data Coordinate System: Universal Transverse Mercator (UTM) WGS84Service Coordinate System: Web Mercator Auxiliary Sphere WGS84 (EPSG:3857)Extent: GlobalSource imagery: Sentinel-2 L2ACell Size: 10-metersType: ThematicAttribution: Esri, Impact ObservatoryWhat can you do with this layer?Global land use/land cover maps provide information on conservation planning, food security, and hydrologic modeling, among other things. This dataset can be used to visualize land use/land cover anywhere on Earth. This layer can also be used in analyses that require land use/land cover input. For example, the Zonal toolset allows a user to understand the composition of a specified area by reporting the total estimates for each of the classes. NOTE: Land use focus does not provide the spatial detail of a land cover map. As such, for the built area classification, yards, parks, and groves will appear as built area rather than trees or rangeland classes.Class definitionsValueNameDescription1WaterAreas where water was predominantly present throughout the year; may not cover areas with sporadic or ephemeral water; contains little to no sparse vegetation, no rock outcrop nor built up features like docks; examples: rivers, ponds, lakes, oceans, flooded salt plains.2TreesAny significant clustering of tall (~15 feet or higher) dense vegetation, typically with a closed or dense canopy; examples: wooded vegetation, clusters of dense tall vegetation within savannas, plantations, swamp or mangroves (dense/tall vegetation with ephemeral water or canopy too thick to detect water underneath).4Flooded vegetationAreas of any type of vegetation with obvious intermixing of water throughout a majority of the year; seasonally flooded area that is a mix of grass/shrub/trees/bare ground; examples: flooded mangroves, emergent vegetation, rice paddies and other heavily irrigated and inundated agriculture.5CropsHuman planted/plotted cereals, grasses, and crops not at tree height; examples: corn, wheat, soy, fallow plots of structured land.7Built AreaHuman made structures; major road and rail networks; large homogenous impervious surfaces including parking structures, office buildings and residential housing; examples: houses, dense villages / towns / cities, paved roads, asphalt.8Bare groundAreas of rock or soil with very sparse to no vegetation for the entire year; large areas of sand and deserts with no to little vegetation; examples: exposed rock or soil, desert and sand dunes, dry salt flats/pans, dried lake beds, mines.9Snow/IceLarge homogenous areas of permanent snow or ice, typically only in mountain areas or highest latitudes; examples: glaciers, permanent snowpack, snow fields.10CloudsNo land cover information due to persistent cloud cover.11RangelandOpen areas covered in homogenous grasses with little to no taller vegetation; wild cereals and grasses with no obvious human plotting (i.e., not a plotted field); examples: natural meadows and fields with sparse to no tree cover, open savanna with few to no trees, parks/golf courses/lawns, pastures. Mix of small clusters of plants or single plants dispersed on a landscape that shows exposed soil or rock; scrub-filled clearings within dense forests that are clearly not taller than trees; examples: moderate to sparse cover of bushes, shrubs and tufts of grass, savannas with very sparse grasses, trees or other plants.Classification ProcessThese maps include Version 003 of the global Sentinel-2 land use/land cover data product. It is produced by a deep learning model trained using over five billion hand-labeled Sentinel-2 pixels, sampled from over 20,000 sites distributed across all major biomes of the world.The underlying deep learning model uses 6-bands of Sentinel-2 L2A surface reflectance data: visible blue, green, red, near infrared, and two shortwave infrared bands. To create the final map, the model is run on multiple dates of imagery throughout the year, and the outputs are composited into a final representative map for each year.The input Sentinel-2 L2A data was accessed via Microsoft’s Planetary Computer and scaled using Microsoft Azure Batch.CitationKarra, Kontgis, et al. “Global land use/land cover with Sentinel-2 and deep learning.” IGARSS 2021-2021 IEEE International Geoscience and Remote Sensing Symposium. IEEE, 2021.AcknowledgementsTraining data for this project makes use of the National Geographic Society Dynamic World training dataset, produced for the Dynamic World Project by National Geographic Society in partnership with Google and the World Resources Institute.

