Learning about structural errors in models of complex dynamical systems

DOI10.1016/J.JCP.2024.113157MaRDI QIDQ6572173FDOQ6572173

Authors: Jin-Long Wu, Matthew E. Levine, Tapio Schneider, A. M. Stuart 

Publication date: 15 July 2024

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

Recommendations

• A framework for machine learning of model error in dynamical systems
• A causality-based learning approach for discovering the underlying dynamics of complex systems from partial observations with stochastic parameterization
• Learning and correcting non-Gaussian model errors
• Learning stochastic closures using ensemble Kalman inversion
• Deep learning of dynamics and signal-noise decomposition with time-stepping constraints

zbMATH Keywords

machine learninginverse problemdynamical systemmodel errorstochastic modelnon-local model

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Probabilistic methods, stochastic differential equations (65Cxx) Inference from stochastic processes (62Mxx)

Cites Work

• Algorithm 808
• Bayesian calibration of computer models. (With discussion)
• Gaussian processes for machine learning.
• Title not available (Why is that?)
• Langevin diffusions and Metropolis-Hastings algorithms
• Discovering governing equations from data by sparse identification of nonlinear dynamical systems
• Efficient estimation of stochastic volatility using noisy observations: a multi-scale approach
• Sparse dynamics for partial differential equations
• A Tale of Two Time Scales
• Compressed sensing
• Combining Field Data and Computer Simulations for Calibration and Prediction
• Embedology
• Analysis and approximation of nonlocal diffusion problems with volume constraints
• A computational strategy for multiscale systems with applications to Lorenz 96 model
• Nonlocal diffusion and applications
• Nonequilibrium statistical mechanics
• Nonparametric estimation of diffusions: a differential equations approach
• Parameter estimation for partially observed hypoelliptic diffusions
• On inference for partially observed nonlinear diffusion models using the Metropolis-Hastings algorithm
• Maximum likelihood drift estimation for multiscale diffusions
• Learning about physical parameters: the importance of model discrepancy
• When is a model good enough? Deriving the expected value of model improvement via specifying internal model discrepancies
• Ensemble Kalman methods for inverse problems
• Parameter estimation for multiscale diffusions
• Ensemble Kalman methods with constraints
• Estimation of parameters and eigenmodes of multivariate autoregressive models
• Semiparametric drift and diffusion estimation for multiscale diffusions
• Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: a data-driven, physics-informed Bayesian approach
• Turbulence modeling in the age of data
• Finite sampling interval effects in Kramers-Moyal analysis
• Iterative updating of model error for Bayesian inversion
• Numerical strategy for model correction using physical constraints
• A new framework for extracting coarse-grained models from time series with multiscale structure
• A novel evolutionary algorithm applied to algebraic modifications of the RANS stress-strain relationship
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Recurrent neural network closure of parametric POD-Galerkin reduced-order models based on the Mori-Zwanzig formalism
• RANS turbulence model development using CFD-driven machine learning
• Learning nonlocal constitutive models with neural networks
• Machine learning for fluid mechanics
• Statistical Analysis with Missing Data, Third Edition
• Nonlocal Modeling, Analysis, and Computation
• A framework for machine learning of model error in dynamical systems
• Large-scale sparse inverse covariance matrix estimation
• Subgrid modelling for two-dimensional turbulence using neural networks
• Learning partial differential equations via data discovery and sparse optimization
• Data-driven model reduction, Wiener projections, and the Koopman-Mori-Zwanzig formalism
• Ensemble Kalman inversion for sparse learning of dynamical systems from time-averaged data
• nPINNs: nonlocal physics-informed neural networks for a parametrized nonlocal universal Laplacian operator. Algorithms and applications
• Calibrate, emulate, sample
• Learning dynamical systems from data: a simple cross-validation perspective. I: Parametric kernel flows
• Learning dynamical systems from data: a simple cross-validation perspective. III: Irregularly-sampled time series
• Solving and learning nonlinear PDEs with Gaussian processes
• The Random Feature Model for Input-Output Maps between Banach Spaces
• Learning stochastic closures using ensemble Kalman inversion
• Ensemble inference methods for models with noisy and expensive likelihoods
• Localized ensemble Kalman inversion
• Autodifferentiable ensemble Kalman filters
• Inverse Problems and Data Assimilation
• Ensemble Kalman method for learning turbulence models from indirect observation data
• EMBEDDED MODEL ERROR REPRESENTATION FOR BAYESIAN MODEL CALIBRATION
• Parameter estimation for multiscale diffusions: an overview
• Error modeling for surrogates of dynamical systems using machine learning
• Model selection of chaotic systems from data with hidden variables using sparse data assimilation

Cited In (1)

• Neural dynamical operator: continuous spatial-temporal model with gradient-based and derivative-free optimization methods

This page was built for publication: Learning about structural errors in models of complex dynamical systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6572173)