Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

gLaSDI: Parametric physics-informed greedy latent space dynamics identification

Journal Article · · Journal of Computational Physics
 [1];  [2];  [3];  [2];  [1]
  1. University of California, San Diego, CA (United States)
  2. Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
  3. University of Arizona, Tucson, AZ (United States)

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. Here, 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 -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 2,658× speed-up with 1 to 5% relative errors.

Research Organization:
Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
Grant/Contract Number:
AC52-07NA27344
OSTI ID:
1999976
Alternate ID(s):
OSTI ID: 2000140
Report Number(s):
LLNL--JRNL-834220; 1052759
Journal Information:
Journal of Computational Physics, Journal Name: Journal of Computational Physics Vol. 489; ISSN 0021-9991
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (67)

The Partition of Unity Method journal February 1997
Learning reduced‐order dynamics for parametrized shallow water equations from data journal May 2021
Large-scale topology optimization using preconditioned Krylov subspace methods with recycling
  • Wang, Shun; Sturler, Eric de; Paulino, Glaucio H.
  • International Journal for Numerical Methods in Engineering, Vol. 69, Issue 12 https://doi.org/10.1002/nme.1798
journal January 2007
Non-linear model reduction for uncertainty quantification in large-scale inverse problems journal January 2009
Proper orthogonal decomposition-based model order reduction via radial basis functions for molecular dynamics systems journal July 2013
Model order reduction for meshfree solution of Poisson singularity problems
  • Chen, Jiun‐Shyan; Marodon, Camille; Hu, Hsin‐Yun
  • International Journal for Numerical Methods in Engineering, Vol. 102, Issue 5 https://doi.org/10.1002/nme.4743
journal August 2014
Improving the efficiency of large scale topology optimization through on-the-fly reduced order model construction: EFFICIENT TOPOLOGY OPTIMIZATION THROUGH ON-THE-FLY ROM CONSTRUCTION journal October 2014
A discontinuous and adaptive reduced order model for the angular discretization of the Boltzmann transport equation journal September 2020
Variational multiscale proper orthogonal decomposition: Navier-stokes equations: VARIATIONAL MULTISCALE POD journal December 2013
Genetic programming as a means for programming computers by natural selection journal June 1994
A dual mesh method with adaptivity for stress-constrained topology optimization journal November 2019
Gaussian process-based surrogate modeling framework for process planning in laser powder-bed fusion additive manufacturing of 316L stainless steel journal September 2017
A topology optimization method for geometrically nonlinear structures with meshless analysis and independent density field interpolation journal April 2014
A decomposed subspace reduction for fracture mechanics based on the meshfree integrated singular basis function method journal August 2018
A Practical Factorization of a Schur Complement for PDE-Constrained Distributed Optimal Control journal December 2014
Non-intrusive reduced order modeling of natural convection in porous media using convolutional autoencoders: Comparison with linear subspace techniques journal February 2022
Improving variable-fidelity surrogate modeling via gradient-enhanced kriging and a generalized hybrid bridge function journal March 2013
Stabilized reduced order models for the advection–diffusion–reaction equation using operator splitting journal June 2016
MFEM: A modular finite element methods library journal January 2021
Characterising the Digital Twin: A systematic literature review journal May 2020
Data-driven operator inference for nonintrusive projection-based model reduction journal July 2016
A physics-constrained data-driven approach based on locally convex reconstruction for noisy database journal May 2020
Operator inference for non-intrusive model reduction of systems with non-polynomial nonlinear terms journal December 2020
Component-wise reduced order model lattice-type structure design journal August 2021
Domain-decomposition least-squares Petrov–Galerkin (DD-LSPG) nonlinear model reduction journal October 2021
Deep autoencoders for physics-constrained data-driven nonlinear materials modeling journal November 2021
Reduced order models for Lagrangian hydrodynamics journal January 2022
Non-intrusive data-driven model reduction for differential–algebraic equations derived from lifting transformations journal February 2022
Projection-based model reduction of dynamical systems using space–time subspace and machine learning journal February 2022
LaSDI: Parametric Latent Space Dynamics Identification journal September 2022
