From the 1 of 12 linked papers with an AI index.
12 papers
Origins and mitigation of double descent in reduced order modeling
Andrei A. Klishin, J. Nathan Kutz, Krithika Manohar
The paper investigates why double descent errors occur in reduced‑order models and proposes a data‑noise averaging framework to predict and mitigate these instabilities, demonstrat…
Real-time optimal control with shallow recurrent decoder networks
Matteo Tomasetto, Francesco Braghin, J. Nathan Kutz +1
Controlling dynamical systems in real-time across multiple scenarios is critical to enabling adaptive control strategies, ensuring stability and efficiency. However, to tailor cont…
PRONE: Petrov-Galerkin Operator Learning Unifies DMD, SINDy & Koopmanism
Matthew J. Colbrook, April Herwig, J. Nathan Kutz
Data-driven dynamics often asks how to linearize a nonlinear system. We ask instead: which observables should be advanced, and where should their futures live? This leads to Petrov…
Signature of glassy dynamics in dynamic modes decompositions
Zachary G. Nicolaou, Hangjun Cho, Yuanzhao Zhang +2
Glasses are traditionally characterized by their rugged landscape of disordered low-energy states and their slow relaxation towards thermodynamic equilibrium. Far from equilibrium,…
An Interpretable Data-Driven Model of the Flight Dynamics of Hawks
Lydia France, Karl Lapo, J. Nathan Kutz
Despite significant analysis of bird flight, generative physics models for flight dynamics do not currently exist. Yet the underlying mechanisms responsible for various flight mano…
Data-driven methods to discover stable linear models of the helicity injectors on HIT-SIU
Zachary L. Daniel, Alan A. Kaptanoglu, Christopher J. Hansen +3
Accurate and efficient circuit models are necessary to control the power electronic circuits found on plasma physics experiments. Tuning and controlling the behavior of these circu…