SpatioTemporal Asset Catalog (STAC) Item - S2C_MSIL2A_20250922T001621_N0511_R059_T60WWU_20250922T012012 in sentinel-2-l2a

SpatioTemporal Asset Catalog (STAC) Item - 20NLH_2024-04-01_2024-08-01 in sentinel2-temporal-mosaics

The Sentinel-2 Level-2A Collection 1 product provides orthorectified Surface Reflectance (Bottom-Of-Atmosphere: BOA), with sub-pixel multispectral and multitemporal registration accuracy. Scene Classification (including Clouds and Cloud Shadows), AOT (Aerosol Optical Thickness) and WV (Water Vapour) maps are included in the product.

Within the Copernicus program, the European Space Agency (ESA) makes satellite data from the Sentinel missions available free of charge. The LGV prepares the data quarterly for easier use. Originally, the satellite data can be obtained via the national platform CODE-DE (Copernicus Data and Exploitation Platform – Germany). Data basis: - Sentinel-2 L2A: Multispectral, atmospherically corrected data - Georeferenced mosaic - Tile count: 25 - Tile size: 8 km x 8 km - Tile selection: recency and degree of cloud cover - Color representation: RGB, CIR, NDVI - Ground resolution: 10m - Color depth: 8 bit RGB (Red Green Blue): The band combination of red (B4), green (B3) and blue (B2) emulates human color perception. Healthy vegetation is shown in green, urban areas are shown in white / gray and water areas are shown in blue, depending on the turbidity. CIR (Color Infrared): The band combination of near infrared (B8), red (B4) and green (B3) highlights vegetation. Due to the chlorophyll content of the plants, this reflects particularly strongly in the near infrared range and is displayed reddish. Urban areas appear cyan-blue / gray and water areas dark blue. NDVI (Normalized Difference Vegetation Index): The NDVI is a frequently used index, which is used to assess vegetation. It is calculated from the near infrared (B8) and red (B4) bands: NDVI = (NIR-Red)/(NIR+Red) [© Contains modified Copernicus Sentinel data [2018-2021], processed on CODE-DE]

SpatioTemporal Asset Catalog (STAC) Item - S2C_MSIL2A_20250922T001621_N0511_R059_T60WWC_20250922T012012 in sentinel-2-l2a

SpatioTemporal Asset Catalog (STAC) Item - SENTINEL2A_20250628-110921-945_L2A_T30TWP_C in sentinel2-l2a-theia

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.

For each acquisition, the data was obtained at 2 processing levels: 1C
(from PEPS, CNES' mirror of Sentinel data) and 2A (from Theia's
catalogue), the latter having been produced by the MAJA processor.

For each acquisition, 100,000 pixels where sampled. Only non-saturated
pixels were selected, regardless of their cloud or shadow status. Pixel
positions were selected on the 20m resolution grid. For each 20m pixel
position, the following information was recorded:
- whether the pixel was detected as a cloud or a shadow (without
distinction of these 2 states),
- the reflectance in the 20m bands for levels 1C and 2A,
- the reflectance of the 4 corresponding pixels of each of the 10m
resolution bands for levels 1C and 2A,
- the reflectance at the 20m pixel position of the 60m resolution bands
after bicubic resampling for level 1C.
- the solar and viewing angles for each pixel.

For each sampled scene, a CSV file with the name TILE_DATE_samples.csv (for example T05KRA_20171124_samples.csv) is provided.

Each row in the file corresponds to a pixel. The columns provide the following variables:
- An integer used as unique identifier of the pixel in the file.
- The tile name in TIJXYZ format.
- The date in YYYMMDD format.
- The coverage: the percentage of the tile covered by the relative orbit of the acquisition.
- The x and y integer coordinates of the 20m. resolution pixel in the array.
- 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.
- 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.
- The reflectances of the L1C 60m resolution bands resampled to the 20m grid. The 3 columns are named L1C_B01, L1C_B09, L1C_B10.
- 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.
- The solar Zenith and Azimuth angles: sun_zen, sun_az:
- 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.
- 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.

