Earth Observation GeoSpatial Data Analytics

Trillions of pixels of images and multispectral data are beamed back to earth from NASA, ESA, JAXA, ISRO and private satellites every day. Earth Observation Satellites gather information on the physical, chemical and biological systems of our planet for the last 60 years. 

We deploy machine learning to process enormous amounts of varied data for change analysis, discover trends & anomalies and unlock knowledge and secrets that are put to use for groundbreaking environmental action. 

We harness the power of cloud computing, data science, machine learning and computer vision to analyse these numerous Earth Observation datasets.  Our artificial intelligence provides critical actionable insights and decision support that has been impossible to fathom just a few years ago.

We provide analytics from dozens of data sets with unprecedented efficiency and deliver powerful insights for solving the biggest challenges facing our planet.

Our analysis are available for any region of the world without any software and technical knowledge. 

The MODIS Fire Burned Area  is a monthly global ~250m spatial resolution dataset containing information on burned area as well as ancillary data. It is based on surface reflectance in the Near Infrared (NIR) band from the MODIS instrument onboard the Terra satellite, as well as active fire information from the same sensor of the Terra and Aqua satellites.

The burned area algorithm uses a two-phase hybrid approach. In a first step pixels with a high probability of being burned (called “seeds”) are detected based on the active fires. In a second one, a contextual growing is applied to completely detect the fire patch. This growing phase is controlled by an adaptive thresholding, where thresholds are computed based on the specific characteristics of the area surrounding each seed. The variable used to guide the whole detection process is the NIR drop between pre- and post-fire images.

Fire CCI51 was developed as part of the ESA Climate Change Initiative Programme, and it is also part of the Copernicus Climate Change Service.

The Fire (HSC) product contains four images: one in the form of a fire mask and the other three with pixel values identifying fire temperature, fire area, and fire radiative power. 

The ABI L2+ FHS metadata mask assigns a flag to every earth-navigated pixel that indicates its disposition with respect to the FHS algorithm. Operational users who have the lowest tolerance for false alarms should focus on the “processed” and “saturated” categories (mask codes 10, 11, 30, and 31), but within these categories there can still be false alarms.

The MOD14A1 V6 dataset provides daily fire mask composites at 1km resolution derived from the MODIS 4- and 11-micrometer radiances. The fire detection strategy is based on absolute detection of a fire (when the fire strength is sufficient to detect), and on detection relative to its background (to account for variability of the surface temperature and reflection by sunlight). The product distinguishes between fire, no fire and no observation. This information is used for monitoring the spatial and temporal distribution of fires in different ecosystems, detecting changes in fire distribution and identifying new fire frontiers, wild fires, and changes in the frequency of the fires or their relative strength.

The Hydrologically Enforced Digital Elevation Model (DEM-H) was derived from the SRTM data acquired by NASA in February 2000. The model has been hydrologically conditioned and drainage enforced. The DEM-H captures flow paths based on SRTM elevations and mapped stream lines, and supports delineation of catchments and related hydrological attributes. The dataset was derived from the 1 second smoothed Digital Elevation Model (DEM-S; ANZCW0703014016) by enforcing hydrological connectivity with the ANUDEM software, using selected AusHydro V1.6 (February 2010) 1:250,000 scale watercourse lines (ANZCW0503900101) and lines derived from DEM-S to define the watercourses. The drainage enforcement has produced a consistent representation of hydrological connectivity with some elevation artefacts resulting from the drainage enforcement. A full description of the methods is in preparation.

Dataset Provider: UCSB/CHG

Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS) is a 30+ year quasi-global rainfall dataset. CHIRPS incorporates 0.05° resolution satellite imagery with in-situ station data to create gridded rainfall time series for trend analysis and seasonal drought monitoring.

The Cloud and Moisture Imagery products are all at 2km resolution.

Bands 1-6 are reflective. The dimensionless “reflectance factor” quantity is normalized by the solar zenith angle. These bands support the characterization of clouds, vegetation, snow/ice, and aerosols.

Bands 7-16 are emissive. The brightness temperature at the Top-Of-Atmosphere (TOA) is measured in Kelvin. These bands support the characterization of the surface, clouds, water vapor, ozone, volcanic ash, and dust based on emissive properties.

The Sentinel-1 mission provides data from a dual-polarization C-band Synthetic Aperture Radar (SAR) instrument at 5.405GHz (C band). This collection includes the S1 Ground Range Detected (GRD) scenes, processed using the Sentinel-1 Toolbox to generate a calibrated, ortho-corrected product. The collection is updated daily. New assets are ingested within two days after they become available.

