Data-Driven Reduction for a Class of Multiscale Fast-Slow Stochastic Dynamical Systems
From MaRDI portal
Abstract: Multiple time scale stochastic dynamical systems are ubiquitous in science and engineering, and the reduction of such systems and their models to only their slow components is often essential for scientific computation and further analysis. Rather than being available in the form of an explicit analytical model, often such systems can only be observed as a data set which exhibits dynamics on several time scales. We will focus on applying and adapting data mining and manifold learning techniques to detect the slow components in such multiscale data. Traditional data mining methods are based on metrics (and thus, geometries) which are not informed of the multiscale nature of the underlying system dynamics; such methods cannot successfully recover the slow variables. Here, we present an approach which utilizes both the local geometry and the local dynamics within the data set through a metric which is both insensitive to the fast variables and more general than simple statistical averaging. Our analysis of the approach provides conditions for successfully recovering the underlying slow variables, as well as an empirical protocol guiding the selection of the method parameters.
Recommendations
- An efficient data-driven multiscale stochastic reduced order modeling framework for complex systems
- Stochastic model reduction for slow-fast systems with moderate time scale separation
- Data-based stochastic model reduction for the Kuramoto-Sivashinsky equation
- Data-driven reduced-order modeling for nonautonomous dynamical systems in multiscale media
- Data-driven closures for stochastic dynamical systems
- Reductions and Deviations for Stochastic Partial Differential Equations Under Fast Dynamical Boundary Conditions
- Data-driven variational multiscale reduced order models
- A data-driven Krylov model order reduction for large-scale dynamical systems
Cites work
- scientific article; zbMATH DE number 54145 (Why is no real title available?)
- scientific article; zbMATH DE number 3366247 (Why is no real title available?)
- scientific article; zbMATH DE number 3023295 (Why is no real title available?)
- A Khasminskii type averaging principle for stochastic reaction-diffusion equations
- Closed-form likelihood expansions for multivariate diffusions
- Convergence of numerical time-averaging and stationary measures via Poisson equations
- Diffusion maps
- Equation-free, coarse-grained multiscale computation: enabling microscopic simulators to perform system-level analysis
- Extracting macroscopic dynamics: model problems and algorithms
- Fitting Effective Diffusion Models to Data Associated with a “Glassy" Potential: Estimation, Classical Inference Procedures, and Some Heuristics
- Gauge invariance of degenerate Riemannian metrics
- Geometric diffusions as a tool for harmonic analysis and structure definition of data: diffusion maps
- Group invariant scattering
- Image Completion by Diffusion Maps and Spectral Relaxation
- Intrinsic modeling of stochastic dynamical systems using empirical geometry
- Laplacian Eigenmaps for Dimensionality Reduction and Data Representation
- Manifold Learning for Latent Variable Inference in Dynamical Systems
- Manifold parametrizations by eigenfunctions of the Laplacian and heat kernels
- Markov Chains and Stochastic Stability
- Memory Effects in Irreversible Thermodynamics
- Model reduction of multi-scale chemical Langevin equations
- Non-linear independent component analysis with diffusion maps
- On the Poisson equation and diffusion approximation. I
- Optimal prediction and the Mori–Zwanzig representation of irreversible processes
- Parameter estimation for multiscale diffusions
- Parsimonious representation of nonlinear dynamical systems through manifold learning: a chemotaxis case study
- Perturbation methods in applied mathematics
- Telescopic projective methods for parabolic differential equations
- The Quasi-Steady-State Assumption: A Case Study in Perturbation
- The earth mover's distance as a metric for image retrieval
- Time-scale separation from diffusion-mapped delay coordinates
- Transport, Collective Motion, and Brownian Motion
Cited in
(24)- Data-driven discovery of slow-fast stochastic differential equations with data binning and sparse Bayesian strategy
- Data-driven spectral decomposition and forecasting of ergodic dynamical systems
- GANs and Closures: Micro-Macro Consistency in Multiscale Modeling
- Physical insights from complex multiscale non-linear system dynamics: identification of fast and slow variables
- The spatiotemporal coupling in delay-coordinates dynamic mode decomposition
- Slow invariant manifolds of singularly perturbed systems via physics-informed machine learning
- Scientific machine learning for closure models in multiscale problems: a review
- Transition manifolds of complex metastable systems. Theory and data-driven computation of effective dynamics
- A Geometric Approach to the Transport of Discontinuous Densities
- Data-driven probability density forecast for stochastic dynamical systems
- Approximation of slow and fast dynamics in multiscale dynamical systems by the linearized relaxation redistribution method
- A weak characterization of slow variables in stochastic dynamical systems
- Discovery of slow variables in a class of multiscale stochastic systems via neural networks
- A trajectory-free framework for analysing multiscale systems
- Kernel-based parameter estimation of dynamical systems with unknown observation functions
- A data-driven method for the steady state of randomly perturbed dynamics
- Spatiotemporal analysis using Riemannian composition of diffusion operators
- Nonlinear model reduction for slow-fast stochastic systems near unknown invariant manifolds
- Computing committors in collective variables via Mahalanobis diffusion maps
- Transport map accelerated adaptive importance sampling, and application to inverse problems arising from multiscale stochastic reaction networks
- Reduction methods in climate dynamics -- a brief review
- Slow invariant manifolds of fast-slow systems of ODEs with physics-informed neural networks
- Manifold learning for organizing unstructured sets of process observations
- A computational method to extract macroscopic variables and their dynamics in multiscale systems
This page was built for publication: Data-Driven Reduction for a Class of Multiscale Fast-Slow Stochastic Dynamical Systems
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3188143)
