Session Description

The EXCLAIM symposium is organised along a tutorial and four main topics. Please find the description of the individual topics below:

Tutorial - Machine learning for weather and climate

A machine learning revolution is underway in weather and climate, leveraging the trove of datasets and easy to use frameworks for building models. The EXCLAIM symposium will feature some of the state-of-the-art in this rapidly evolving domain. For experts in weather and climate this brings a new set of jargon and techniques to learn, but these can be learnt and there is a place for you in this revolution. In this tutorial we will break down the jargon and demystify machine learning for this domain. We will introduce the leading techniques in the field, discuss some of the outstanding challenges and highlight how you can engage in the revolution.

Speakers:

• Matthew Chantry (ECMWF) & Mihai Alexe (ECMWF)

Session A - Creating the foundations of AI-based modeling of weather and climate

Recent years have seen an explosion of new ideas and approaches of how AI-based methods can be used to model weather and climate. In this session, we invite contributions that focus on the methods and the foundations of AI in the field of weather and climate modeling. The breath of methods is wide, and can include methods that aim to emulate existing models, methods that aim to replace existing parameterizations, or methods that focus on equation discovery. We thereby welcome contributions across the full spectrum of implementation, including those that have already been applied successfully and those that are currently more at the conceptual level.

Keynotes in this session:

• Peter Düben:
  Yes - Al is a part of the Future of Weather and Climate Modeling

• Maria Molina:
  Machine Learning for Uncovering Patterns in the Earth Systems

Session B - Harnessing the power of AI in modeling weather and climate

The studies showing the power of GraphCast and other AI-based modeling approaches for weather and climate have had a transformative impact on the field. In this session, we invite contributions that demonstrate the power of AI in the modeling of weather and climate. The focus is on the scientific insight gained by following this approach, and the specific advantages and disadvantages emerging from the applications.

Keynotes in this session:

• Mike Pritchard:
  The ongoing potential of AI based weather & climate simulation
• Oliver Watt-Meyer
  The Ai2 Climate Emulator: Capabilities, Challenges and Opportunities

Session C - Harnessing the power of physics-based modeling of weather and climate

The capability of pushing physics-based models toward kilometer-scale grid spacing globally enables revolutionary insights into earth system processes. In this session, we invite contributions that demonstrate the power of high-resolution physics-based modeling of the earth system and its components and showcase insights that can be gained from this approach.

Keynotes in this session:

• Peter Caldwell:
  Km-Scale Physics-Based Model Projections are not only Possible, but also Necessary
• Cathy Hohenegger:
  Learning from kilometre-scale global simulations of the Earth System