Adaptive learning of effective dynamics for online modeling of complex systems

DOI10.1016/j.cma.2023.116204arXiv2304.01732MaRDI QIDQ6096436

Pantelis R. Vlachas, Leonidas J. Guibas, Michail Chatzimanolakis, Ivica Kičić, Georgios Arampatzis, Petros Koumoutsakos

Publication date: 12 September 2023

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

Full work available at URL: https://arxiv.org/abs/2304.01732

zbMATH Keywords

Navier-Stokes equationscomputer simulationsmachine learningcontinuous learningadaptive reduced-order modelingonline real-time learning

Mathematics Subject Classification ID

Fluid mechanics (76-XX) Statistical mechanics, structure of matter (82-XX)

Cites Work

• Unnamed Item
• Unnamed Item
• The heterogeneous multiscale methods
• A penalization method to take into account obstacles in incompressible viscous flows
• Dynamic data-driven reduced-order models
• POD-DL-ROM: enhancing deep learning-based reduced order models for nonlinear parametrized PDEs by proper orthogonal decomposition
• Unsteady flow prediction from sparse measurements by compressed sensing reduced order modeling
• Data-driven reduced order model with temporal convolutional neural network
• Modeling the dynamics of PDE systems with physics-constrained deep auto-regressive networks
• Data-driven operator inference for nonintrusive projection-based model reduction
• Diffusion maps
• Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
• LaSDI: parametric latent space dynamics identification
• Online Adaptive Model Reduction for Nonlinear Systems via Low-Rank Updates
• Nonintrusive and Structure Preserving Multiscale Integration of Stiff ODEs, SDEs, and Hamiltonian Systems with Hidden Slow Dynamics via Flow Averaging
• Data-driven forecasting of high-dimensional chaotic systems with long short-term memory networks
• Model Reduction and Approximation
• Overcoming catastrophic forgetting in neural networks
• Data-driven discovery of coordinates and governing equations
• Learning data-driven discretizations for partial differential equations
• Online Dynamic Mode Decomposition for Time-Varying Systems
• Non‐linear model reduction for uncertainty quantification in large‐scale inverse problems
• Numerical Solution of the Navier-Stokes Equations
• Learning physics-based models from data: perspectives from inverse problems and model reduction
• gLaSDI: parametric physics-informed greedy latent space dynamics identification

This page was built for publication: Adaptive learning of effective dynamics for online modeling of complex systems