Greg Cocks Annual 30 Metre Maps Of Global Grassland Class And Extent (2000–2022) Based On Spatiotemporal Machine Learning
--
https://doi.org/10.1038/s41597-024-04139-6 <-- shared paper
--
https://landcarbonlab.org/insights/first-global-annual-cultivated-natural-grassland-data/ <-- blog post
--
https://developers.google.com/earth-engine/datasets/publisher/global-pasture-watch <-- Google EarthEngine
--
https://github.com/wri/global-pasture-watch <-- GitHub Repository
--
#GIS #spatial #mapping #workflow #global #grassland #shrubland #vegetation #spatialanalysis #AI #machinelearning #spatiotemporal #remotesensing #earthobservation #GLAD #landsat #imagery #opendata #landcover #agriculture #change #natural #model #modeling #pasture #cultivated #GlobalPastureWatch #grazing #livestock
Recent searches
Search options
Administered by:
#globalpasturewatch
Within the #GlobalPastureWatch (https://LandCarbonLab.org/data) project we are building global open data sets at 30-m resolution to help World Resources Institute produce most accurate and most up-to-date maps of pastures and grasslands including changes in canopy height and monthly GPP. The LandCarbonLab.org project specifically aims at deploying solutions for sustainable landscapes on the ground across boundaries.
We are processing global 1997-2022+ Landsat images to produce complete, consistent, current & correct (cloud-free) mosaics per continent & globally. Our interest is primarily in monthly / bimonthly values, then we plan to use these to quantify vegetation, map pasture types, crops / land cover, tillage intensity, dynamic soil properties and similar. Read more in: https://opengeohub.org/article/analysis-ready-and-cloud-optimized-arco-landsat-data-for-all/ #OpenEarthMonitor #AI4soilhealth #globalpasturewatch