Interpretable and efficient data-driven discovery and control of distributed systems

Today's article comes from the journal of Data-Centric Engineering. The authors are Wolf et al., from the Technical University of Darmstadt, in Germany. In this paper they're trying to bridge the gap between full-scale physics simulations and black-box learning. Their idea is to learn a small, simplified representation of a complex physical system, one that still captures how it responds to control.

DOI: 10.1017/dce.2025.10027