Search
Buy your pass
OnlineDiscovery - AI for Earth and Sustainability Science Badge available

Distributional robustness for climate change

  • Register

     

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

    • Date
    26 February 2026
    Timeframe
    16:00 - 17:00 CET
    Duration
    60 minutes
    • Days
      Hours
      Min
      Sec

    Detection and attribution (D&A) of climate change aims to understand the causal links between external drivers of the climate system, such as greenhouse gases or aerosols, and observed changes in climate variables, including temperature and precipitation. Changes in these external factors can affect the reliability of conclusions drawn from supervised machine learning and statistical learning methods.

    This talk approaches climate change detection from the perspective of robustness to interventions, and more specifically, distributional robustness to shifts in the external forcings. The goal is to develop models that generalize well to changes in external conditions. It is shown that explicitly accounting for such interventions leads to more reliable detection of key climate drivers from temperature observations, even under strong variations in other forcings.

    Overall, the results highlight the importance of distributional robustness for climate change detection in the presence of complex and evolving external influences.

     

    Session Objectives:

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

    • Understand the main concepts employed in detection and attribution of climate change.
    • Identify and understand the impact of interventions and their relevance for climate science.
    • Identify links between distributional robustness and causal inference.

    Recommended Mastery Level/Prerequisites:

    • Basic understanding of statistical and machine learning concepts.
    • Familiarity with climate data is beneficial.
    • Optional: Prior exposure to causal inference.
    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
    Fine-scale environmental suitability mapping of Aedes aegypti

    Fine-scale environmental suitability mapping of Aedes aegypti

    4 February 2026 - 16:00 to 17:00

    Distributional robustness for climate change

    Distributional robustness for climate change

    26 February 2026 - 16:00 to 17:00

    Related stories

    Are you sure you want to remove this speaker?