Live demonstration of SITS with SEPAL platform in the GEO-GFOI Workshop

The BDC team will present tomorrow (June, 16th) in the GEO-GFOI Workshop a live demonstration of the R package SITS (Satellite Image Time Series Analysis) running in the SEPAL platform.

SITS is an open source R package for satellite image time series analysis and machine learning. It supports the complete cycle of data analysis for land classification.

SEPAL (System for earth observations, data access, processing & analysis for land monitoring) is an open source platfom developed by the Open Foris team in Forestry Department of the United Nations Food and Agriculture Organization (FAO).

Organized by Group of Earth Observation (GEO) and Global Forest Observations Initiative (GFOI) the workshop will be held virtually on 16-17 June. For more information, access the workshop page:

Source: Brazil Data Cube project.

Two Landsat-8/OLI image mosaics of Brazil are available on the Brazil Data Cube Portal

Two image mosaics of Brazil was launched today by the Brazil Data Cube project team. These mosaic were generated from Landsat-8/OLI images, surface reflectance, with 30 meters of spatial resolution.

These mosaics were generated by selecting best pixels (free of clouds and cloud shadows) in two periods of 6 months: (1) July 2017 to December 2017 and (2) January 2018 to June 2018. The products use RGB color composition of the SWIR1 (B6), NIR (B5) e RED (B4) bands.

The visualization and download of these mosaics can be done in the BDC portal:

The Earth observation data cubes that were used to produce these mosaics, named Landsat-8 6M Cube (OLI) with all spectral bands from 1 to 7, are also available in the project portal.

In addition to the mosaics and the data cubes with 30 meters of spatial resolution, we offer other versions of mosaics with 64 and 250 meters, respectively. These mosaics can be download in GeoTIFF format from the following links:

These mosaics also can be access with GIS applications through the OGC WMS service using the following address.


Source: Brazil Data Cube team

New publication by the Brazil Data Cube team

Scholarship holder Lorena Santos, from the Brazil Data Cube project, published the article “Quality control and class noise reduction of satellite image time series” in the ISPRS Journal of Photogrammetry and Remote Sensing, together with her OTG advisors and project researchers, Karine Ferreira, Gilberto Camara and Michelle Picoli. “

The article is the result of her PHD at Brazil’s National Institute for Space Research on Applied Computing, and it shows the importance of using good quality samples when machine learning techniques are applied. The article proposes a method that uses self-organizing maps and Bayesian inference to reduce class noise through satellite images time series.

To see other publications by the BDC team, visit

Source: Brazil Data Cube Project.

  • Method for class noise reduction in satellite image time series reference data.