A data-driven statistical-stochastic surrogate modeling strategy for complex nonlinear non-stationary dynamics
From MaRDI portal
Publication:6158085
Abstract: We propose a statistical-stochastic surrogate modeling approach to predict the response of the mean and variance statistics under various initial conditions and external forcing perturbations. The proposed modeling framework extends the purely statistical modeling approach that is practically limited to the homogeneous statistical regime for high-dimensional state variables. The new closure system allows one to overcome several practical issues that emerge in the non-homogeneous statistical regimes. First, the proposed ensemble modeling that couples the mean statistics and stochastic fluctuations naturally produces positive-definite covariance matrix estimation, which is a challenging issue that hampers the purely statistical modeling approaches. Second, the proposed closure model, which embeds a non-Markovian neural-network model for the unresolved fluxes such that the variance of the dynamics is consistent, overcomes the inherent instability of the stochastic fluctuation dynamics. Effectively, the proposed framework extends the classical stochastic parametric modeling paradigm for the unresolved dynamics to a semi-parametric parameterization with a residual Long-Short-Term-Memory neural network architecture. Third, based on empirical information metric, we provide an efficient and effective training procedure by fitting a loss function that measures the differences between response statistics. Supporting numerical examples are provided with the Lorenz-96 model, a system of ODEs that admits the characteristic of chaotic dynamics with both homogeneous and inhomogeneous statistical regimes. In the latter case, we will see the effectiveness of the statistical prediction even though the resolved Fourier modes corresponding to the leading mean energy and variance spectra do not coincide.
Recommendations
- Probabilistic-learning-based stochastic surrogate model from small incomplete datasets for nonlinear dynamical systems
- Conditional deep surrogate models for stochastic, high-dimensional, and multi-fidelity systems
- Generative stochastic modeling of strongly nonlinear flows with non-Gaussian statistics
- A data-driven non-linear assimilation framework with neural networks
- Conditional Gaussian nonlinear system: a fast preconditioner and a cheap surrogate model for complex nonlinear systems
Cites work
- scientific article; zbMATH DE number 4020643 (Why is no real title available?)
- An introduction to turbulent dynamical systems in complex systems
- Deep learning
- Ensemble forecasting
- Filtering complex turbulent systems.
- Foundations of machine learning
- Gaussian processes for machine learning.
- Information Theory and Stochastics for Multiscale Nonlinear Systems
- Kernel-based prediction of non-Markovian time series
- Linear and nonlinear statistical response theories with prototype applications to sensitivity analysis and statistical control of complex turbulent dynamical systems
- Linear response, or else
- Machine learning for prediction with missing dynamics
- Nonequilibrium statistical mechanics
- Probabilistic Forecasting and Bayesian Data Assimilation
- Statistically accurate low-order models for uncertainty quantification in turbulent dynamical systems
- Strategies for reduced-order models for predicting the statistical responses and uncertainty quantification in complex turbulent dynamical systems
- Subgrid modelling for two-dimensional turbulence using neural networks
Cited in
(6)- Transport and scale interactions in geophysical flows. Abstracts from the workshop held July 16--21, 2023
- Conditional Gaussian nonlinear system: a fast preconditioner and a cheap surrogate model for complex nonlinear systems
- The robustness of an efficient probabilistic data-based tool for simulating the non-stationary response of non-linear systems
- Surrogate Models for Oscillatory Systems Using Sparse Polynomial Chaos Expansions and Stochastic Time Warping
- A data-driven method for the steady state of randomly perturbed dynamics
- Probabilistic-learning-based stochastic surrogate model from small incomplete datasets for nonlinear dynamical systems
This page was built for publication: A data-driven statistical-stochastic surrogate modeling strategy for complex nonlinear non-stationary dynamics
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6158085)