The list of column names is the following:
- tile
- date
- coverage
- x
- y
- L1C_B02_0
- L1C_B02_1
- L1C_B02_2
- L1C_B02_3
- L1C_B03_0
- L1C_B03_1
- L1C_B03_2
- L1C_B03_3
- L1C_B04_0
- L1C_B04_1
- L1C_B04_2
- L1C_B04_3
- L1C_B08_0
- L1C_B08_1
- L1C_B08_2
- L1C_B08_3
- L1C_B05
- L1C_B06
- L1C_B07
- L1C_B8A
- L1C_B11
- L1C_B12
- L1C_B01
- L1C_B09
- L1C_B10
- L2A_B2_0
- L2A_B2_1
- L2A_B2_2
- L2A_B2_3
- L2A_B3_0
- L2A_B3_1
- L2A_B3_2
- L2A_B3_3
- L2A_B4_0
- L2A_B4_1
- L2A_B4_2
- L2A_B4_3
- L2A_B8_0
- L2A_B8_1
- L2A_B8_2
- L2A_B8_3
- L2A_B5
- L2A_B6
- L2A_B7
- L2A_B8A
- L2A_B11
- L2A_B12
- sun_zen
- sun_az
- inc_even_zen
- inc_odd_zen
- inc_even_az
- inc_odd_az
- L1C_B02_60
- L1C_B03_60
- L1C_B04_60
- L1C_B08_60
- L1C_B05_60
- L1C_B06_60
- L1C_B07_60
- L1C_B8A_60
- L1C_B11_60
- L1C_B12_60
- L2A_B2_60
- L2A_B3_60
- L2A_B4_60
- L2A_B8_60
- L2A_B5_60
- L2A_B6_60
- L2A_B7_60
- L2A_B8A_60
- L2A_B11_60
- L2A_B12_60
- CLM

The list of available CSV files is the following:

