Analysis Ready Data (ARD)
Also known as: ARD, analysis-ready imagery
Analysis ready data (ARD) is imagery processed so it can be used directly for analysis with consistent geometry, metadata, and quality information.
Definitions for common earth observation and geospatial terms. Product-specific naming lives in the FAQ and docs. Each term page has a stable URL you can reference.
Showing 66 terms.
Also known as: ARD, analysis-ready imagery
Analysis ready data (ARD) is imagery processed so it can be used directly for analysis with consistent geometry, metadata, and quality information.
Also known as: delivery cadence, update frequency
Cadence is how often a processed product is delivered, which can differ from sensor revisit time.
Also known as: temporal composite, best-pixel composite
A composite is a mosaic built over a time window, often selecting the “best” pixel per location.
Also known as: elevation model
A DEM is a raster representing elevation, used for terrain correction, hydrology, and orthorectification.
Also known as: geolocation, geo-registration
Georeferencing links pixels or coordinates in a dataset to real-world locations on Earth.
Also known as: delivery delay, time-to-delivery
Latency is the delay between when data is acquired and when a usable product is delivered to the user.
Also known as: mosaicking
A mosaic combines multiple scenes into one continuous image covering a larger area or time window.
Also known as: missing data, invalid pixels, NA (raster)
NoData is a special value that means a pixel has no valid measurement, for example due to clouds or missing coverage.
Also known as: ortho correction, ortho-rectified
Orthorectification corrects geometric distortion so imagery aligns properly with the ground, using terrain and sensor geometry.
Also known as: QA band, quality layer
A quality mask is a layer that flags pixels with issues such as clouds, shadows, saturation, or low confidence.
Also known as: radiometric calibration, radiometric consistency
Radiometry is the measurement and calibration of electromagnetic energy recorded by a sensor.
Also known as: processing baseline, reprocessed data
Reprocessing means older data is processed again with updated algorithms or calibration, which can change values for the same date.
Also known as: project, CRS transform
Reprojection converts data from one coordinate reference system (CRS) to another.
Also known as: interpolation (raster), grid resampling
Resampling changes the pixel grid of a raster, for example when reprojecting or changing resolution.
Also known as: revisit interval, repeat cycle
Revisit time is the typical time between observations of the same location by a sensor or constellation.
Also known as: UTM zone
UTM is a projected coordinate system that divides Earth into zones, allowing measurements in meters.
Also known as: Area of Interest
An AOI is the geographic area you want to analyze or request data for, defined by a boundary such as a polygon or bounding box.
Also known as: bounding box, extent
A bounding box is a rectangle defined by minimum and maximum coordinates, commonly used to specify an AOI.
Also known as: projection, spatial reference
A CRS defines how coordinates map to locations on Earth, including the projection and datum.
Also known as: EPSG:4326, EPSG identifier
An EPSG code is a numeric identifier for a CRS, such as EPSG:4326 for WGS84 latitude/longitude.
Also known as: geodata, spatial data
Geospatial data is any data tied to a location on Earth, such as maps, satellite imagery, or field boundaries.
Also known as: area polygon, boundary
A polygon is a closed boundary used to represent an area such as a field, region, or administrative unit.
Also known as: EPSG:4326, lat/lon
WGS84 is a global geographic coordinate system commonly used for latitude and longitude.
Also known as: token, access key
An API key is a credential used to authenticate requests and associate them with an account or application.
Also known as: quota, throttling
A rate limit restricts how many requests an API accepts in a time window to protect stability and fairness.
Also known as: AC, surface correction
Atmospheric correction removes or reduces atmospheric effects so scenes are more comparable across time and space.
Also known as: BRDF normalization, directional reflectance
BRDF describes how reflectance changes with viewing and illumination geometry, affecting apparent brightness across scenes.
Also known as: cloud flag, QA cloud
A cloud mask labels pixels likely affected by clouds so they can be excluded or handled differently.
Also known as: shadow mask, cloud shade
Cloud shadow is the darkening of the surface caused by clouds blocking sunlight, often mistaken for real change.
Also known as: aerosol haze, smoke haze
Haze is atmospheric scattering from aerosols that reduces contrast and shifts reflectance, especially in blue bands.
Also known as: multispectral imagery, passive optical
Optical imagery measures reflected sunlight, providing rich spectral information but being sensitive to clouds and illumination.
Also known as: top-of-sensor radiance
Radiance is the raw physical quantity measured by optical sensors, representing energy reaching the sensor.
