Dimensionality reduction is the essence of many data processing problems, including
filtering, data compression, reduced-order modeling and pattern analysis. While traditionally …

Computational fluid dynamics (CFD) is known for producing high-dimensional
spatiotemporal data. Recent advances in machine learning (ML) have introduced a myriad …

ABSTRACT A primary spectral submanifold (SSM) is the unique smoothest nonlinear
continuation of a nonresonant spectral subspace E of a dynamical system linearized at a …

Numerical simulations of multiphase flows are crucial in numerous engineering applications,
but are often limited by the computationally demanding solution of the Navier–Stokes (NS) …

Reduced-order models (ROMs) can effectively balance the accuracy and efficiency of
computational fluid dynamics (CFD). The nonlinear flow field characteristics cannot be …

In this study we propose a novel data-driven reduced-order model for complex dynamics,
including nonlinear, multi-attractor, multi-frequency and multiscale behaviours. The starting …

We propose the first machine-learned control-oriented flow estimation for multiple-input,
multiple-output plants. The starting point is constant actuation with open-loop actuation …

In the face of mounting economic constraints, researchers are increasingly turning to data-
driven methods for reconstructing unknown global fields from limited data. While traditional …

Physics-informed neural networks (PINNs) are function approximators that can incorporate
physics laws during training. In recent years, PINNs have been shown to be capable of …

Uniform flow past side-by-side circular cylinders is a classical fluid dynamic model that
triggers rich phenomena, from which asymmetric wakes usually emerge. Such asymmetry …