Tag: google earth engine

World Resources Institute and Google announced 10m resolution global land cover data called Dynamic World powered by Google Earth Engine and AI Platform. Dynamic World is a 10m near-real-time LULC dataset that includes nine classes and available for the Sentinel-2 L1C collection from 2015 until today. The image here is the land cover map of Dhaka which once took me many hours to produce is now just clicks away.

Dynamic World allows researchers to build their own maps based on the outputs of our machine learning model, a major advancement in map making. Researchers can combine local information with the data from Dynamic World to produce a new map, for example a map that analyzes crop harvests between particular dates. Dynamic World is also useful for understanding longer-term trends of seasonal ecosystem change, as seen in the Okavango Delta, an area that attracts thirsty wildlife when it floods in July and August and then dries from September to October.

Google earth blog

The Geo for Good Summit for 2020 has announced several new features for the Google maps product. This year Google announced the REST API for Google Earth Engine which can be used to develop any custom app in any programming language. The REST API ensures several new features,

  • Monitor API Usage in Google Cloud Console – API usage can be monitored in the Google Cloud Console and assets may also be managed in the future with Cloud IAM.
  • Cloud IAM for managing asset access – Plan to migrate all Earth Engine ACL enforcement to Cloud IAM.  Allows for more sophisticated sharing between users, groups and organizations across individual assets and across an entire project.
  • Manage fine grain Earth Engine API usage with Cloud IAM – Individual API endpoints usage can be managed for users with a single Cloud Project. 

The presentation gives a demo showing how you can use this inside your custom app. Google also announced Cloud-Optimized GeoTIFF support for Earth Engine. Users can upload their COG to Google Cloud storage and call them using ee.Image.loadGeoTIFF. Checkout the full presentation here.