Coarse-graining Hamiltonian systems using WSINDy

DA Messenger, JW Burby, DM Bortz - Scientific Reports, 2024 - nature.com
Weak form equation learning and surrogate modeling has proven to be computationally
efficient and robust to measurement noise in a wide range of applications including ODE …

Lie group forced variational integrator networks for learning and control of robot systems

V Duruisseaux, TP Duong, M Leok… - … for Dynamics and …, 2023 - proceedings.mlr.press
Incorporating prior knowledge of physics laws and structural properties of dynamical
systems into the design of deep learning architectures has proven to be a powerful …

Reduced-order model and attractor identification for large eddy simulation of squirrel cage fan

Q Xiao, B Jiang, X Yang, Y Ding, J Wang - Physics of Fluids, 2023 - pubs.aip.org
A large eddy simulation (LES) of a squirrel cage fan (SCF) provides a precise representation
of turbulent flows with different degrees of complexity. This study comprehensively analyzes …

Intelligent attractors for singularly perturbed dynamical systems

DA Serino, AA Loya, JW Burby, IG Kevrekidis… - arXiv preprint arXiv …, 2024 - arxiv.org
Singularly perturbed dynamical systems, commonly known as fast-slow systems, play a
crucial role in various applications such as plasma physics. They are closely related to …

Dynamics of McMillan mappings III. Symmetric map with mixed nonlinearity

T Zolkin, S Nagaitsev, I Morozov, S Kladov… - arXiv preprint arXiv …, 2024 - arxiv.org
This article extends the study of dynamical properties of the symmetric McMillan map,
emphasizing its utility in understanding and modeling complex nonlinear systems. Although …

Towards enforcing hard physics constraints in operator learning frameworks

V Duruisseaux, M Liu-Schiaffini, J Berner… - ICML 2024 AI for …, 2024 - openreview.net
Enforcing physics constraints in surrogate models for PDE evolution operators can improve
the physics plausibility of their predictions and their convergence and generalization …

Projected Neural Differential Equations for Learning Constrained Dynamics

A White, A Büttner, M Gelbrecht, V Duruisseaux… - arXiv preprint arXiv …, 2024 - arxiv.org
Neural differential equations offer a powerful approach for learning dynamics from data.
However, they do not impose known constraints that should be obeyed by the learned …

Latent space dynamics learning for stiff collisional-radiative models

X Xie, Q Tang, X Tang - Machine Learning: Science and …, 2024 - iopscience.iop.org
In this work, we propose a data-driven method to discover the latent space and learn the
corresponding latent dynamics for a collisional-radiative (CR) model in radiative plasma …

[图书][B] Symplectic Numerical Integration at the Service of Accelerated Optimization and Structure-Preserving Dynamics Learning

V Duruisseaux - 2023 - search.proquest.com
Symplectic numerical integrators for Hamiltonian systems form the paramount class of
geometric numerical integrators, and have been very well investigated in the past forty …