This dataset contains the yearly maps of land use and land cover classification for Amazon biome, Brazil, from 2000 to 2019 at 250 meters of spatial resolution. We used image time series from MOD13Q1 product from MODIS (collection 6), with four bands (NDVI, EVI, near-infrared, and mid-infrared) as data input. A deep learning classification MLP network consisting of 4 hidden layers with 512 units was trained using a set of 33,052 time series of 12 known classes from both natural and anthropic land covers.Quality assessment using 5-fold cross-validation of the training samples indicates an overall accuracy of 99.22% and the following user's and producer's accuracy for the land cover classes: ProdAcc UserAccForest 99.80% 99.86%Pasture 98.72% 98.04%Soy_Corn 98.92% 99.06%Soy_Cotton 99.23% 99.25%Fallow_Cotton 95.74% 96.43%Millet_Cotton 100.00% 97.98%Soy_Fallow 99.76% 99.09%Savanna2 99.94% 99.47%Savanna1 98.18% 99.06%Wetlands 99.31% 98.19%Soy_Millet 76.67% 84.66%Soy_Sunflower 84.62% 78.57%

The following files are provided:(a) 19 classified maps in compressed TIFF format (one per year) from 2001 to 2019 at ~250m of spatial resolution.(b) A colourmap style to display the files in desktop QGIS software (.qml).(c) The training data set in an R compressed format (.rds) containing 33,052 ground samples.---The R package used to classify the maps is available as open-source on https://github.com/e-sensing/sits.---Note: The GeoTIFF raster files use the Sinusoidal Projection, the same cartographical projection used by MODIS images. The proj4 string is"+proj=sinu +lon_0=0 +x_0=0 +y_0=0 +a=6371007.181 +b=6371007.181 +units=m +no_defs "---------------------AcknowledgementsThis research was funded by: (a) The São Paulo Research Foundation (FAPESP) through the eScience Program grant 2014/08398-6 and grants 2016/23750-3 and 2017/19812-6; (b) The Brazil Data Cube project, funded by the Amazon Fund through the financial collaboration of the Brazilian Development Bank (BNDES) and the Foundation for Science, Technology and Space Applications (FUNCATE) no.~17.2.0536.1; (c) The RESTORE+ project, which is part of the International Climate Initiative (IKI), supported by the Federal Ministry for the Environment, Nature Conservation and Nuclear Safety (BMU) based on a decision adopted by the German Bundestag