2023-05-04T13:11:58.897140

2023-05-04T13:11:58.897141

30

30 degrees north to 30 degrees south

Updated weekly

regional

Use the following credit when these data are displayed: Source: GLAD/UMD, accessed through Global Forest Watch Use the following credit when these data are cited: Hansen, M.C., A. Krylov, A. Tyukavina, P.V. Potapov, S. Turubanova, B. Zutta, S. Ifo, B. Margono, F. Stolle, and R. Moore. 2016. Humid tropical forest disturbance alerts using Landsat data. *Environmental Research Letters*, 11 (3). Accessed through Global Forest Watch on [date]. www.globalforestwatch.org

GLAD alerts

Hansen, M.C., A. Krylov, A. Tyukavina, P.V. Potapov, S. Turubanova, B. Zutta, S. Ifo, B. Margono, F. Stolle, and R. Moore. 2016. Humid tropical forest disturbance alerts using Landsat data. *Environmental Research Letters*, 11 (3).

[CC BY 4.0](https://creativecommons.org/licenses/by/4.0/)

English

This data set, created by the [GLAD](http://glad.geog.umd.edu/) (Global Land Analysis & Discovery) lab at the University of Maryland and supported by Global Forest Watch, is the first Landsat-based alert system for tree cover loss. While most existing loss alert products use 250-meter resolution MODIS imagery, these alerts have a 30-meter resolution and thus can detect loss at a much finer spatial scale. The alerts are operational for land areas between 30 degrees north and south. New Landsat 7 and 8 images are downloaded as they are posted online, assessed for cloud cover or poor data quality, and compared to the three previous years of Landsat-derived metrics (including ranks, means, and regressions of red, infrared and shortwave bands, and ranks of NDVI, NBR, and NDWI). The metrics and the latest Landsat image are run through seven decision trees to calculate a median probability of forest disturbance. Pixels with probability >50% are reported as tree cover loss alerts. The entire process is run in [Google Earth Engine](https://earthengine.google.com/) to ensure reliable updates and scalability. For more information on methodology, see the [paper in Environmental Research Letters](http://iopscience.iop.org/article/10.1088/1748-9326/11/3/034008). Alerts are not classified as high confidence until two or more out of four consecutive observations are labelled as tree cover loss. Alerts are removed from the dataset after four consecutive observations or more than 180 days if they are not classified as high confidence. You can choose to view only high confidence alerts in the menu, though keep in mind that using only high confidence alerts misses the newest detections of tree cover loss.

Identifies areas of likely tree cover loss in near-real time

While Landsat 7 and 8 satellites together have a revisit period of 8 days, cloud cover can majorly limit the availability of imagery, particularly in the wet season. Alert dates represent the instance of detection, though tree cover loss could have taken place earlier, possibly weeks earlier, due to persistent cloud cover. In this data set, 'tree cover' is defined as all vegetation greater than 5 meters in height with greater than 60% canopy cover, and may take the form of natural forests or plantations. 'Tree cover loss' indicates the canopy removal of at least half a pixel and can be due to a variety of factors, including mechanical harvesting, fire, disease, or storm damage. As such, 'loss' does not equate to deforestation. In Peru, where the alert system was first developed, the authors evaluated the data to have 13.5 percent false positives (loss detected where none occurred), though the majority of those false positives (9.5 percent) occur on the edges of clearings. On edges, the 30 meter Landsat pixels show a mix of forest and other land cover, which makes them prone to error in the system. The rate of false positives drops to 1 percent when only considering high confidence alerts. The data has 33 percent false negatives (undetected loss where it has occurred), though most of these occur in secondary forests likely because the algorithm was created to capture primary forest loss. The higher rate of false negatives compared to false positives also indicates that the alerts are a conservative estimate of the tree cover loss that is actually occurring. When zoomed out, this data layer displays some degree of inaccuracy because the data points must be collapsed to be visible on a larger scale. Zoom in for greater detail.

Forest Change

Getting even nearer to real-time, first data set of Landsat alerts!

http://iopscience.iop.org/article/10.1088/1748-9326/11/3/034008

f272d653-5675-4971-966f-1446a33e4896