The Tree Cover Gain data set measures areas of tree cover gain across all global land (except Antarctica and other Arctic islands) at 30 × 30 meter resolution, displayed as a 12-year cumulative layer. The data were generated using multispectral satellite imagery from the Landsat 7 thematic mapper plus (ETM+) sensor. Over 600,000 Landsat 7 images were compiled and analyzed using Google Earth Engine, a cloud platform for earth observation and data analysis. The clear land surface observations (30 × 30 meter pixels) in the satellite images were assembled and a supervised learning algorithm was then applied to identify per pixel tree cover gain. Tree cover gain is defined as the establishment of tree canopy at the Landsat pixel scale in an area that previously had no tree cover. Tree cover gain may indicate a number of potential activities, including natural forest growth or the crop rotation cycle of tree plantations. The data set is encoded with values 0-1, where 0 represents pixels of no tree cover gain, and 1 indicates pixels of tree cover gain from 2001 to 2012 (note that tree cover gain is not an annual data set, and only extends to the year 2012).Accuracy and ValidationA validation assessment of the 2000-2012 Hansen/UMD/Google/USGS/NASA change data was carried out independently from the mapping exercise at the global and biome (tropical, subtropical, temperate, and boreal) scale. A stratified ransom sample (for no change, loss, and gain) of 1500 block, each 120 x 120 meters, was used as validation data. The amount of tree cover gain within each block was estimated using Landsat, MODIS, and Google Earth high-resolution imagery and compared to the map. Overall accuracies for gain were over 99.5% globally and for all biomes. However, since the overall accuracy calculation are positively skewed due to the high percentage of no change pixels, it is also important to assess the accuracy of the change predictions. The user's accuracy of the change predictions. The user's accuracy (i.e. the percentage of pixels labelled as tree cover gain that actually gained tree cover) was 87.8% at the global level. At the biome level, user's accuracies were 81.9%, 85.5%, 62.0%, and 76.7% for the tropical, subtropical, temperate, and boreal biomes, respectively. 

Dataset Attributes

Related Datasets