Data-driven surrogates for high dimensional models using Gaussian process regression on the Grassmann manifold

Abstract

This paper introduces a surrogate modeling scheme based on Grassmannian manifold learning to be used for cost-efficient predictions of high-dimensional stochastic systems. The method exploits subspace-structured features of each solution by projecting it onto a Grassmann manifold. The method utilizes a solution clustering approach in order to identify regions of the parameter space over which solutions are sufficiently similarly such that they can be interpolated on the Grassmannian. In this clustering, the reduced-order solutions are partitioned into disjoint clusters on the Grassmann manifold using the eigen-structure of properly defined Grassmannian kernels and, the Karcher mean of each cluster is estimated. Then, the points in each cluster are projected onto the tangent space with origin at the corresponding Karcher mean using the exponential mapping. For each cluster, a Gaussian process regression model is trained that maps the input parameters of the system to the reduced solution points of the corresponding cluster projected onto the tangent space. Using this Gaussian process model, the full-field solution can be efficiently predicted at any new point in the parameter space. In certain cases, the solution clusters will span disjoint regions of the parameter space. In such cases, for each of the solution clusters we utilize a second, density-based spatial clustering to group their corresponding input parameter points in the Euclidean space. The proposed method is applied to two numerical examples. The first is a nonlinear stochastic ordinary differential equation with uncertain initial conditions. The second involves modeling of plastic deformation in a model amorphous solid using the Shear Transformation Zone theory of plasticity.

31 pages, 22 Figures

References in corpus (14)

• Dynamics of Viscoplastic Deformation in Amorphous Solids
• Deformation and Failure of Amorphous Solidlike Materials
• Shear-transformation-zone theory of plastic deformation near the glass transition
• Evaluation of the "disorder temperature" and "free volume" formalisms via simulations of shear banding in amorphous solids
• Nonequilibrium Thermodynamics of Amorphous Materials II: Effective-Temperature Theory
• Data-driven probability concentration and sampling on manifold
• Nonequilibrium Thermodynamics of Amorphous Materials III: Shear-Transformation-Zone Plasticity
• Nonequilibrium Thermodynamics of Amorphous Materials I: Internal Degrees of Freedom and Volume Deformation
• An Eulerian projection method for quasi-static elastoplasticity
• Assessing the Performance of Leja and Clenshaw-Curtis Collocation for Computational Electromagnetics with Random Input Data
• Uncertainty quantification for complex systems with very high dimensional response using Grassmann manifold variations
• Parallel three-dimensional simulations of quasi-static elastoplastic solids
• Accelerated scale bridging with sparsely approximated Gaussian learning
• Probabilistic Performance-Pattern Decomposition (PPPD): analysis framework and applications to stochastic mechanical systems

Cited by in corpus (19)

• Active Learning with Multifidelity Modeling for Efficient Rare Event Simulation
• Latent Map Gaussian Processes for Mixed Variable Metamodeling
• On the influence of over-parameterization in manifold based surrogates and deep neural operators
• Probabilistic learning on manifolds constrained by nonlinear partial differential equations for small datasets
• Manifold learning-based polynomial chaos expansions for high-dimensional surrogate models
• Adaptive active subspace-based metamodeling for high-dimensional reliability analysis
• Projection pursuit adaptation on polynomial chaos expansions
• A physics and data co-driven surrogate modeling method for high-dimensional rare event simulation
• Data-driven Uncertainty Quantification in Computational Human Head Models
• From partial data to out-of-sample parameter and observation estimation with Diffusion Maps and Geometric Harmonics
• Dimensionality reduction can be used as a surrogate model for high-dimensional forward uncertainty quantification
• Grassmannian diffusion maps based surrogate modeling via geometric harmonics
• Learning thermodynamically constrained equations of state with uncertainty
• Probabilistic learning inference of boundary value problem with uncertainties based on Kullback-Leibler divergence under implicit constraints
• Polynomial Chaos Expansions on Principal Geodesic Grassmannian Submanifolds for Surrogate Modeling and Uncertainty Quantification
• Simpler Grassmannian optimization
• Navigating Uncertainties in Machine Learning for Structural Dynamics: A Comprehensive Survey of Probabilistic and Non-Probabilistic Approaches in Forward and Inverse Problems
• Bi-invariant Geodesic Regression with Data from the Osteoarthritis Initiative
• A survey of unsupervised learning methods for high-dimensional uncertainty quantification in black-box-type problems