Search
Buy your pass
OnlineDiscovery - GeoAI Badge available

GeoAI in Earth Engine: AlphaEarth Foundations and the Satellite Embedding dataset

  • Register

     

    * Register (or log in) to the Neural Network to add this session to your agenda or watch the replay

    • Date
    14 January 2026
    Timeframe
    14:30 - 16:30 CET Geneva
    Duration
    120 minutes
    • Days
      Hours
      Min
      Sec

    Modern geospatial data archives house petabytes of Earth observation imagery, yet transforming raw pixels into accurate and actionable insights remains an ongoing challenge. This hands-on session introduces Google’s new Satellite Embedding dataset, a revolutionary image collection that leverages multi-source, multimodal deep learning to help participants create better maps faster with fewer manual annotations. The session will start with a brief overview of AlphaEarth Foundations, a new AI embedding model developed by Google DeepMind that was used to generate the Satellite Embedding dataset. The session will then explore the AlphaEarth Foundations embedding space, explain how Satellite Embeddings can be used for pixel-based similarity search, and implement a basic supervised classification workflow using the Earth Engine API. Participants are invited to learn how AlphaEarth Foundations and the Satellite Embedding dataset can help accelerate mapping and monitoring workflows, with no deep learning experience required.

     

    Session Objectives:

    By the end of this session, participants will be able to:

    • Describe the core capabilities and differentiating characteristics of the AlphaEarth Foundations model and Satellite Embedding dataset.
    • Interactively explore the AlphaEarth Foundations embedding space.
    • Implement an embeddings-based similarity search.
    • Develop a supervised classification workflow using the Earth Engine API.

    Recommended Mastery Level / Prerequisites:

    • This session is open and accessible to anyone who’s interested in learning more about AlphaEarth Foundations and the Satellite Embedding dataset.
    • General familiarity with satellite imagery, Earth Engine, and classific ML techniques is helpful but not required.
    • To get the most out of the hands-on portions, an Earth Engine account is strongly recommended. See earthengine.google.com for more information on how to sign up.
    • Recommended reading: Google DeepMind blog on AlphaEarth Foundations, Earth Engine Medium post on the Satellite Embedding dataset, and the AlphaEarth Foundations publication. Those newer to working with embeddings may also want to read this more general post on vector embeddings.
    Share this session with your network
    • Session starts in
      Days
      Hours
      Min
      Sec
    Add to Calendar
    Discover more from programme stream
    Discovery - GeoAI
    GeoAI in Earth Engine: AlphaEarth Foundations and the Satellite Embedding...

    GeoAI in Earth Engine: AlphaEarth Foundations and the Satellite Embedding...

    14 January 2026 - 14:30 to 16:30

    Introduction to TESSERA: Time-series embeddings for geospatial analysis

    Introduction to TESSERA: Time-series embeddings for geospatial analysis

    22 January 2026 - 14:00 to 15:00

    Hands-on TESSERA: Time-series embeddings for geospatial analysis

    Hands-on TESSERA: Time-series embeddings for geospatial analysis

    2 February 2026 - 14:00 to 15:30

    Embedding workflows for Earth Observation tasks

    Embedding workflows for Earth Observation tasks

    25 February 2026 - 14:00 to 15:30

    Introduction to Terratorch

    Introduction to Terratorch

    19 March 2026 - 14:00 to 15:30

    Related stories

    Are you sure you want to remove this speaker?