Manifold learning-based polynomial chaos expansions for high-dimensional surrogate models

Abstract

In this work we introduce a manifold learning-based method for uncertainty quantification (UQ) in systems describing complex spatiotemporal processes. Our first objective is to identify the embedding of a set of high-dimensional data representing quantities of interest of the computational or analytical model. For this purpose, we employ Grassmannian diffusion maps, a two-step nonlinear dimension reduction technique which allows us to reduce the dimensionality of the data and identify meaningful geometric descriptions in a parsimonious and inexpensive manner. Polynomial chaos expansion is then used to construct a mapping between the stochastic input parameters and the diffusion coordinates of the reduced space. An adaptive clustering technique is proposed to identify an optimal number of clusters of points in the latent space. The similarity of points allows us to construct a number of geometric harmonic emulators which are finally utilized as a set of inexpensive pre-trained models to perform an inverse map of realizations of latent features to the ambient space and thus perform accurate out-of-sample predictions. Thus, the proposed method acts as an encoder-decoder system which is able to automatically handle very high-dimensional data while simultaneously operating successfully in the small-data regime. The method is demonstrated on two benchmark problems and on a system of advection-diffusion-reaction equations which model a first-order chemical reaction between two species. In all test cases, the proposed method is able to achieve highly accurate approximations which ultimately lead to the significant acceleration of UQ tasks.

arXiv comment29 pages, 14 figures

References in corpus (24)

• Deep Learning in Neural Networks: An Overview
• Bayesian Deep Convolutional Encoder-Decoder Networks for Surrogate Modeling and Uncertainty Quantification
• Deep Learning Methods for Reynolds-Averaged Navier-Stokes Simulations of Airfoil Flows
• Deep UQ: Learning deep neural network surrogate models for high dimensional uncertainty quantification
• A non-adapted sparse approximation of PDEs with stochastic inputs
• Sparse Pseudospectral Approximation Method
• Enhancing ${\ell }_1$-minimization estimates of polynomial chaos expansions using basis selection
• Least Squares Polynomial Chaos Expansion: A Review of Sampling Strategies
• Sparse Polynomial Chaos Expansions via Compressed Sensing and D-optimal Design
• Data-driven probability concentration and sampling on manifold
• Efficient Uncertainty Quantification for Dynamic Subsurface Flow with Surrogate by Theory-guided Neural Network
• Polynomial chaos expansions for dependent random variables
• Compressive sensing adaptation for polynomial chaos expansions
• Data-driven surrogates for high dimensional models using Gaussian process regression on the Grassmann manifold
• Basis Adaptive Sample Efficient Polynomial Chaos (BASE-PC)
• Probabilistic learning on manifolds constrained by nonlinear partial differential equations for small datasets
• Grassmannian Learning: Embedding Geometry Awareness in Shallow and Deep Learning
• Uncertainty quantification for complex systems with very high dimensional response using Grassmann manifold variations
• A preconditioning approach for improved estimation of sparse polynomial chaos expansions
• Non-intrusive Surrogate Modeling for Parametrized Time-dependent PDEs using Convolutional Autoencoders
• Optimization on flag manifolds
• Nonlinear dimension reduction for surrogate modeling using gradient information
• Adaptive Sparse Polynomial Chaos Expansions via Leja Interpolation
• Grassmannian diffusion maps based dimension reduction and classification for high-dimensional data

Cited by in corpus (5)

• Multivariate sensitivity-adaptive polynomial chaos expansion for high-dimensional surrogate modeling and uncertainty quantification
• Data-driven Uncertainty Quantification in Computational Human Head Models
• Dimensionality reduction can be used as a surrogate model for high-dimensional forward uncertainty quantification
• Neural Chaos: A Spectral Stochastic Neural Operator
• A Resolution Independent Neural Operator