Earth observation foundation models with Prithvi-EO-2.0 and TerraTorch

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

  • Date
    19 March 2025
    Timeframe
    15:00 - 17:00 CET Geneva
    Duration
    2 hours
    Share this session

    Would you like to enhance your skills in leveraging state-of-the-art geospatial foundation models? Are you familiar with basic concepts of machine learning and Earth observation data? Then this hands-on workshop is perfect for you. It introduces how to utilize the powerful Prithvi-EO-2.0 foundation model with TerraTorch to perform flexible geospatial tasks. 

    Workshop Focus Areas 

    The workshop will cover three key use cases: 

    1. Image Classification: Learn to classify satellite imagery for land cover mapping. 
    1. Segmentation: Explore techniques for precise delineation of geographical features. 
    1. Regression: Discover how to predict continuous variables from satellite data. 

    Tools and Frameworks 

    Participants will gain hands-on experience with: 

    • Prithvi-EO-2.0: A state-of-the-art geospatial foundation model trained on diverse Earth observation data. 
    • TerraTorch: An efficient, open-source framework for geospatial deep learning developed by IBM. 
    • Practical Applications: Real-world scenarios demonstrating the power of geospatial AI. 

    Workshop Agenda 

    Part 1: Introduction to Prithvi-EO-2.0 and TerraTorch 

    • Overview of Prithvi-EO-2.0. 
    • Setting up your environment. 
    • Basic usage of TerraTorch. 

    Part 2: Hands-on Sessions 

    Participants will be provided with an environment to run their code and notebooks tailored to explore the following tasks: 

    • Image Classification: Perform land cover mapping using satellite imagery. 
    • Segmentation: Extract and delineate geographical features with precision. 
    • Regression: Predict environmental variables from satellite data. 

    Workshop assistants: Benedikt Blumenstiel, Romeo Kienzler, Blair Edwards.

    Please post in the Neural Network chat any questions you may have during the lab

    Key Takeaways 

    Participants will come away from the workshop understanding how to setup and use the TerraTorch environment, load and preprocess satellite imagery, fine-tune Prithvi-EO-2.0, as an example of one of the foundation models available in TerraTorch, for different AI tasks, and evaluate the model performance. 

    Participation

    Anyone with basic skills of machine learning is invited to register and participate in this workshop. However, support for cloud credits to follow along the labs will be restricted to 200 on first come first serve basis. The first 200 registered users will be asked to provide a GitHub handle and will be able to get AWS resources. Other users will be provided a notebook on Colab for people to follow the training. 

  • Share this session
    Discover more from programme stream
    Optimizing zero-shot segmentation of Remote Sensing imagery using LangRS: A...

    Optimizing zero-shot segmentation of Remote Sensing imagery using LangRS: A...

    22 May 2025 - 14:30 to 16:00