gLaSDI: parametric physics-informed greedy latent space dynamics identification
From MaRDI portal
Publication:6107110
Abstract: A parametric adaptive physics-informed greedy Latent Space Dynamics Identification (gLaSDI) method is proposed for accurate, efficient, and robust data-driven reduced-order modeling of high-dimensional nonlinear dynamical systems. In the proposed gLaSDI framework, an autoencoder discovers intrinsic nonlinear latent representations of high-dimensional data, while dynamics identification (DI) models capture local latent-space dynamics. An interactive training algorithm is adopted for the autoencoder and local DI models, which enables identification of simple latent-space dynamics and enhances accuracy and efficiency of data-driven reduced-order modeling. To maximize and accelerate the exploration of the parameter space for the optimal model performance, an adaptive greedy sampling algorithm integrated with a physics-informed residual-based error indicator and random-subset evaluation is introduced to search for the optimal training samples on the fly. Further, to exploit local latent-space dynamics captured by the local DI models for an improved modeling accuracy with a minimum number of local DI models in the parameter space, a k-nearest neighbor convex interpolation scheme is employed. The effectiveness of the proposed framework is demonstrated by modeling various nonlinear dynamical problems, including Burgers equations, nonlinear heat conduction, and radial advection. The proposed adaptive greedy sampling outperforms the conventional predefined uniform sampling in terms of accuracy. Compared with the high-fidelity models, gLaSDI achieves 17 to 2,658x speed-up with 1 to 5% relative errors.
Recommendations
Cites work
- A decomposed subspace reduction for fracture mechanics based on the meshfree integrated singular basis function method
- A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder
- A physics-constrained data-driven approach based on locally convex reconstruction for noisy database
- A practical factorization of a Schur complement for PDE-constrained distributed optimal control
- A Schur method for balanced-truncation model reduction
- A topology optimization method for geometrically nonlinear structures with meshless analysis and independent density field interpolation
- An algorithmic comparison of the hyper-reduction and the discrete empirical interpolation method for a nonlinear thermal problem
- Bayesian operator inference for data-driven reduced-order modeling
- Component-wise reduced order model lattice-type structure design
- Conservative model reduction for finite-volume models
- Data-driven discovery of coordinates and governing equations
- Data-driven operator inference for nonintrusive projection-based model reduction
- Deep autoencoders for physics-constrained data-driven nonlinear materials modeling
- Deep learning in fluid dynamics
- Discovering governing equations from data by sparse identification of nonlinear dynamical systems
- Domain-decomposition least-squares Petrov-Galerkin (DD-LSPG) nonlinear model reduction
- Finite volume POD-Galerkin stabilised reduced order methods for the parametrised incompressible Navier-Stokes equations
- Gradient-based constrained optimization using a database of linear reduced-order models
- Improving the efficiency of large scale topology optimization through on-the-fly reduced order model construction
- Lagrangian dynamic mode decomposition for construction of reduced-order models of advection-dominated phenomena
- Large-scale topology optimization using preconditioned Krylov subspace methods with recycling
- Large‐Scale Inverse Problems and Quantification of Uncertainty
- LaSDI: parametric latent space dynamics identification
- Lift \& learn: physics-informed machine learning for large-scale nonlinear dynamical systems
- MFEM: a modular finite element methods library
- Model order reduction for meshfree solution of Poisson singularity problems
- Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders
- Neural architecture search: a survey
- Non-intrusive data-driven model reduction for differential-algebraic equations derived from lifting transformations
- Nonlinear model reduction for uncertainty quantification in large-scale inverse problems
- Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms
- Predicting solar wind streams from the inner-heliosphere to Earth via shifted operator inference
- Projection-based model reduction of dynamical systems using space-time subspace and machine learning
- Projection-based model reduction: formulations for physics-based machine learning
- Proper orthogonal decomposition-based model order reduction via radial basis functions for molecular dynamics systems
- Reduced order models for Lagrangian hydrodynamics
- Reducing the Dimensionality of Data with Neural Networks
- Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference
- SNS: A Solution-Based Nonlinear Subspace Method for Time-Dependent Model Order Reduction
- Space-time least-squares Petrov-Galerkin projection for nonlinear model reduction
- Space-time reduced order model for large-scale linear dynamical systems with application to Boltzmann transport problems
- Stabilized reduced order models for the advection-diffusion-reaction equation using operator splitting
- THE PARTITION OF UNITY METHOD
- The shifted proper orthogonal decomposition: a mode decomposition for multiple transport phenomena
- Variational multiscale proper orthogonal decomposition: Navier-Stokes equations
Cited in
(14)- Local Lagrangian reduced-order modeling for the Rayleigh-Taylor instability by solution manifold decomposition
- Adaptive learning of effective dynamics for online modeling of complex systems
- GPLaSDI: Gaussian process-based interpretable latent space dynamics identification through deep autoencoder
- Weak-Form Latent Space Dynamics Identification
- Gappy AE: a nonlinear approach for gappy data reconstruction using auto-encoder
- A multi-resolution physics-informed recurrent neural network: formulation and application to musculoskeletal systems
- tLaSDI: thermodynamics-informed latent space dynamics identification
- Projection-based model order reduction of embedded boundary models for CFD and nonlinear FSI
- Improved greedy identification of latent dynamics with application to fluid flows
- Physics-informed active learning with simultaneous weak-form latent space dynamics identification
- Higher-order LaSDI: reduced order modeling with multiple time derivatives
- Local reduced-order modeling for electrostatic plasmas by physics-informed solution manifold decomposition
- Efficient data-driven regression for reduced-order modeling of spatial pattern formation
- Latent space dynamics identification for interface tracking with application to shock-induced pore collapse
This page was built for publication: gLaSDI: parametric physics-informed greedy latent space dynamics identification
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6107110)