This collection contains all of the GRD scenes. Each scene has one of 3 resolutions (10, 25 or 40 meters), 4 band combinations (corresponding to scene polarization) and 3 instrument modes. Use of the collection in a mosaic context will likely require filtering down to a homogeneous set of bands and parameters. See this article for details of collection use and preprocessing. Each scene contains either 1 or 2 out of 4 possible polarization bands, depending on the instrument’s polarization settings. horizontal transmit/vertical receive

Each scene also includes an additional ‘angle’ band that contains the approximate incidence angle from ellipsoid in degrees at every point. This band is generated by interpolating the ‘incidenceAngle’ property of the ‘geolocationGridPoint’ gridded field provided with each asset.

Each scene is pre-processed with

-Thermal noise removal

-Radiometric calibration

-Terrain correction using SRTM 30 or ASTER DEM for areas greater than 60 degrees latitude, where SRTM is not available. 

FIRMS Model Fire Information for Resource Management System

The Earth Engine version of the Fire Information for Resource Management System (FIRMS) dataset contains the LANCE fire detection product in rasterized form. The near real-time (NRT) active fire locations are processed by LANCE using the standard MODIS MOD14/MYD14 Fire and Thermal Anomalies product. Each active fire location represents the centroid of a 1km pixel that is flagged by the algorithm as containing one or more fires within the pixel. The data are rasterized as follows: for each FIRMS active fire point, a 1km bounding box (BB) is defined; pixels in the MODIS sinusoidal projection that intersect the FIRMS BB are identified; if multiple FIRMS BBs intersect the same pixel, the one with higher confidence is retained; in case of a tie, the brighter one is retained.

The data in the near-real-time dataset are not considered to be of science quality.

Today, only 4 billion hectares of Forest cover are left on planet Earth.

The world has lost one-third of its forest – an area twice the size of the United States.

Using radar data from the European Space Agency’s Sentinel-1 satellites, which cover the tropics every 6 to 12 days. The long wavelength radio waves can also penetrate smoke and haze, providing insight on forest loss that is occurring in areas that are otherwise shrouded.

Forest/Gain Loss is one of the most important insights from Earth Observation Satellites.

With at least one image of every location on Earth per season for 43 years, the Landsat Satellite data archive contains more than 50 trillion pixels.

Remote sensing has been used for mapping the distribution of forest ecosystems, global fluctuations in plant productivity with season, and the three-dimensional (3D) structure of forests.

The range and diversity of sensing systems, as well as the variety of applications, have evolved greatly over the last century

Landsat 9, like Landsat 8, has a higher imaging capacity than past Landsats, allowing more valuable data to be added to the Landsat global land archive—around 1,400 scenes per day.

Landsat 9, like Landsat 8, is both radiometrically and geometrically better than earlier generation Landsats.

In the nearly five decades since Landsat 1 launched, the spectral bands of the Landsat satellites have evolved. Landsat 9 has the most evolved of the Landsat spectral bands.

Landsat 9, launched September 27, 2021, joins Landsat 8 in orbit; the satellite orbits are 8 days out of phase. Landsat 9 replaces Landsat 7 (launched in 1999), taking its place in orbit (8 days out of phase with Landsat 8). The combined Landsat 8 + Landsat 9 revisit time for data collection with be every 8 days, like it currently is for Landsat 8 + Landsat 7.

Land Surface Temperature is an important variable within the Earth climate system. It describes processes such as the exchange of energy and water between the land surface and atmosphere, and influences the rate and timing of plant growth.

Accurately understanding Land Surface Temperature at the global and regional level helps to evaluate land surface–atmosphere exchange processes in models and, when combined with other physical properties such as vegetation and soil moisture, provides a valuable metric of surface state.


Soil moisture is an essential component of the Earth system and plays an important role in the exchange of water, energy and biogeochemical fluxes between the atmosphere and the land surface. Temporally and spatially continuous soil moisture datasets are commonly explored through hydrological and land surface models.

Beyond in situ measurements and model simulations, remote sensing provides another path to estimating soil moisture, which can provide independent reference data for validating model simulations, while avoiding the spatial coverage limitations of ground-based measurements. Optical, thermal infrared, and microwave remote sensing observations have all been used to retrieve soil moisture.

This dataset provides near real-time high-resolution imagery of CO concentrations.

