Neural Network

Learning without labels: New insights into climate and extremes

OnlineDiscovery - AI and Climate Science

  • Register

     

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

    • Date
    16 December 2025
    Timeframe
    17:00 - 18:00 CEST
    Duration
    60 minutes
    Share this session

    Climate variability and weather extremes pose profound challenges for prediction, preparedness, and resilience. Traditional approaches often rely on predefined indices or supervised learning methods, which can overlook unexpected patterns or reinforce biases inherent in labeled datasets. This keynote explores how unsupervised learning techniques can uncover hidden patterns in high-dimensional climate data. Recent innovations are highlighted that adapt established methods to reveal properties not captured by conventional architectures, offering new perspectives on modes of variability and extreme events.

    For instance, a knowledge-guided autoencoder can disentangle distinct Pacific climate models with differing spectral signatures, while a custom hyperparameter search can optimize self-organizing maps to produce smooth, interpretable pathways among weather regimes. Together, these advances help uncover processes and mechanisms that may underlie established climate and weather phenomena. Ultimately, unsupervised learning provides a powerful lens for scientific discovery, with implications for understanding, prediction, and decision-making in a changing climate. 

     

    Session Objectives:

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

    • Explain the limitations of traditional and supervised learning approaches in climate data analysis.
    • Describe how unsupervised learning techniques can reveal hidden patterns in high-dimensional climate datasets.
    • Illustrate recent innovations, such as knowledge-guided autoencoders and optimized self-organizing maps, for understanding climate variability and extreme events.
    • Share this session
    • Days
      Hours
      Min
      Sec
    Add to Calendar
    Discover more from programme stream
    Discovery - AI and Climate Science

    Grounding foundation models for automated climate science

    17 November 2025 - 17:00 to 18:00

    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?