Finite volume POD-Galerkin stabilised reduced order methods for the parametrised incompressible Navier–Stokes equations journal September 2018
Projection-based model reduction: Formulations for physics-based machine learning journal January 2019
Conservative model reduction for finite-volume models journal October 2018
Model reduction of dynamical systems on nonlinear manifolds using deep convolutional autoencoders journal November 2019
Lagrangian dynamic mode decomposition for construction of reduced-order models of advection-dominated phenomena journal April 2020
Gradient-based constrained optimization using a database of linear reduced-order models journal December 2020
Space–time reduced order model for large-scale linear dynamical systems with application to Boltzmann transport problems journal January 2021
A fast and accurate physics-informed neural network reduced order model with shallow masked autoencoder journal February 2022
A hyper-reduction computational method for accelerated modeling of thermal cycling-induced plastic deformations journal June 2021
Review of digital twin about concepts, technologies, and industrial applications journal January 2021
Lift & Learn: Physics-informed machine learning for large-scale nonlinear dynamical systems journal May 2020
Deep learning in fluid dynamics journal January 2017
A framework for data-driven solution and parameter estimation of PDEs using conditional generative adversarial networks journal December 2021
Discovering governing equations from data by sparse identification of nonlinear dynamical systems journal March 2016
Data-driven discovery of coordinates and governing equations journal October 2019
Data-driven reduced-order models via regularised Operator Inference for a single-injector combustion process journal January 2021
Localized non-intrusive reduced-order modelling in the operator inference framework
  • Geelen, Rudy; Willcox, Karen
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 380, Issue 2229 https://doi.org/10.1098/rsta.2021.0206
journal June 2022
CaloGAN: Simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks journal January 2018
A Schur method for balanced-truncation model reduction journal July 1989
Building Surrogate Models Based on Detailed and Approximate Simulations journal June 2005
Hydraulic Turbine Diffuser Shape Optimization by Multiple Surrogate Model Approximations of Pareto Fronts journal April 2007
Reducing the Dimensionality of Data with Neural Networks journal July 2006
Distilling Free-Form Natural Laws from Experimental Data journal April 2009
Nonlinear Dimensionality Reduction by Locally Linear Embedding journal December 2000
Space--Time Least-Squares Petrov--Galerkin Projection for Nonlinear Model Reduction journal January 2019
The Shifted Proper Orthogonal Decomposition: A Mode Decomposition for Multiple Transport Phenomena journal January 2018
SNS: A Solution-Based Nonlinear Subspace Method for Time-Dependent Model Order Reduction journal January 2020
Sampling Low-Dimensional Markovian Dynamics for Preasymptotically Recovering Reduced Models from Data with Operator Inference journal January 2020
The Proper Orthogonal Decomposition in the Analysis of Turbulent Flows journal January 1993
Non-intrusive nonlinear model reduction via machine learning approximations to low-dimensional operators journal December 2021
RBF-POD reduced-order modeling of DNA molecules under stretching and bending journal December 2013
Dynamic mode Decomposition for Construction of Reduced-Order Models of Hyperbolic Problems with Shocks journal January 2021
Hierarchical Kriging Model for Variable-Fidelity Surrogate Modeling journal September 2012
Learning Physics-Based Reduced-Order Models for a Single-Injector Combustion Process journal June 2020
A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics journal May 2019
Non-Intrusive Inference Reduced Order Model for Fluids Using Deep Multistep Neural Network journal August 2019
Efficient Space–Time Reduced Order Model for Linear Dynamical Systems in Python Using Less than 120 Lines of Code journal July 2021

Similar Records

Physics-Informed Active Learning With Simultaneous Weak-Form Latent Space Dynamics Identification
Journal Article · Sun Dec 08 23:00:00 EST 2024 · International Journal for Numerical Methods in Engineering · OSTI ID:2533635

LaSDI: Parametric Latent Space Dynamics Identification
Journal Article · Wed Aug 10 00:00:00 EDT 2022 · Computer Methods in Applied Mechanics and Engineering · OSTI ID:1959470

$\text{GPLaSDI}$: Gaussian Process-based interpretable Latent Space Dynamics Identification through deep autoencoder
Journal Article · Sat Oct 14 00:00:00 EDT 2023 · Computer Methods in Applied Mechanics and Engineering · OSTI ID:2345978