Neural-network learning of SPOD latent dynamics

DOI10.1016/j.jcp.2022.111475OpenAlexW3205705351WikidataQ114950919 ScholiaQ114950919MaRDI QIDQ2168295

Gianluigi Rozza, Oliver T. Schmidt, Romit Maulik, Andrea Lario, Gianmarco Mengaldo

Publication date: 31 August 2022

Published in: Journal of Computational Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2110.09218

zbMATH Keywords

dynamical systemsneural networksreduced order modelingdeep learning

Mathematics Subject Classification ID

Turbulence (76Fxx) Numerical methods for ordinary differential equations (65Lxx) Time-dependent statistical mechanics (dynamic and nonequilibrium) (82Cxx)

Related Items

Multiscale graph neural network autoencoders for interpretable scientific machine learning ⋮ A digital twin framework for civil engineering structures ⋮ Operator inference with roll outs for learning reduced models from scarce and low-quality data

Uses Software

• Tensor2Tensor
• torchdiffeq
• PySPOD
• PyParSVD

Cites Work

• Unnamed Item
• Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
• Data-driven POD-Galerkin reduced order model for turbulent flows
• Non-intrusive reduced order modeling of nonlinear problems using neural networks
• Time-series learning of latent-space dynamics for reduced-order model closure
• Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network
• Physics-informed machine learning for reduced-order modeling of nonlinear problems
• Parametric non-intrusive model order reduction for flow-fields using unsupervised machine learning
• Frequency–time analysis, low-rank reconstruction and denoising of turbulent flows using SPOD
• Statistical Mechanics of Nonequilibrium Liquids
• Turbulence and the dynamics of coherent structures. I. Coherent structures
• Spectral proper orthogonal decomposition and its relationship to dynamic mode decomposition and resolvent analysis
• Modelling of jet noise: a perspective from large-eddy simulations
• Broadband reconstruction of inhomogeneous turbulence using spectral proper orthogonal decomposition and Gabor modes
• Transport, Collective Motion, and Brownian Motion

This page was built for publication: Neural-network learning of SPOD latent dynamics