Reduced order modeling of fluid flows: Machine learning, Kolmogorov barrier, closure modeling, and partitioning

Abstract

In this paper, we put forth a long short-term memory (LSTM) nudging framework for the enhancement of reduced order models (ROMs) of fluid flows utilizing noisy measurements. We build on the fact that in a realistic application, there are uncertainties in initial conditions, boundary conditions, model parameters, and/or field measurements. Moreover, conventional nonlinear ROMs based on Galerkin projection (GROMs) suffer from imperfection and solution instabilities due to the modal truncation, especially for advection-dominated flows with slow decay in the Kolmogorov width. In the presented LSTM-Nudge approach, we fuse forecasts from a combination of imperfect GROM and uncertain state estimates, with sparse Eulerian sensor measurements to provide more reliable predictions in a dynamical data assimilation framework. We illustrate the idea with the viscous Burgers problem, as a benchmark test bed with quadratic nonlinearity and Laplacian dissipation. We investigate the effects of measurements noise and state estimate uncertainty on the performance of the LSTM-Nudge behavior. We also demonstrate that it can sufficiently handle different levels of temporal and spatial measurement sparsity. This first step in our assessment of the proposed model shows that the LSTM nudging could represent a viable realtime predictive tool in emerging digital twin systems.

References in corpus (15)

• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Turbulence Modeling in the Age of Data
• Linear predictors for nonlinear dynamical systems: Koopman operator meets model predictive control
• Proper Orthogonal Decomposition Closure Models For Turbulent Flows: A Numerical Comparison
• Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• A deep learning enabler for non-intrusive reduced order modeling of fluid flows
• An artificial neural network framework for reduced order modeling of transient flows
• Time-series learning of latent-space dynamics for reduced-order model closure
• A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence
• Deep convolutional recurrent autoencoders for learning low-dimensional feature dynamics of fluid systems
• A stabilized proper orthogonal decomposition reduced-order model for large scale quasigeostrophic ocean circulation
• Proper orthogonal decomposition closure models for fluid flows: Burgers equation
• Memory embedded non-intrusive reduced order modeling of non-ergodic flows
• A Localized Reduced-Order Modeling Approach for PDEs with Bifurcating Solutions

Cited by in corpus (2)

• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number