- T05KRA_20171124_samples.csv
- T05KRA_20180329_samples.csv
- T05KRA_20180523_samples.csv
- T05KRA_20190408_samples.csv
- T05KRA_20191129_samples.csv
- T05KRA_20200402_samples.csv
- T05KRA_20200601_samples.csv
- T05KRA_20200805_samples.csv
- T05KRA_20201203_samples.csv
- T06KTF_20160324_samples.csv
- T06KTF_20171010_samples.csv
- T06KTF_20180627_samples.csv
- T06KTF_20181224_samples.csv
- T06KTF_20200616_samples.csv
- T06KTF_20200924_samples.csv
- T11SPC_20180918_samples.csv
- T11SPC_20180928_samples.csv
- T11SPC_20181013_samples.csv
- T11SPC_20181112_samples.csv
- T14SPF_20170321_samples.csv
- T14SQE_20170308_samples.csv
- T14SQE_20190402_samples.csv
- T14SQF_20180405_samples.csv
- T14SQF_20190420_samples.csv
- T18TUR_20180509_samples.csv
- T18TVS_20191026_samples.csv
- T18TXS_20171018_samples.csv
- T18UVU_20190703_samples.csv
- T18UVU_20190827_samples.csv
- T18UWU_20190327_samples.csv
- T18UXU_20200210_samples.csv
- T18UXV_20191013_samples.csv
- T18UYV_20191217_samples.csv
- T19LHH_20200925_samples.csv
- T19LHJ_20190723_samples.csv
- T19LHJ_20200218_samples.csv
- T19TCL_20170811_samples.csv
- T19TCL_20201103_samples.csv
- T20LKP_20171001_samples.csv
- T20LKP_20191125_samples.csv
- T20LLQ_20180901_samples.csv
- T20NNP_20190807_samples.csv
- T20PPC_20191103_samples.csv
- T21NYG_20191002_samples.csv
- T21NZG_20180714_samples.csv
- T22KHA_20191027_samples.csv
- T22MGB_20201216_samples.csv
- T22MHB_20200803_samples.csv
- T22NCH_20181009_samples.csv
- T23KKR_20160808_samples.csv
- T23MKS_20200830_samples.csv
- T23MLS_20191219_samples.csv
- T23MLT_20190319_samples.csv
- T23MLT_20191114_samples.csv
- T23MLT_20200313_samples.csv
- T24MWU_20190916_samples.csv
- T24MWU_20201214_samples.csv
- T24MYT_20160918_samples.csv
- T24MYT_20200425_samples.csv
- T25LBL_20161214_samples.csv
- T25LBL_20180801_samples.csv
- T25LBL_20181209_samples.csv
- T25MBM_20171214_samples.csv
- T25MBN_20200113_samples.csv
- T25MBP_20180607_samples.csv
- T28PCB_20181129_samples.csv
- T28PDU_20181101_samples.csv
- T28PEV_20170405_samples.csv
- T28PGA_20170909_samples.csv
- T28PHC_20170323_samples.csv
- T28QCD_20160513_samples.csv
- T28QFD_20171002_samples.csv
- T28QFD_20180729_samples.csv
- T29SNC_20180927_samples.csv
- T29SPR_20201222_samples.csv
- T30PUT_20200522_samples.csv
- T30QZE_20181213_samples.csv
- T30QZE_20190924_samples.csv
- T30TTM_20181128_samples.csv
- T30TYM_20200126_samples.csv
- T31PGS_20191023_samples.csv
- T31QBU_20170107_samples.csv
- T31QCU_20170308_samples.csv
- T31QEU_20180330_samples.csv
- T31SDV_20171126_samples.csv
- T31SFA_20180907_samples.csv
- T31TDL_20190903_samples.csv
- T31UFS_20170814_samples.csv
- T31UGT_20171229_samples.csv
- T32PLS_20200919_samples.csv
- T32ULD_20161224_samples.csv
- T32ULE_20181124_samples.csv
- T32UMD_20190224_samples.csv
- T33KWP_20190729_samples.csv
- T33TUJ_20201007_samples.csv
- T36SXB_20191127_samples.csv
- T36SYB_20180317_samples.csv
- T36SYB_20200902_samples.csv
- T36SYB_20200907_samples.csv
- T36SYC_20180307_samples.csv
- T36SYC_20180327_samples.csv
- T36SYD_20170804_samples.csv
- T36SYD_20190111_samples.csv
- T37SBT_20190126_samples.csv
- T37SBU_20161122_samples.csv
- T37SBU_20201022_samples.csv
- T38KMB_20170817_samples.csv
- T38KNU_20200228_samples.csv
- T38KPE_20191026_samples.csv
- T38TNL_20180328_samples.csv
- T39KTU_20201126_samples.csv
- T40KCB_20160805_samples.csv
- T40KCB_20170323_samples.csv
- T40KCB_20170820_samples.csv
- T40KCB_20171123_samples.csv
- T40KCB_20200317_samples.csv
- T40KCB_20200829_samples.csv
- T42FVL_20180319_samples.csv
- T42FVL_20180729_samples.csv
- T42FVL_20201208_samples.csv
- T42FWL_20170405_samples.csv
- T42FWL_20200812_samples.csv
- T43QHA_20170315_samples.csv
- T43QHA_20180213_samples.csv
- T43QHV_20181110_samples.csv
- T43TCG_20200925_samples.csv
- T43TEG_20181227_samples.csv
- T43TEG_20201017_samples.csv
- T43TFH_20190516_samples.csv
- T44QLG_20181016_samples.csv
- T44TKM_20180408_samples.csv
- T44TLM_20181214_samples.csv
- T44TLN_20171224_samples.csv
- T44TLN_20190123_samples.csv
- T44TLN_20190128_samples.csv
- T45QWE_20200305_samples.csv
- T45QXG_20170316_samples.csv
- T45QXG_20190510_samples.csv
- T45QYF_20190721_samples.csv
- T45RXH_20190110_samples.csv
- T45RYH_20181002_samples.csv
- T45RYH_20201105_samples.csv
- T45RYJ_20190316_samples.csv
- T45RYK_20190105_samples.csv
- T45RYK_20190301_samples.csv
- T46QBM_20190117_samples.csv
- T46QBM_20190201_samples.csv
- T46QCL_20161213_samples.csv
- T46QCL_20191014_samples.csv
- T46RBN_20181118_samples.csv
- T46RCN_20181118_samples.csv
- T46RCN_20200127_samples.csv
- T46RCQ_20200117_samples.csv
- T47QRB_20200221_samples.csv
- T47QRB_20201117_samples.csv
- T47QRC_20170820_samples.csv
- T47QRC_20180318_samples.csv
- T47QRC_20200302_samples.csv
- T47QRC_20201217_samples.csv
- T48PVQ_20170814_samples.csv
- T48PVU_20170521_samples.csv
- T48PWA_20181222_samples.csv
- T48PWB_20180928_samples.csv
- T48PWR_20200525_samples.csv
- T48QTE_20201227_samples.csv
- T49MFM_20181031_samples.csv

