Numerical bifurcation analysis of PDEs from lattice Boltzmann model simulations: a parsimonious machine learning approach

DOI10.1007/s10915-022-01883-yzbMath1490.65184arXiv2201.13323OpenAlexW4283359998WikidataQ114225557 ScholiaQ114225557MaRDI QIDQ2149520

Gianluca Fabiani, Ioannis Gallos, Ioannis G. Kevrekidis, Evangelos Galaris, Constantinos I. Siettos

Publication date: 29 June 2022

Published in: Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2201.13323

zbMATH Keywords

inverse problempartial differential equationsmachine learningdiffusion mapslattice Boltzmann modellingnumerical bifurcation analysisrandom projection neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Particle methods and lattice-gas methods (76M28) Inverse problems for PDEs (35R30) Numerical methods for inverse problems for initial value and initial-boundary value problems involving PDEs (65M32)

Related Items (5)

Discrete-time nonlinear feedback linearization via physics-informed machine learning ⋮ Physics-agnostic and physics-infused machine learning for thin films flows: modelling, and predictions from small data ⋮ Learning black- and gray-box chemotactic PDEs/closures from agent based Monte Carlo simulation data ⋮ A novel physics-informed deep learning strategy with local time-updating discrete scheme for multi-dimensional forward and inverse consolidation problems ⋮ Data-driven control of agent-based models: an equation/variable-free machine learning approach

Uses Software

• datafold

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• An efficient Newton-Krylov implementation of the constrained runs scheme for initializing on a slow manifold
• Semiglobal stabilization of nonlinear systems using fuzzy control and singular perturbation methods
• A multispeed discrete Boltzmann model for transcritical 2D shallow water flows
• Newton-Krylov solvers for the equation-free computation of coarse traveling waves
• Database-friendly random projections: Johnson-Lindenstrauss with binary coins.
• Truncated Chebyshev series approximation of fuzzy systems for control and nonlinear system identification
• Inferring solutions of differential equations using noisy multi-fidelity data
• Machine learning of linear differential equations using Gaussian processes
• Hidden physics models: machine learning of nonlinear partial differential equations
• Multilayer feedforward networks are universal approximators
• Parsimonious representation of nonlinear dynamical systems through manifold learning: a chemotaxis case study
• Manifold learning for parameter reduction
• Numerical solution and bifurcation analysis of nonlinear partial differential equations with extreme learning machines
• Local extreme learning machines and domain decomposition for solving linear and nonlinear partial differential equations
• Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients
• An experimental unification of reservoir computing methods
• Diffusion maps
• Diffusion maps, spectral clustering and reaction coordinates of dynamical systems
• Scalings in diffusion-driven reaction \(A+B\to C\): numerical simulations by lattice BGK models
• Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
• Lattice Boltzmann method for direct numerical simulation of turbulent flows
• An Analysis of Equivalent Operator Preconditioning for Equation-Free Newton–Krylov Methods
• Extensions of Lipschitz mappings into a Hilbert space
• Automated reverse engineering of nonlinear dynamical systems
• Continuation-Conjugate Gradient Methods for the Least Squares Solution of Nonlinear Boundary Value Problems
• Linear Inversion of Band-Limited Reflection Seismograms
• Arc-Length Continuation and Multigrid Techniques for Nonlinear Elliptic Eigenvalue Problems
• Universal approximation bounds for superpositions of a sigmoidal function
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• “Coarse” stability and bifurcation analysis using time-steppers: A reaction-diffusion example
• Deep Hidden Physics Models: Deep Learning of Nonlinear Partial Differential Equations
• Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
• Geometric diffusions as a tool for harmonic analysis and structure definition of data: Diffusion maps
• Reconstruction of normal forms by learning informed observation geometries from data
• An elementary proof of a theorem of Johnson and Lindenstrauss
• Numerical Methods for Bifurcations of Dynamical Equilibria
• A Model for Collision Processes in Gases. I. Small Amplitude Processes in Charged and Neutral One-Component Systems
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Numerical bifurcation analysis of PDEs from lattice Boltzmann model simulations: a parsimonious machine learning approach