Rangel Pinagé E; Keller M; Longo M; Peck C; Duffy P; Csillik O
BR-FNA; BR-FST; BR-XIN
Feliz Natal Municipality; Saracá-Taquera National Forest; Xingu Indigenous Territory
Model output; Remote sensing
Jan. 1, 2012
Dec. 31, 2020
Forest degradation by fires and selective logging is widespread in the Amazon region. We implemented a gradient boosted classification modeling framework to classify intact, logged, and burned forests at three Amazonian sites: Feliz Natal Municipality and Xingu Indigenous Territory in Mato Grosso State, and Saracá-Taquera National Forest in Pará State. We used forest degradation history from Landsat time-series as reference data and textural metrics derived from PlanetScope images as predictors. Textural metrics were computed using the Gray-Level Co-Occurrence Matrix (GLCM) textural technique. Included in the attached zip file are ten files:
- a shapefile containing the reference data (fire and selective logging polygons and year of event) for each site;
- a multiband tif file containing the 8 GLCM metrics used as predictors (Mean, Variance, Homogeneity, Contrast, Dissimilarity, Entropy, Angular Second Moment, Correlation) at the original PlanetScope resolution (3.125m) for each site;
- a multiband tif file containing the 72 aggregated GLCM metrics used as predictors (Mean, Variance, Homogeneity, Contrast, Dissimilarity, Entropy, Angular Second Moment, and Correlation aggregated using the mean, first quartile, third quartile, maximum, median, minimum, root mean square, standard deviation, and skewness statistics) at 562m resolution for each site;
- a multiband tif file containing the 3 probability grids for either intact, logged, or burned forests at the aggregation resolution (562m) for each site.
Version 2 of this dataset contains minor changes from the review process of the associated publication.
The shapefiles with the reference data were generated from the visual interpretation of Landsat images.
Textural metrics were computed using the Gray-Level Co-Occurrence Matrix (GLCM) textural technique on the Enhanced Vegetation Index (EVI) derived from PlanetScope images. These computations were performed in the R statistical environment using the glcm package. The GLCM metrics were later aggregated to a coarser resolution using GDAL.
The grid data containing the forest degradation class probability were generated using the described modeling framework.
Oregon State University; USDA Forest Service; Jet Propulsion Laboratory; Lawrence Berkeley National Laboratory; Neptune and Company, Inc.
Rangel Pinagé, Ekena - Oregon State University ([email protected])
Rangel Pinagé E; Keller M; Longo M; Peck C; Duffy P; Csillik O (2023): Reference data, predictors, and probability grids for forest degradation classes in three sites in the Brazilian Amazon. 2.0. NGEE Tropics Data Collection. (dataset). https://doi.org/10.15486/ngt/1872685
Planet data access for the generation of the GLCM metrics was provided through the NASA Commercial SmallSat Data Acquisition (CSDA) Program. Funding for NGEE-Tropics data resources was provided by the U.S. Department of Energy Office of Science, Office of Biological and Environmental Research.
Data Link: Download Dataset
This are no dataset references available.