- T49MFN_20200109_samples.csv

The increasing demand for high spatial resolution in remote sensing imagery has led to the necessity of super-resolution (SR) algorithms that convert low-resolution (LR) images into high-resolution (HR) ones. To address this need, we introduce SEN2NAIP, a large remote sensing dataset designed to support conventional and reference-based SR model training. SEN2NAIP is structured into two components to provide a broad spectrum of research and application needs. The first component comprises a cross-sensor dataset of 2,851 pairs of LR images from Sentinel-2 L2A and HR images from the National Agriculture Imagery Program (NAIP). Leveraging this dataset, we developed a degradation model capable of converting NAIP images to match the characteristics of Sentinel-2 imagery (S2like). Subsequently, this degradation model was utilized to create the second component, a synthetic dataset comprising 17,657 NAIP and S2like image pairs. With the SEN2NAIP dataset, we aim to provide a valuable resource that facilitates the exploration of new techniques for enhancing the spatial resolution of Sentinel-2 satellite imagery.

Satellite imagery has several applications, including land use and land cover classification, change detection, object detection, etc. Satellite based remote sensing sensors often encounter cloud coverage due to which clear imagery of earth is not collected. The clouded regions should be excluded, or cloud removal algorithms must be applied, before the imagery can be used for analysis. Most of these preprocessing steps require a cloud mask. In case of single-scene imagery, though tedious, it is relatively easy to manually create a cloud mask. However, for a larger number of images, an automated approach for identifying clouds is necessary. This model can be used to automatically generate a cloud mask from Sentinel-2 imagery.Using the modelFollow the guide to use the model. Before using this model, ensure that the supported deep learning libraries are installed. For more details, check Deep Learning Libraries Installer for ArcGIS.Fine-tuning the modelThis model can be fine-tuned using the Train Deep Learning Model tool. Follow the guide to fine-tune this model.InputSentinel-2 L2A imagery in the form of a raster, mosaic dataset or image service.OutputClassified raster containing three classes: Low density, Medium density and High density.Applicable geographiesThis model is expected to work well in Europe and the United States. This model works well for land based areas. Large water bodies such as ocean, seas and lakes should be avoided.Model architectureThis model uses the UNet model architecture implemented in ArcGIS API for Python.Accuracy metricsThis model has an overall accuracy of 94 percent with L2A imagery. The table below summarizes the precision, recall and F1-score of the model on the validation dataset. The comparatively low precision, recall and F1 score for Low density clouds might cause false detection of such clouds in certain urban areas. Also, for certain seasonal clouds some extremely bright pixels might be missed out.ClassPrecisionRecallF1 scoreHigh density0.9600.9750.968Medium density0.9050.8970.901Low density0.7740.5710.657Sample resultsHere are a few results from the model.