A non-intrusive reduced order modeling framework for quasi-geostrophic turbulence

Abstract

In this study, we present a non-intrusive reduced order modeling (ROM) framework for large-scale quasi-stationary systems. The framework proposed herein exploits the time series prediction capability of long short-term memory (LSTM) recurrent neural network such that: (i) in the training phase, the LSTM model is trained on the modal coefficients extracted from the high-resolution data using proper orthogonal decomposition (POD) transform, and (ii) in the testing phase, the trained model predicts the modal coefficients for the total time recursively based on the initial time history. To illustrate the predictive performance of the proposed framework, the mean flow fields and time series response of the field values are reconstructed from the predicted modal coefficients by using an inverse POD transform. As a representative benchmark test case, we consider a two-dimensional quasi-geostrophic (QG) ocean circulation model which, in general, displays an enormous range of fluctuating spatial and temporal scales. We first illustrate that the conventional Galerkin projection based ROM of such systems requires a high number of POD modes to obtain a stable flow physics. In addition, ROM-GP does not seem to capture the intermittent bursts appearing in the dynamics of the first few most energetic modes. However, the proposed non-intrusive ROM framework based on LSTM (ROM-LSTM) yields a stable solution even for a small number of POD modes. We also observe that the ROM-LSTM model is able to capture quasi-periodic intermittent bursts accurately, and yields a stable and accurate mean flow dynamics using the time history of a few previous time states, denoted as the lookback time-window in this paper. Our findings suggest that the proposed ROM framework is capable of predicting noisy nonlinear fluid flows in an extremely efficient way compared to the conventional projection based ROM.

References in corpus (25)

• LSTM: A Search Space Odyssey
• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Spectral proper orthogonal decomposition
• Proper Orthogonal Decomposition Closure Models For Turbulent Flows: A Numerical Comparison
• Data-Driven Forecasting of High-Dimensional Chaotic Systems with Long Short-Term Memory Networks
• Hybrid Forecasting of Chaotic Processes: Using Machine Learning in Conjunction with a Knowledge-Based Model
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• On the need for a nonlinear subscale turbulence term in POD models as exemplified for a high Reynolds number flow over an Ahmed body
• A neural network approach for the blind deconvolution of turbulent flows
• An artificial neural network framework for reduced order modeling of transient flows
• Deep Learning for Time-Series Analysis
• Multistep Neural Networks for Data-driven Discovery of Nonlinear Dynamical Systems
• A Deep Learning based Approach to Reduced Order Modeling for Turbulent Flow Control using LSTM Neural Networks
• Deep learning algorithm for data-driven simulation of noisy dynamical system
• Extreme learning machine for reduced order modeling of turbulent geophysical flows
• Markov Processes, Hurst Exponents, and Nonlinear Diffusion Equations with application to finance
• Approximate deconvolution large eddy simulation of a barotropic ocean circulation model
• DR-RNN: A deep residual recurrent neural network for model reduction
• A stabilized proper orthogonal decomposition reduced-order model for large scale quasigeostrophic ocean circulation
• Proper orthogonal decomposition closure models for fluid flows: Burgers equation
• An Efficient Coarse Grid Projection Method for Quasigeostrophic Models of Large-Scale Ocean Circulation
• Short note on the behavior of recurrent neural network for noisy dynamical system
• Efficient Construction of Local Parametric Reduced Order Models Using Machine Learning Techniques
• Numerical assessments of ocean energy extraction from western boundary currents using a quasi-geostrophic ocean circulation model

Cited by in corpus (25)

• On closures for reduced order models $-$ A spectrum of first-principle to machine-learned avenues
• Data-driven recovery of hidden physics in reduced order modeling of fluid flows
• Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions
• Data-Driven Variational Multiscale Reduced Order Models
• Digital Twin: Values, Challenges and Enablers
• A long short-term memory embedding for hybrid uplifted reduced order models
• Long short-term memory embedded nudging schemes for nonlinear data assimilation of geophysical flows
• Model fusion with physics-guided machine learning
• Parameterized Neural Ordinary Differential Equations: Applications to Computational Physics Problems
• Nonlinear proper orthogonal decomposition for convection-dominated flows
• Neural-network learning of SPOD latent dynamics
• Deep neural network enabled corrective source term approach to hybrid analysis and modeling
• Equation-free surrogate modeling of geophysical flows at the intersection of machine learning and data assimilation
• Calibrating hypersonic turbulence flow models with the HIFiRE-1 experiment using data-driven machine-learned models
• Reduced-order modeling of unsteady fluid flow using neural network ensembles
• Dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraint
• A data driven reduced order model of fluid flow by Auto-Encoder and self-attention deep learning methods
• Data assimilation empowered neural network parameterizations for subgrid processes in geophysical flows
• Interface learning of multiphysics and multiscale systems
• Reduced order modeling of fluid flows: Machine learning, Kolmogorov barrier, closure modeling, and partitioning
• Reduced Order Models for the Quasi-Geostrophic Equations: A Brief Survey
• Nonintrusive reduced order modeling of convective Boussinesq flows
• Closure Learning for Nonlinear Model Reduction Using Deep Residual Neural Network
• An evolve-then-correct reduced order model for hidden fluid dynamics
• Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection