Non-linear manifold reduced-order models with convolutional autoencoders and reduced over-collocation method
From MaRDI portal
Abstract: Non-affine parametric dependencies, nonlinearities and advection-dominated regimes of the model of interest can result in a slow Kolmogorov n-width decay, which precludes the realization of efficient reduced-order models based on linear subspace approximations. Among the possible solutions, there are purely data-driven methods that leverage autoencoders and their variants to learn a latent representation of the dynamical system, and then evolve it in time with another architecture. Despite their success in many applications where standard linear techniques fail, more has to be done to increase the interpretability of the results, especially outside the training range and not in regimes characterized by an abundance of data. Not to mention that none of the knowledge on the physics of the model is exploited during the predictive phase. In order to overcome these weaknesses, we implement the non-linear manifold method introduced by Carlberg et al [37] with hyper-reduction achieved through reduced over-collocation and teacher-student training of a reduced decoder. We test the methodology on a 2d non-linear conservation law and a 2d shallow water models, and compare the results obtained with a purely data-driven method for which the dynamics is evolved in time with a long-short term memory network.
Cites work
- A deep learning approach to Reduced Order Modelling of parameter dependent partial differential equations
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
- A nonlinear manifold-based reduced order model for multiscale analysis of heterogeneous hyperelastic materials
- A Stochastic Collocation Method for Elliptic Partial Differential Equations with Random Input Data
- An `empirical interpolation' method: Application to efficient reduced-basis discretization of partial differential equations
- An EIM-degradation free reduced basis method via over collocation and residual hyper reduction-based error estimation
- Certified reduced basis methods for parametrized partial differential equations
- Decay of the Kolmogorov \(N\)-width for wave problems
- Deep learning
- Efficient non linear model reduction via a least-squares Petrov-Galerkin projection and compressive tensor approximations
- Generalized reduced basis methods and n-width estimates for the approximation of the solution manifold of parametric PDEs
- Interpolation-based reduced-order modelling for steady transonic flows via manifold learning
- Iterative methods for model reduction by domain decomposition
- Kolmogorov and linear widths of balls in Sobolev spaces on compact manifolds
- Kolmogorov widths under holomorphic mappings
- Machine learning. A probabilistic perspective
- Model reduction and approximation. Theory and algorithms
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
- Nonlinear Kolmogorov widths
- Nonlinear model reduction via discrete empirical interpolation
- Optimal nonlinear approximation
- POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
- Reduced-order model for the BGK equation based on POD and optimal transport
- Reduced-order modeling of a two-dimensional flow with moving shocks.
- SNS: A Solution-Based Nonlinear Subspace Method for Time-Dependent Model Order Reduction
- Solution of the implicitly discretised reacting flow equations by operator-splitting
- Space-time least-squares Petrov-Galerkin projection for nonlinear model reduction
- The GNAT method for nonlinear model reduction: effective implementation and application to computational fluid dynamics and turbulent flows
- The neural network shifted-proper orthogonal decomposition: a machine learning approach for non-linear reduction of hyperbolic equations
Cited in
(35)- Canonical and noncanonical Hamiltonian operator inference
- A new method to interpolate POD reduced bases–Application to the parametric model order reduction of a gas bearings supported rotor
- A continuous convolutional trainable filter for modelling unstructured data
- Branched latent neural maps
- A graph convolutional autoencoder approach to model order reduction for parametrized PDEs
- Model order reduction for parameterized electromagnetic problems using matrix decomposition and deep neural networks
- A fast and accurate domain decomposition nonlinear manifold reduced order model
- An optimisation-based domain-decomposition reduced order model for parameter-dependent non-stationary fluid dynamics problems
- Gappy AE: a nonlinear approach for gappy data reconstruction using auto-encoder
- Model order reduction of an ultraweak and optimally stable variational formulation for parametrized reactive transport problems
- On the latent dimension of deep autoencoders for reduced order modeling of PDEs parametrized by random fields
- GFN: a graph feedforward network for resolution-invariant reduced operator learning in multifidelity applications
- Efficient prediction of phase-field crystal dynamics via -variational autoencoders and time-series transformers on coupled physical fields
- Kernel manifolds: nonlinear-augmentation dimensionality reduction using reproducing kernel Hilbert spaces
- Neural empirical interpolation method for nonlinear model reduction
- Nonlinear model reduction with neural Galerkin schemes on quadratic manifolds
- Model order reduction for seismic applications
- Stabilizing and solving unique continuation problems by parameterizing data and learning finite element solution operators
- Data-driven nonlinear model reduction to spectral submanifolds via oblique projection
- Physics informed neural network framework for unsteady discretized reduced order system
- Optimal transport-based displacement interpolation with data augmentation for reduced order modeling of nonlinear dynamical systems
- Hamiltonian reduction using a convolutional auto-encoder coupled to a Hamiltonian neural network
- Entropy-stable model reduction of one-dimensional hyperbolic systems using rational quadratic manifolds
- Optimal transport-inspired deep learning framework for slow-decaying Kolmogorov n-width problems: exploiting Sinkhorn loss and Wasserstein kernel
- Explicable hyper-reduced order models on nonlinearly approximated solution manifolds of compressible and incompressible Navier-Stokes equations
- Learning latent space dynamics with model-form uncertainties: a stochastic reduced-order modeling approach
- A practical existence theorem for reduced order models based on convolutional autoencoders
- A subspace-adaptive weights cubature method with application to the local hyperreduction of parameterized finite element models
- PDE-free mass-constrained learning of complex systems with hidden states
- Deep orthogonal decomposition: a continuously adaptive neural network approach to model order reduction of parametrized partial differential equations
- Machine learning-based quadratic closures for non-intrusive reduced order models
- Nonlinear reduced basis using mixture Wasserstein barycenters: application to an eigenvalue problem inspired from quantum chemistry
- Convolutional Symmetric AutoEncoders: enhancing latent stability via differential geometry
- Nonlinear model reduction for transport-dominated problems
- Model reduction of convection-dominated viscous conservation laws using implicit feature tracking and landmark image registration
This page was built for publication: Non-linear manifold reduced-order models with convolutional autoencoders and reduced over-collocation method
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6158995)
