Blar i Institutt for teknisk kybernetikk på tidsskrift "Physics of Fluids"
Viser treff 1-10 av 10
-
A deep learning enabler for non-intrusive reduced order modeling of fluid flows
(Journal article; Peer reviewed, 2019)In this paper, we introduce a modular deep neural network (DNN) framework for data-driven reduced order modeling of dynamical systems relevant to fluid flows. We propose various DNN architectures which numerically predict ... -
Data-driven recovery of hidden hysics in reduced order modeling of fluid flows
(Peer reviewed; Journal article, 2020)In this article, we introduce a modular hybrid analysis and modeling (HAM) approach to account for hidden physics in reduced order modeling (ROM) of parameterized systems relevant to fluid dynamics. The hybrid ROM framework ... -
Data-driven recovery of hidden physics in reduced order modeling of fluid flows
(Peer reviewed; Journal article, 2020)In this article, we introduce a modular hybrid analysis and modeling (HAM) approach to account for hidden physics in reduced order modeling (ROM) of parameterized systems relevant to fluid dynamics. The hybrid ROM framework ... -
Feature engineering and symbolic regression methods for detecting hidden physics from sparse sensor observation data
(Peer reviewed; Journal article, 2020)We put forth a modular approach for distilling hidden flow physics from discrete and sparse observations. To address functional expressiblity, a key limitation of the black-box machine learning methods, we have exploited ... -
Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows
(Peer reviewed; Journal article, 2020)Reduced rank nonlinear filters are increasingly utilized in data assimilation of geophysical flows but often require a set of ensemble forward simulations to estimate forecast covariance. On the other hand, predictor–corrector ... -
Memory embedded non-intrusive reduced order modeling of non-ergodic flows
(Journal article; Peer reviewed, 2019)Generating a digital twin of any complex system requires modeling and computational approaches that are efficient, accurate, and modular. Traditional reduced order modeling techniques are targeted at only the first two, ... -
Model fusion with physics-guided machine learning: Projection-based reduced-order modeling
(Journal article; Peer reviewed, 2021)The unprecedented amount of data generated from experiments, field observations, and large-scale numerical simulations at a wide range of spatiotemporal scales has enabled the rapid advancement of data-driven and especially ... -
Nonlinear proper orthogonal decomposition for convection-dominated flows
(Peer reviewed; Journal article, 2021)Autoencoder techniques find increasingly common use in reduced order modeling as a means to create a latent space. This reduced order representation offers a modular data-driven modeling approach for nonlinear dynamical ... -
On closures for reduced order models— A spectrum of first-principle to machine-learned avenues
(Peer reviewed; Journal article, 2021)For over a century, reduced order models (ROMs) have been a fundamental discipline of theoretical fluid mechanics. Early examples include Galerkin models inspired by the Orr–Sommerfeld stability equation and numerous vortex ... -
Physics guided machine learning using simplified theories
(Peer reviewed; Journal article, 2021)Recent applications of machine learning, in particular deep learning, motivate the need to address the generalizability of the statistical inference approaches in physical sciences. In this Letter, we introduce a modular ...