Carbon monoxide (CO) is an important atmospheric trace gas for understanding tropospheric chemistry. In certain urban areas, it is a major atmospheric pollutant. Main sources of CO are combustion of fossil fuels, biomass burning, and atmospheric oxidation of methane and other hydrocarbons. Whereas fossil fuel combustion is the main source of CO at northern mid-latitudes, the oxidation of isoprene and biomass burning play an important role in the tropics. TROPOMI on the Sentinel 5 Precursor (S5P) satellite observes the CO global abundance exploiting clear-sky and cloudy-sky Earth radiance measurements in the 2.3 µm spectral range of the shortwave infrared (SWIR) part of the solar spectrum. TROPOMI clear sky observations provide CO total columns with sensitivity to the tropospheric boundary layer. For cloudy atmospheres, the column sensitivity changes according to the light path

A Vegetation Index (VI) is a spectral transformation of two or more bands designed to enhance the contribution of vegetation properties and allow reliable spatial and temporal inter-comparisons of terrestrial photosynthetic activity and canopy structural variations.

Starting in 2009, the Earth Observation Team of the Science and Technology Branch (STB) at Agriculture and Agri-Food Canada (AAFC) began the process of generating annual crop type digital maps. Focusing on the Prairie Provinces in 2009 and 2010, a Decision Tree (DT) based methodology was applied using optical (Landsat-5, AWiFS, DMC) and radar (Radarsat-2) based satellite images. Beginning with the 2011 growing season, this activity has been extended to other provinces in support of a national crop inventory. To date this approach can consistently deliver a crop inventory that meets the overall target accuracy of at least 85% at a final spatial resolution of 30m (56m in 2009 and 2010).

The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) is a multispectral imager that was launched on board NASA’s Terra spacecraft in December, 1999. ASTER can collect data in 14 spectral bands from the visible to the thermal infrared. Each scene covers an area of 60 x 60 km. These scenes, produced by the USGS, contain calibrated at-sensor radiance, ortho-rectified and terrain corrected.

The Shuttle Radar Topography Mission (SRTM) digital elevation dataset was originally produced to provide consistent, high-quality elevation data at near global scope. This version of the SRTM digital elevation data has been processed to fill data voids, and to facilitate its ease of use.

The CORINE (coordination of information on the environment) Land Cover (CLC) inventory was initiated in 1985 to standardize data collection on land in Europe to support environmental policy development. The project is coordinated by the European Environment Agency (EEA) in the frame of the EU Copernicus programme and implemented by national teams. The number of participating countries has increased over time currently including 33 (EEA) member countries and six cooperating countries (EEA39) with a total area of over 5.8 Mkm2.

The Copernicus Global Land Service (CGLS) is earmarked as a component of the Land service to operate a multi-purpose service component that provides a series of bio-geophysical products on the status and evolution of land surface at global scale.

The Dynamic Land Cover map at 100 m resolution (CGLS-LC100) is a new product in the portfolio of the CGLS and delivers a global land cover map at 100 m spatial resolution.

COPERNICUS/S2_HARMONIZED that shifts data with PROCESSING_BASELINE ‘04.00’ or above (after 2022-01-25) 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 monitoring of vegetation, soil and water cover, as well as observation of inland waterways and coastal areas.

Sentinel-2 is a wide-swath, high-resolution, multi-spectral imaging mission supporting Copernicus Land Monitoring studies, including the monitoring of vegetation, soil and water cover, as well as observation of inland waterways and coastal areas.

This dataset provides offline high-resolution imagery of the UV Aerosol Index (UVAI), also called the Absorbing Aerosol Index (AAI).

The AAI is based on wavelength-dependent changes in Rayleigh scattering in the UV spectral range for a pair of wavelengths. The difference between observed and modelled reflectance results in the AAI. When the AAI is positive, it indicates the presence of UV-absorbing aerosols like dust and smoke. It is useful for tracking the evolution of episodic aerosol plumes from dust outbreaks, volcanic ash, and biomass burning.

The TROPOMI/S5P cloud properties retrieval is based on the OCRA and ROCINN algorithms currently being used in the operational GOME and GOME-2 products. OCRA retrieves the cloud fraction using measurements in the UV/VIS spectral regions and ROCINN retrieves the cloud height (pressure) and optical thickness (albedo) using measurements in and around the oxygen A-band at 760 nm. Version 3.0 of the algorithms are used, which are based on a more realistic treatment of clouds as optically uniform layers of light-scattering particles. Additionally, the cloud parameters are also provided for a cloud model which assumes the cloud to be a Lambertian reflecting boundary