Kel Markert

In this session, we will build on what you've learned about Google's innovative “Model as Data” approach with Embedding Fields by showing the portability and usefulness of this dataset outside of Earth Engine. Why would you want to do this when the classification works so well in Earth Engine already?

Earth Engine is evolving towards seamless integration with diverse platforms, services, and data formats, with Python as the universal connector. Join us to explore recent improvements in Earth Engine's Python client library and gain hands-on experience using it in a notebook environment.

Many traditional scientific workflows are run with on-premise infrastructure and are not optimized to take full advantage of cloud computing resources. Furthermore, traditional workflows may not fit within the Earth Engine compute model.

Earth Engine has two primary interfaces: the JavaScript Code Editor and the Python client library. This session will help you understand the differences between the two and why you might use one over the other.

This session provides an overview of multiple datasets and applications for water detection from EO data with EE, including surface water occurrence and change mapping, coastal changes and bathymetry, moisture. Then the session provides a hands-on experience focusing on the waterbody dynamics and flood detection with optical multispectral and SAR satellite imagery.

Learn about the Earth Engine REST API that provides access to various Earth Engine functionality through a set of HTTP endpoints. We'll review the functionality that the API provides, and then do a hands-on session to help users enable it in their projects and make some HTTP calls to our service.