4 papers
Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamics
Katherine Rosenfeld, Maike Sonnewald
Generative AI emulators are increasingly used in scientific domains where we already have strong theory, benchmarks, and physical intuition. This raises a central evaluation and in…
OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting
Sanah Suri, Kieran Ringel, Maike Sonnewald
Extreme ocean phenomena are challenging not only to predict but to diagnose, as accurate forecasts alone do not reveal the underlying physical drivers. While recent machine learnin…
Setting the Standard: Recommended Practices for Data Preprocessing in Data-Driven Climate Prediction
Jason C. Furtado, Maria J. Molina, Marybeth C. Arcodia +12
Artificial intelligence (AI) - and specifically machine learning (ML) - applications for climate prediction across timescales are proliferating quickly. The emergence of these meth…
Unveiling 3D Ocean Biogeochemical Provinces in the North Atlantic: A Systematic Comparison and Validation of Clustering Methods
Yvonne Jenniges, Maike Sonnewald, Sebastian Maneth +2
Defining ocean regions and water masses helps to understand marine processes and can serve downstream tasks such as defining marine protected areas. However, such definitions often…