Land cover change maps for Mato Grosso State in Brazil: 2001-2017 (Version 2), links to files
Fuente:
PANGAEA
Salvato in:
| Autori principali: | , , , , , , , , , , |
|---|---|
| Natura: | Dataset Open Access |
| Lingua: | en |
| Pubblicazione: |
PANGAEA
2018
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1867170088255225856 |
|---|---|
| author | Câmara, Gilberto Picoli, Michelle Simoes, Rolf Maciel, Adeline Carvalho, Alexandre X Y Coutinho, Alexandre Esquerdo, Julio Antunes, Joao Begotti, Rodrigo Arvor, Damien Santos, Lorena |
| author_facet | Câmara, Gilberto Picoli, Michelle Simoes, Rolf Maciel, Adeline Carvalho, Alexandre X Y Coutinho, Alexandre Esquerdo, Julio Antunes, Joao Begotti, Rodrigo Arvor, Damien Santos, Lorena |
| collection | Datos científicos de ciencias marinas y ambientales |
| contents | This data set includes yearly maps of land cover classification for the state of Mato Grosso, Brasil, from 2001 to 2017, based on MODIS image time series (collection 6) at 250 meter spatial resolution (product MOD13Q1). Ground samples consisting of 1,892 time series with known labels are used as training data for a support vector machine classifier. We used the radial basis function kernel, with cost C=1 and gamma = 0.01086957. The classes include natural and human-transformed land areas, discriminating among different agricultural crops in state of Land cover change maps for Mato Grosso State in BrazilMato 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 96% and the following user's and producer's accuracy for the land cover classes: Cerrado: UA - 98% PA - 99% Fallow_Cotton UA - 96% PA - 93% Forest UA - 99% PA - 98% Pasture UA - 97% PA - 98% Soy-Corn UA- 91% PA - 93% Soy-Cotton UA - 97% PA - 97% Soy-Fallow UA - 98% PA - 98% Soy-Millet UA- 90% PA - 89% Soy-Sunflower UA - 77% PA - 65% --- The correlation coefficients between the agricultural areas classified by our method and the estimates by IBGE (Brazil's Census Bureau) for the harvests from 2001 to 2017, were equal to 0.98. At state level the soybean, cotton, corn and sunflower areas had a correlation equal 0.97, 0.85, 0.98 and 0.80. The areas classified as forest were compared with the Hansen et al. (2013) mapping for the year 2000. In order to separate the forest areas, we examined the areas with more than 25% tree cover on the Hansen et al. (2013, doi:10.1126/science.1244693) map. We found that 99% of the pixels classified as forest match the pixels indicated by Hansen et al. (2013) as having more than 25% tree cover. When we joined the cerrado and forest classes, 84% of the pixels match the pixels by Hansen et al. (2013, doi:10.1126/science.1244693) as having more than 25% tree cover. The pixels labelled as pasture were compared to the pasture mapping done by Parente et al. (2017, doi:10.1016/j.jag.2017.06.003) . We found that 80% of the pixels classified as pasture match the pixels indicated by Parente et al. (2017, doi:10.1016/j.jag.2017.06.003) for the state of Mato Grosso. In the data set "Land cover change maps for Mato Grosso State in Brazil version 2", we analysed the samples from the clustering process using self-organizing maps. The samples with high level of confusion were removed from the dataset. In addition, we used a Bayesian smoothing method to reclassify the pixels based on machine learning probabilities associated to each class and each pixel. The main rationale is to change those pixels classes with low certainty (high entropy) to the neighborhood classes with high certainty (low entropy) using a Bayesian inference. To reclassify pixels we used a 3x3 window from which we computed the neighborhood entropy. --- 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 csv file with the training data set (1,892 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)" |
| format | Dataset Open Access |
| id | pangaea_https___doi_org_10_1594_PANGAEA_895495 |
| institution | PANGAEA |
| language | en |
| publishDate | 2018 |
| publisher | PANGAEA |
| record_format | pangaea |
| spellingShingle | Land cover change maps for Mato Grosso State in Brazil: 2001-2017 (Version 2), links to files Câmara, Gilberto Picoli, Michelle Simoes, Rolf Maciel, Adeline Carvalho, Alexandre X Y Coutinho, Alexandre Esquerdo, Julio Antunes, Joao Begotti, Rodrigo Arvor, Damien Santos, Lorena Brazil; File content; File format; File name; File size; MatoGrosso; MULT; Multiple investigations; Uniform resource locator/link to file This data set includes yearly maps of land cover classification for the state of Mato Grosso, Brasil, from 2001 to 2017, based on MODIS image time series (collection 6) at 250 meter spatial resolution (product MOD13Q1). Ground samples consisting of 1,892 time series with known labels are used as training data for a support vector machine classifier. We used the radial basis function kernel, with cost C=1 and gamma = 0.01086957. The classes include natural and human-transformed land areas, discriminating among different agricultural crops in state of Land cover change maps for Mato Grosso State in BrazilMato 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 96% and the following user's and producer's accuracy for the land cover classes: Cerrado: UA - 98% PA - 99% Fallow_Cotton UA - 96% PA - 93% Forest UA - 99% PA - 98% Pasture UA - 97% PA - 98% Soy-Corn UA- 91% PA - 93% Soy-Cotton UA - 97% PA - 97% Soy-Fallow UA - 98% PA - 98% Soy-Millet UA- 90% PA - 89% Soy-Sunflower UA - 77% PA - 65% --- The correlation coefficients between the agricultural areas classified by our method and the estimates by IBGE (Brazil's Census Bureau) for the harvests from 2001 to 2017, were equal to 0.98. At state level the soybean, cotton, corn and sunflower areas had a correlation equal 0.97, 0.85, 0.98 and 0.80. The areas classified as forest were compared with the Hansen et al. (2013) mapping for the year 2000. In order to separate the forest areas, we examined the areas with more than 25% tree cover on the Hansen et al. (2013, doi:10.1126/science.1244693) map. We found that 99% of the pixels classified as forest match the pixels indicated by Hansen et al. (2013) as having more than 25% tree cover. When we joined the cerrado and forest classes, 84% of the pixels match the pixels by Hansen et al. (2013, doi:10.1126/science.1244693) as having more than 25% tree cover. The pixels labelled as pasture were compared to the pasture mapping done by Parente et al. (2017, doi:10.1016/j.jag.2017.06.003) . We found that 80% of the pixels classified as pasture match the pixels indicated by Parente et al. (2017, doi:10.1016/j.jag.2017.06.003) for the state of Mato Grosso. In the data set "Land cover change maps for Mato Grosso State in Brazil version 2", we analysed the samples from the clustering process using self-organizing maps. The samples with high level of confusion were removed from the dataset. In addition, we used a Bayesian smoothing method to reclassify the pixels based on machine learning probabilities associated to each class and each pixel. The main rationale is to change those pixels classes with low certainty (high entropy) to the neighborhood classes with high certainty (low entropy) using a Bayesian inference. To reclassify pixels we used a 3x3 window from which we computed the neighborhood entropy. --- 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 csv file with the training data set (1,892 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)" |
| title | Land cover change maps for Mato Grosso State in Brazil: 2001-2017 (Version 2), links to files |
| topic | Brazil; File content; File format; File name; File size; MatoGrosso; MULT; Multiple investigations; Uniform resource locator/link to file |
| url | https://doi.org/10.1594/PANGAEA.895495 |