Learning from limited data in Earth system sciences: optimal selection of datasets and algorithms

Prof. in Dr.in Nikki Vercauteren, Dr.in Claudia Acquistapace & Prof. Dr. Aleksandar Bojchevski

5 - 7. November 2025, Cologne

Small data challenges are particularly common in Earth System Sciences. Examples include the study of rare and extreme events, which tend to have high societal impact but are often poorly forecasted by classical models. The workshop will discuss targeted machine learning methods for “small data” problems - when the underlying learning task is highly underdetermined, due to a large problem dimension relative to the size of training datasets. The goal is to bring together experts of data and computer sciences with experts of Earth system sciences that use and possibly develop such methods. We will discuss and identify:

•  Optimal selection or treatment of data: How can one augment the information content of the limited dataset by smart data selection or preprocessing approaches? How can one benefit from multiple data sources?
• Highly efficient approaches to the small data problem, as well as overfitting challenges in artificial intelligence.
• Techniques to study and improve reliability of machine learning methods and quantify uncertainty.
• Key challenges motivated by AI application in Earth system sciences.

You will find the registration information here soon.