Also known as: surface reflectance (general)
Reflectance is the fraction of incoming light that a surface reflects, commonly used for analysis and comparison.
Also known as: BOA, Level-2, L2, L2A
Surface reflectance estimates what reflectance would be at the ground after removing atmospheric effects.
Also known as: Level-1 reflectance, L1, L1C
TOA reflectance is reflectance at the top of the atmosphere, before full atmospheric correction to the surface.
Also known as: sigma0, sigma nought, dB backscatter
Backscatter is the amount of radar signal returned to the sensor, influenced by roughness, moisture, and structure.
Also known as: look angle
Incidence angle is the angle between the radar beam and the surface; it affects SAR backscatter and comparability.
Also known as: VV, VH, HH, HV
Polarization describes the transmit and receive orientation of radar waves; different polarizations respond to different surface properties.
Also known as: radar imagery, microwave radar
SAR is an active radar sensor that works day or night and can see through clouds, measuring surface scattering rather than reflected sunlight.
Also known as: speckle noise
Speckle is a grainy noise pattern in SAR imagery caused by coherent interference, typically reduced by filtering or multi-looking.
Also known as: spectral band, channel
A band is a single spectral channel in an image, measuring energy within a specific wavelength range.
Also known as: DN, raw pixel value
A digital number (DN) is the raw pixel value recorded by a sensor before it is converted to physical units like radiance or reflectance.
Also known as: EO, Earth observation data, satellite monitoring
Earth observation is the use of satellites, aircraft, or drones to measure and monitor the planet’s surface and atmosphere.
Also known as: cell, raster cell
A pixel is the smallest unit in a raster; it represents the sensor’s measurement over a ground area.
Also known as: grid data, pixel grid
A raster is a grid of pixels where each pixel stores a value, commonly used for satellite imagery and elevation models.
Also known as: satellite sensing, aerial sensing
Remote sensing measures Earth from a distance using sensors that record reflected or emitted energy.
Also known as: ground resolution, meters per pixel
Spatial resolution describes the ground detail an image can represent, commonly expressed as meters per pixel.
Also known as: wavelength resolution
Spectral resolution describes how finely a sensor samples wavelengths and how narrow its bands are.
Also known as: revisit, revisit frequency
Temporal resolution describes how often a location is observed, such as a 5-day revisit.
Also known as: shapes, features
Vector data represents geometry as points, lines, and polygons, typically used for boundaries, roads, and field parcels.
Also known as: change analysis, alerting
Change detection identifies meaningful differences between dates, such as harvest, flooding, deforestation, or construction.
Also known as: multi-sensor fusion
Data fusion combines multiple data sources or sensors to create a more complete or consistent product.
Also known as: imputation, missing data filling
Gap filling estimates missing values in time series caused by clouds, shadows, or data dropouts.
Also known as: radiometric harmonization, normalization
Harmonization reduces differences between scenes or sensors so values are more comparable across time.
Also known as: Normalized Difference Vegetation Index
NDVI is a vegetation index that uses red and near-infrared reflectance to approximate vegetation greenness and vigor.
Also known as: no future leak, causal processing
Temporal integrity means an output for a given date is built only from information available on or before that date.
Also known as: timeseries, temporal stack
A time series is a sequence of observations over time for the same location, used for monitoring and change detection.
Also known as: field statistics, polygon statistics
Zonal statistics summarize raster values inside a polygon, such as average NDVI per field.
Also known as: Cloud Optimized GeoTIFF, cloud-optimized geotiff
A COG is a GeoTIFF organized for fast partial reads over HTTP, enabling streaming access without downloading the full file.
Also known as: tif, tiff
GeoTIFF is a raster image format that embeds georeferencing metadata so pixels map to real-world coordinates.
Also known as: SpatioTemporal Asset Catalog
STAC is a standard for describing geospatial data assets so they can be discovered and accessed consistently.
Also known as: reference data, labels
Ground truth is reference information about real conditions on the ground used to train or validate models.
Also known as: labeled data
Training data is the labeled examples used to fit a machine learning model.
Also known as: model evaluation, testing
Validation tests model performance on data not used for training, to estimate how well it will generalize.
Also known as: S1, Sentinel 1
Sentinel-1 is an ESA SAR mission providing radar observations that work through clouds and at night.
Also known as: S2, Sentinel 2
Sentinel-2 is an ESA optical multispectral mission widely used for land monitoring at 10–60 m resolution.