Digital Twin Sandbox
Have you always wanted to test your machine learning algorithm at the global scale but lacked a clean, cloudless dataset? Now we are offering you one, openly available. And it looks beautiful.
Build just about any global scale application with the publicly available, harmonized yearly stack of data. The 120-meter resolution data is free of clouds and free of most of the remote sensing complexity, making the collection easy to use regardless if you're an expert building large-scale machine learning models, or just an enthusiast observing global phenomena.
Deep Learning Approach for Crop Type Mapping
GEM takes advantage of the large volumes of available EO, weather, climate and other non- EO data to establish economically viable continuous monitoring of the Earth. As part of GEM, the development of scalable and cost-effective solutions is being tested on various use-cases, which include also crop identification.
Read more about this in our article A Deep Learning Approach for Crop Type Mapping Based on Combined Time Series of Satellite and Weather Data.
Watch our presentation!
GEM at the Living Planet Symposium 2022
It was a pleasure to participate in the European Space Agency’s Living Planet Symposium in Bonn, Germany in May 23-27. GEM was presented during the poster session on the third day. The Symposium with more than 4,700 registered atendees was a great opportunity to highlight the project's objectives, platform and use cases.
See the GEM poster here and the LPS22 page for more information.