Buy your pass
OnlineDiscovery - AI and Climate Science

Grounding foundation models for automated climate science

  • Register

    Watch

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

    • Date
    17 November 2025
    Timeframe
    17:00 - 18:00 CET Geneva
    Duration
    60 minutes

    Despite the huge success of foundation models across fields, these models still suffer from hallucinations and can produce physically inconsistent outputs. To leverage foundation models for climate science, it is critical to integrate first principles and physical laws into the learning and reasoning of these models. This talk discusses an ongoing effort to ground foundation models, including diffusion models and large language models, for climate science. In particular, the presentation covers dynamics-informed diffusion models for emulating complex fluids and an adaptive framework for LLM agents to use scientific tools. Use cases are demonstrated involving the development of an autonomous LLM agent as a climate co-scientist.

     

    Session Objectives:

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

    • Identify the limitations of current foundation models in climate science.
    • Understand how integrating first principles and physical laws can ground diffusion models and LLMs for reliable scientific use.
    • Recognize emerging applications of autonomous LLM agents as climate co-scientists for simulation, reasoning, and tool use.
    • Share this session with your network
    Discover more from programme stream
    Discovery - AI and Climate Science
    Learning without labels: New insights into climate and extremes

    Learning without labels: New insights into climate and extremes

    16 December 2025 - 17:00 to 18:00

    Related stories

    Are you sure you want to remove this speaker?