Câmara, Gilberto; Picoli, Michelle; Simoes, Rolf; Maciel, Adeline; Carvalho, Alexandre X Y; Coutinho, Alexandre; Esquerdo, Julio; Antunes, Joao; Begotti, Rodrigo; Arvor, Damien (2017): Land cover change maps for Mato Grosso State in Brazil: 2001-2016, links to files. PANGAEA, https://doi.org/10.1594/PANGAEA.881291, Supplement to: Picoli, Michelle; Câmara, Gilberto; Sanches, Ieda; Simoes, Rolf; Carvalho, Alexandre X Y; Maciel, Adeline; Coutinho, Alexandre; Esquerdo, Julio; Antunes, Joao; Begotti, Rodrigo; Arvor, Damien; Almeida, Claudio (2018): Big earth observation time series analysis for monitoring Brazilian agriculture. ISPRS Journal of Photogrammetry and Remote Sensing, 145, 328-339, https://doi.org/10.1016/j.isprsjprs.2018.08.007
Always quote citation above when using data! You can download the citation in several formats below.
Alert New version:
Câmara, Gilberto; Picoli, Michelle; Maciel, Adeline; Simoes, Rolf; Santos, Lorena; Andrade, Pedro R; Ferreira, Karine; Begotti, Rodrigo; Sanches, Ieda; Carvalho, Alexandre X Y; Coutinho, Alexandre; Esquerdo, Julio; Antunes, Joao; Arvor, Damien (2019): Land cover change maps for Mato Grosso State in Brazil: 2001-2017 (version 3). PANGAEA, https://doi.org/10.1594/PANGAEA.899706
This data sets include yearly maps of land cover classification for the state of Mato Grosso, Brasil, from 2001 to 2016, based on MODIS image time series at 250 meter spatial resolution. Ground samples consisting of 2,115 time series with known labels are used as training data for a support vector machine classifier. The classes include natural and human-transformed land areas, discriminating among different agricultural crops in state of Mato Grosso, Brazil's agricultural frontier. The results provide spatially explicit estimates of productivity increases in agriculture as well as the trade-offs between crop and pasture expansion. Quality assessment using a 5-fold cross-validation of the training samples indicates an overall accuracy of 93% and the following user's and producer's accuracy for the land cover classes:
Cerrado: UA - 99% PA - 98%
Fallow_Cotton UA - 100% PA - 100%
Forest UA - 99% PA - 98%
Pasture UA - 95% PA - 96%
Soy-Corn UA- 87% PA - 97%
Soy-Cotton UA - 99% PA - 94%
Soy-Fallow UA - 100% PA - 100%
Soy-Millet UA- 84% PA - 84%
Soy-Sunflower UA - 85% PA - 85%
The correlation coefficients between the agricultural areas classified by our method and the estimates by IBGE (Brazil's Census Bureau) for the harvests from 2005 to 2016, were equal to 0.98. At state level the soybean, cotton, corn and sunflower areas had a correlation equal 0.98, 0.73, 0.96 and 0.80.
The following data sets are provided:
(a) The classified maps in compressed TIFF format (one per year) at MODIS resolution.
(b) A QGIS style file for displaying the data in the QGIS software
(c) An RDS file (R compressed format) with the training data set (2,115 ground samples).
The software used to produce the analysis is available as open source on https://github.com/e-sensing.
Note: The TIFF raster files use the Sinusoidal Projection, which is the same cartographical projection used by the input MODIS images. When opening the TIFF raster maps in QGIS, to ensure correct navigation please use the Sinusoidal Projection, by selecting in QGIS projection menu, the following option:
"Generated CRS (+proj=sinu +lon_0=0 +x_0=0 +y_0=0 +a=6371007.181 +b=6371007.181 +units=m +no_defs)"
Câmara, Gilberto; Picoli, Michelle; Simoes, Rolf; Maciel, Adeline; Carvalho, Alexandre X Y; Coutinho, Alexandre; Esquerdo, Julio; Antunes, Joao; Begotti, Rodrigo; Arvor, Damien; Santos, Lorena (2018): Land cover change maps for Mato Grosso State in Brazil: 2001-2017 (Version 2), links to files. PANGAEA, https://doi.org/10.1594/PANGAEA.895495
Latitude: -12.700000 * Longitude: -56.000000
|#||Name||Short Name||Unit||Principal Investigator||Method/Device||Comment|
|1||File content||Content||Câmara, Gilberto|
|2||File name||File name||Câmara, Gilberto|
|3||File format||File format||Câmara, Gilberto|
|4||File size||File size||kByte||Câmara, Gilberto|
|5||Uniform resource locator/link to file||URL file||Câmara, Gilberto|
35 data points