Machine learning and climate change: learning from present-day observations to predict the future

Go back to programme

Machine learning and climate change: learning from present-day observations to predict the future

  • Watch

    * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

  • Global climate change projections are still subject to substantial modelling uncertainties. A variety of Emergent Constraints (ECs) have been suggested to address these uncertainties, but they remain heavily debated in the scientific community. Still, the central idea behind ECs to relate future projections to already observable quantities has no real substitute.  

    Here we discuss machine learning (ML) approaches for new types of controlling factor analysis (CFA) as a promising alternative. The principal idea is to use ML to find climate-invariant relationships in historical data, which also hold approximately under strong climate change scenarios. On the basis of existing big data archives, these climate-invariant relationships can be validated in perfect-climate-model frameworks.  

    From a ML perspective, we argue that CFA is more promising for three reasons: (a) it can be objectively validated both for past data and future data and (b) it provides more direct – by design physically-plausible – links between historical observations and potential future climates compared to ECs and (c) it can take higher-dimensional relationships into account that better characterize the complex nature of the multi-scale climate system. We highlight these advantages for two recently published examples in the form of constraints on climate feedback mechanisms (clouds, stratospheric water vapour). 

    This live event includes a 15-minute networking event hosted on the AI for Good Neural Network. This is your opportunity to ask questions, interact with the panelists and participants and build connections with the AI for Good community.

    Share this session
    • Watch

      Register

      * Register (or log in) to the AI4G Neural Network to add this session to your agenda or watch the replay

    • Start date
      13 March 2024 at 17:00 CET Geneva | 12:00-13:15 EDT, New York | 00:00-01:15 CST, Beijing
    • End date
      13 March 2024 at 18:15 CET Geneva | 12:00-13:15 EDT, New York | 00:00-01:15 CST, Beijing
    • Duration
      75 minutes (including 15 minutes networking)
    • Topics
    • UN SDGs

    Are you sure you want to remove this speaker?