The European Space Agency has released the WorldCover 2021 map based on Sentinel-1 and Sentinel-2 constellations with 11 classes, 10m resolution and 77% accuracy independently validated.
Sentinel-2
- This project maps tree extent at the ten-meter scale using open source artificial intelligence and satellite imagery. Learn more here.
- Sen4AgriNet is a harmonized multi-country, multi-temporal benchmark dataset for agricultural earth observation machine learning applications. Learn more here.
- Dynamic World provides global, near real-time land cover data at a 10 meter resolution, giving an unprecedented level of detail about what's on the land and how it's being used.
- This workflow generates automatic contours for agricultural parcels, given Sentinel-2 images. It uses Sentinel Hub to download the imagery and a ResUnet-a architecture.
- This article explains how to train a segmentation model for classifying the use of cropland, based on a land cover dataset for South America.
- This video shows you how to use the STAC API Browser Plugin in QGIS to search for Sentinel-2 or Landsat images for an AOI and load the images as Cloud Optimized GeoTIFFs (COGs).
- Check here for a dual stream U-Net architecture method for urban change detection using Sentinel-1 and Sentinel-2 data fusion.
- Looking for some analysis-ready earth observation data for Europe? Here you can find 210GB of cloud/artifact-free Sentinel-2 images at 30m from 2018 to 2020 and available as cloud-optimized GeoTIFFs.
