[ivory-search id="3463" title="Default Search Form"]
Search
Register here
Search
Type below to search:
OnlineDiscovery - AI for Earth and Sustainability Science Badge available

AI for fast and flexible climate modeling

  • Register

     

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

    • Date
    18 March 2026
    Timeframe
    17:00 - 18:00 CET
    Duration
    60 minutes
    • Days
      Hours
      Min
      Sec

    AI-driven weather forecast models are now more accurate and faster than the best physics-based systems. Extending these advances to seamless weather-climate prediction poses broader challenges, but progress is rapid. Several models trained on ERA5 capture historical variability and trends. The key question is whether such systems can generalize to project future climate reliably. Purely data-driven extrapolation remains elusive, but emulators of physics-based models trained across multiple climates are emerging as a promising route. These can generate ensembles of ocean-coupled simulations that are statistically consistent with their reference models but at orders-of-magnitude lower cost.

    The author presents results from the open-source Ai2 Climate Emulator (ACE). ACE emulates daily weather variability and climate at 100 km resolution, running ~1500 years/day on a single GPU, about 100× faster than comparable physics-based models. It can be trained on ERA5 or AMIP-style forcings, paired with AI downscaling to km-scale weather, or coupled to slab-ocean models to capture climate change responses. Most recently, when coupled to Samudra, a full-depth ocean emulator, ACE reproduced stable coupled climate states and realistic El Niño–Southern Oscillation variability. Together, these advances point to AI emulators enabling the rapid generation of climate prediction information for a wide range of user-specific needs.

     

    Session Objectives:

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

    • Understand the principles of AI-driven climate emulation and its advantages over traditional physics-based models.
    • Analyze historical climate data and AI emulator outputs to assess model fidelity and limitations.
    • Apply AI emulators (e.g., ACE) to generate climate simulations under varying scenarios.
    • Evaluate the potential and constraints of AI-based models for future climate projections.
    • Design workflows integrating AI emulation with downscaling and coupled ocean models for research applications.

     

    Recommended Mastery Level/Prerequisites:

    • Graduate-level understanding of climate science, atmospheric dynamics, or Earth system modeling.
    • Familiarity with Python and machine learning frameworks is recommended but not mandatory.
    • Basic knowledge of numerical weather prediction and climate modeling concepts is helpful.
    Share this session with your network
    • Session starts in
      Days
      Hours
      Min
      Sec
    Add to Calendar
    Discover more from programme stream
    Discovery - AI for Earth and Sustainability Science
    Deadtrees.earth: Crowdsourced drone data for global tree mortality maps

    Deadtrees.earth: Crowdsourced drone data for global tree mortality maps

    4 March 2026 - 16:00 to 17:00

    AI for fast and flexible climate modeling

    AI for fast and flexible climate modeling

    18 March 2026 - 17:00 to 18:00

    Related stories

    Are you sure you want to remove this speaker?