GPLaSDI: Gaussian process-based interpretable latent space dynamics identification through deep autoencoder

DOI10.1016/J.CMA.2023.116535arXiv2308.05882OpenAlexW4387631016MaRDI QIDQ6118601FDOQ6118601

Debojyoti Ghosh, Jonathan L. Belof, Youngsoo Choi, Christophe Bonneville

Publication date: 21 March 2024

Published in: Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2308.05882

zbMATH Keywords

Gaussian processespartial differential equationautoencodersreduced-order-modellatent-space identification

Mathematics Subject Classification ID

Systems theory; control (93-XX) Computer science (68-XX)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Reducing the Dimensionality of Data with Neural Networks
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Efficient implementation of weighted ENO schemes
• Uncertainty quantification. Theory, implementation, and applications
• Non‐linear model reduction for uncertainty quantification in large‐scale inverse problems
• Large-scale topology optimization using preconditioned Krylov subspace methods with recycling
• Variational multiscale proper orthogonal decomposition: Navier‐stokes equations
• Reduced-order model tracking and interpolation to solve PDE-based Bayesian inverse problems
• Finite volume POD-Galerkin stabilised reduced order methods for the parametrised incompressible Navier-Stokes equations
• Computational Physics
• Computational Electromagnetics
• Stabilized reduced order models for the advection-diffusion-reaction equation using operator splitting
• Deep learning in fluid dynamics
• Data-driven discovery of coordinates and governing equations
• Local approximate Gaussian process regression for data-driven constitutive models: development and comparison with neural networks
• Reduced order models for Lagrangian hydrodynamics
• Component-wise reduced order model lattice-type structure design
• SNS: A Solution-Based Nonlinear Subspace Method for Time-Dependent Model Order Reduction
• Stress-constrained topology optimization of lattice-like structures using component-wise reduced order models
• Weak SINDy for partial differential equations
• LaSDI: parametric latent space dynamics identification
• gLaSDI: parametric physics-informed greedy latent space dynamics identification
• Bayesian deep learning for partial differential equation parameter discovery with sparse and noisy data

Cited In (3)

• tLaSDI: thermodynamics-informed latent space dynamics identification
• Accurate data-driven surrogates of dynamical systems for forward propagation of uncertainty
• Gappy AE: a nonlinear approach for gappy data reconstruction using auto-encoder

This page was built for publication: GPLaSDI: Gaussian process-based interpretable latent space dynamics identification through deep autoencoder

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6118601)