Statistics and AI for weather and climate science

March 9-11, 2027

Heidelberg, Germany

Photo credit: T. Schwerdt / HAdW

About the workshop

AI is transforming weather and climate science as AI-based weather and climate models now rival their physics-based counterparts on various standard benchmarks while producing forecasts at a fraction of the computational cost. However, many important questions remain beyond overall prediction skills. How reliable are their forecasts for extreme events, particularly for those outside their training range? Can they capture spatio-temporal and inter-variable dependence, and are their forecasts physically consistent? How well do they quantify uncertainty? What strengths of physics-based models do they still lack?

Answering these questions is essential for understanding how AI-based and physics-based numerical models differ, identifying where AI models could be further improved, and building trust in using AI weather and climate models for scientific discovery and operational forecasting. However, the mathematical and statistical tools to address these questions remain underdeveloped.

This workshop brings together researchers from applied mathematics, statistics, atmospheric and Earth sciences, and computer science to foster interdisciplinary discussions on these challenges and deepen our understanding of AI weather and climate models.

Speakers

We are happy that the following invited speakers have confirmed their participation in the workshop:

Call for abstracts

Application for in-person participation in the workshop is now open at: https://indico.kit.edu/event/5779/registrations/1113/. Please consider presenting your current research and submit an abstract. Due to the size of the venue, we can accept only limited number of applications.

We have limited funding available for participants whose travel costs cannot be covered by their own institutions. If you would like to apply for the funding, please specify how much you need in the application form.

The application deadline is Nov. 23, 2026.

Venue

The workshop will be held in the Heidelberg Academy of Sciences and Humanities (address: Karlstraße 4, 69117 Heidelberg).

If you travel by train, you can choose to get off at either the Heidelberg Central Station or the Heidelberg-Altstadt S-Bahn station. From the Central train station, you can take bus lines 20, 32, and 735, and get off at either Neckarmünzplatz or Rathaus/Bergbahn. From the Heidelberg-Altstadt S-Bahn station, you can walk to the Academy or take bus lines 20 or 33.

Organizers and sponsors

The workshop is organized by Zhongwei Zhang (KIT) and Sebastian Lerch (Marburg University). We are very grateful for the funding from the Heidelberg Academy of Sciences and Humanities, the Helmholtz Information and Data Science Academy, and the MathSEE Center at KIT.