Not logged in
PANGAEA.
Data Publisher for Earth & Environmental Science

Câmara, Gilberto; Simoes, Rolf; Picoli, Michelle; Andrade, Pedro R; Rorato, Ana; Santos, Lorena; Maciel, Adeline; Sanches, Ieda; Coutinho, Alexandre; Esquerdo, Julio; Antunes, Joao; Arvor, Damien; Begotti, Rodrigo; Sanchez, Alber; Queiroz, Gilberto; Ferreira, Karine (2020): Land use and land cover maps for Amazon biome in Brazil for 2001-2019 derived from MODIS time series [dataset]. PANGAEA, https://doi.org/10.1594/PANGAEA.911560

Always quote citation above when using data! You can download the citation in several formats below.

RIS CitationBibTeX CitationShow MapGoogle Earth

Abstract:
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 UserAcc
Forest 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%
Keyword(s):
Brazilian Amazonia; land use classification; LUCC; MODIS; tropical forest
Coverage:
Median Latitude: -9.959547 * Median Longitude: -57.825557 * South-bound Latitude: -10.938970 * West-bound Longitude: -65.736030 * North-bound Latitude: -9.000000 * East-bound Longitude: -43.000000
Event(s):
Amazon_Brazil * Latitude: -9.000000 * Longitude: -43.000000 * Method/Device: Multiple investigations (MULT)
Amazonia_Brazil-Bolivia * Latitude Start: -9.939670 * Longitude Start: -65.736030 * Latitude End: -10.938970 * Longitude End: -64.740640 * Location: Amazon * Method/Device: Satellite remote sensing (SAT)
Comment:
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 "
---------------------
Acknowledgements
This 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
Parameter(s):
#NameShort NameUnitPrincipal InvestigatorMethod/DeviceComment
File contentContentCâmara, Gilberto
File nameFile nameCâmara, Gilberto
File formatFile formatCâmara, Gilberto
File sizeFile sizekByteCâmara, Gilberto
Uniform resource locator/link to fileURL fileCâmara, Gilberto
Size:
100 data points

Data

Download dataset as tab-delimited text — use the following character encoding:


Content

File name

File format

File size [kByte]

URL file
QGIS style file for displaying the data in the QGIS softwaresits_amazon_style.qmlQML2.652sits_amazon_style.qml
Classified maps in compressed TIFF format for 2001 at 250 meters of spatial resolutionAMZ_2000_9_2001_8.tifTIF7159.144AMZ_2000_9_2001_8.tif
Classified maps in compressed TIFF format for 2002 at 250 meters of spatial resolutionAMZ_2001_9_2002_8.tifTIF7071.264AMZ_2001_9_2002_8.tif
Classified maps in compressed TIFF format for 2003 at 250 meters of spatial resolutionAMZ_2002_9_2003_8.tifTIF7098.578AMZ_2002_9_2003_8.tif
Classified maps in compressed TIFF format for 2004 at 250 meters of spatial resolutionAMZ_2003_9_2004_8.tifTIF7129.119AMZ_2003_9_2004_8.tif
Classified maps in compressed TIFF format for 2005 at 250 meters of spatial resolutionAMZ_2004_9_2005_8.tifTIF7139.752AMZ_2004_9_2005_8.tif
Classified maps in compressed TIFF format for 2006 at 250 meters of spatial resolutionAMZ_2005_9_2006_8.tifTIF7149.706AMZ_2005_9_2006_8.tif
Classified maps in compressed TIFF format for 2007 at 250 meters of spatial resolutionAMZ_2006_9_2007_8.tifTIF7185.979AMZ_2006_9_2007_8.tif
Classified maps in compressed TIFF format for 2008 at 250 meters of spatial resolutionAMZ_2007_9_2008_8.tifTIF7219.539AMZ_2007_9_2008_8.tif
Classified maps in compressed TIFF format for 2009 at 250 meters of spatial resolutionAMZ_2008_9_2009_8.tifTIF7256.251AMZ_2008_9_2009_8.tif
Classified maps in compressed TIFF format for 2010 at 250 meters of spatial resolutionAMZ_2009_9_2010_8.tifTIF7269.083AMZ_2009_9_2010_8.tif
Classified maps in compressed TIFF format for 2011 at 250 meters of spatial resolutionAMZ_2010_9_2011_8.tifTIF7293.663AMZ_2010_9_2011_8.tif
Classified maps in compressed TIFF format for 2012 at 250 meters of spatial resolutionAMZ_2011_9_2012_8.tifTIF7338.303AMZ_2011_9_2012_8.tif
Classified maps in compressed TIFF format for 2013 at 250 meters of spatial resolutionAMZ_2012_9_2013_8.tifTIF7387.644AMZ_2012_9_2013_8.tif
Classified maps in compressed TIFF format for 2014 at 250 meters of spatial resolutionAMZ_2013_9_2014_8.tifTIF7462.263AMZ_2013_9_2014_8.tif
Classified maps in compressed TIFF format for 2015 at 250 meters of spatial resolutionAMZ_2014_9_2015_8.tifTIF7498.388AMZ_2014_9_2015_8.tif
Classified maps in compressed TIFF format for 2016 at 250 meters of spatial resolutionAMZ_2015_9_2016_8.tifTIF7511.352AMZ_2015_9_2016_8.tif
Classified maps in compressed TIFF format for 2017 at 250 meters of spatial resolutionAMZ_2016_9_2017_8.tifTIF7541.117AMZ_2016_9_2017_8.tif
Classified maps in compressed TIFF format for 2018 at 250 meters of spatial resolutionAMZ_2017_9_2018_8.tifTIF7555.097AMZ_2017_9_2018_8.tif
The training data set in an R compressed format containing 33,052 ground samplessamples_amazonia.rdsRDS9285.009samples_amazonia.rds