© Hansen/UMD/Google/USGS/NASA
Data in this layer were generated using multi-spectral satellite imagery from the Landsat 7 thematic mapper plus (ETM+) sensor. The clear surface observations from over 600,000 images were analysed using Google Earth Engine, a cloud platform for earth observation and data analysis, to determine per pixel tree cover using a supervised learning algor ...
Download Data (netCDF) Download Metadata (EML)
DOI: https://doi.org/10.1126/science.1244693
Big DataRemote SensingForest lossGoogleAIMachine LearningGlobal Change
| Title: | Forest loss year |
|---|---|
| Publication Year: | 2019 |
Creator
| Name: | Matthew Hansen |
|---|---|
| E-mail: | mhansen@umd.edu |
| Organisation: | University of Maryland |
Contact
| Name: | Matthew Hansen |
|---|---|
| E-mail: | mhansen@umd.edu |
| Organisation: | University of Maryland |
Essential Biodiversity Variables (EBVs)
| EBV class | Ecosystem structure |
|---|---|
| EBV name | Ecosystem distribution |
Spatial domain
| Spatial extent: | Global |
|---|---|
| Spatial resolution: | 1000 meter |
| Spatial accuracy: | 1000 meter |
Temporal domain
| Temporal resolution: | Yearly |
|---|---|
| Temporal extent: | From 2001-01-01 to 2018-01-01 |
Biological entity
| Entity type: | Ecosystem Types |
|---|
Environmental domain
| Realm: | Terrestrial |
|---|
Metric
| Name: | To be added soon |
|---|---|
| Description: | To be added soon |
Scenario
No scenario provided |
| License: | CC BY 4.0 |
|---|---|
| DOI: |
https://doi.org/10.1126/science.1244693 |
| External links to the project: |
https://earthenginepartners.appspot.com https://earthenginepartners.appspot.com/science-2013-global-forest/download_v1.7.html |
| Description: |
Data in this layer were generated using multi-spectral satellite imagery from the Landsat 7 thematic mapper plus (ETM+) sensor. The clear surface observations from over 600,000 images were analysed using Google Earth Engine, a cloud platform for earth observation and data analysis, to determine per pixel tree cover using a supervised learning algorithm. |
|---|---|
| Keywords: | Big DataRemote SensingForest lossGoogleAIMachine LearningGlobal Change |
EBV datasets YOU MAY ALSO LIKE
We use an existing spatially contiguous, global remote-sensing data product (i.e. the 27-year annual ESA CCI land cover maps which can be categorized as an EBV ‘Ecosystem Distribution’) to derive an annual ...
Changes in bird diversity at the grid cell level caused by land-use, estimated by the cSAR model (Pereira et al). It reports changes in species number (percentage and absolute), relative to 1900, for all bird s...
The modelled suitability for the EUNIS habitat types is an indication of where conditions are favourable for each habitat type based on verified sample plot data (Braun-Blanquet database) and the Maxent softwar...
Data on Area Of Habitat (AOH) for 5090 mammals from 2015 to 2100, in 5 year intervals.
© Stephan Hennekens/Wageningen University
Christian Langer
This is outstanding. Very useful to detect forest change around the world!
Sign in to post a comment for Forest loss year