Validation Points


A total of 85,152 random stratified samples were generated for validation of the MapBiomas annual maps. The samples were visually inspected using Landsat images assigning the land use and land cover class for each year from 1985 to 2018.

This sample set is available in the following csv and shapefile files. Each sample presents coordinates, states, biomes, and information per year of: land cover and land use class (ID of the legend used in the maps); level of concordance (3: maximum, 2: medium and 1: low) and edge pixel between two classes (1: yes and 0: no), indicated in the 'LABEL' column.

The stratification of the samples was done on two levels: by supercards (joining every four IBGE maps of 1:250,000) and by slope classes defined by EMBRAPA. Considering the minimum quantity of 500 points per supercharter and corrected with the Bonferroni equation. Dimensioned so as to ensure a maximum margin of error of 5% and confidence level of 95% in the smallest unit of geographical coverage, in other words, in each supercharter. For the national territory the maximum expected error was 0.5%.

For the visual interpretation the TVI (Temporal Visual Inspection) platform was used, developed by Lapig, in which each pixel was initially interpreted by 3 independent analysts. Pixels for which there was no agreement between the assigned classes were re-inspected by supervisor and the pixel's class assigned.

In Collection 7, these points were updated for the years 2019, 2020 and 2021 and adjusted for the new legend classes. This updated dataset will be released shortly.

For more information on the description of the sampling content and method, access the ATBD by clicking here. Other reference material on sampling and benchmark analysis is available in the article.

For questions, suggestions and other information please contact and participate in the MapBiomas Forum.