Sparse identification of nonlinear dynamics with low-dimensionalized flow representations

DOI10.1017/JFM.2021.697zbMath1500.76068arXiv2010.12177OpenAlexW3196966183MaRDI QIDQ5154682

Kai Fukami, Takaaki Murata, Koji Fukagata, Kai Zhang

Publication date: 5 October 2021

Published in: Journal of Fluid Mechanics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2010.12177

zbMATH Keywords

machine learningadaptive least absolute shrinkage/selection operatorconvolutional neural network autoencodersingle cylinder wakethresholded least square algorithmtwo-parallel cylinders wake

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Wakes and jets (76D25) Basic methods in fluid mechanics (76M99)

Related Items (8)

A framework based on symbolic regression coupled with eXtended physics-informed neural networks for gray-box learning of equations of motion from data ⋮ Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutions ⋮ Airfoil-based convolutional autoencoder and long short-term memory neural network for predicting coherent structures evolution around an airfoil ⋮ Front transport reduction for complex moving fronts ⋮ Koopman dynamic-oriented deep learning for invariant subspace identification and full-state prediction of complex systems ⋮ Data-driven transient lift attenuation for extreme vortex gust-airfoil interactions ⋮ A surrogate reduced order model of the unsteady advection dominant problems based on combination of deep autoencoders-LSTM and POD ⋮ Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression

Uses Software

• Adam
• SINDy
• AEflow

Cites Work

• Unnamed Item
• Unnamed Item
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• The Adaptive Lasso and Its Oracle Properties
• Neural network modeling for near wall turbulent flow.
• Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
• Recovering missing CFD data for high-order discretizations using deep neural networks and dynamics learning
• Reducing the Dimensionality of Data with Neural Networks
• Characteristics of flow over two circular cylinders in a side-by-side arrangement at low Reynolds numbers
• Sparse reduced-order modelling: sensor-based dynamics to full-state estimation
• Spectral proper orthogonal decomposition and its relationship to dynamic mode decomposition and resolvent analysis
• Deterministic Nonperiodic Flow
• Data-Driven Science and Engineering
• 9 From the POD-Galerkin method to sparse manifold models
• Spectral proper orthogonal decomposition and resolvent analysis of near-wall coherent structures in turbulent pipe flows
• Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
• On the Convergence of the SINDy Algorithm
• Low-order model for successive bifurcations of the fluidic pinball
• Data-driven discovery of coordinates and governing equations
• Constrained sparse Galerkin regression
• Nonlinear mode decomposition with convolutional neural networks for fluid dynamics
• Sparse identification of nonlinear dynamics for model predictive control in the low-data limit
• Regularization and Variable Selection Via the Elastic Net
• Discovery of Nonlinear Multiscale Systems: Sampling Strategies and Embeddings
• Global stability of base and mean flows: a general approach and its applications to cylinder and open cavity flows
• Ridge Regression: Biased Estimation for Nonorthogonal Problems
• Periodic Orbits and Chaotic Sets in a Low-Dimensional Model for Shear Flows
• Sparse identification of multiphase turbulence closures for coupled fluid–particle flows

This page was built for publication: Sparse identification of nonlinear dynamics with low-dimensionalized flow representations