Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Boosting efficiency and reducing graph reliance: Basis adaptation integration in Bayesian multi-fidelity networks

Journal Article · · Computer Methods in Applied Mechanics and Engineering
 [1];  [2];  [3];  [2];  [1]
  1. Univ. of California, Los Angeles, CA (United States)
  2. Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
  3. Univ. of Michigan, Ann Arbor, MI (United States)

The computational cost of high-fidelity numerical models makes outer-loop analysis, which requires repeated interrogation of the model such as uncertainty quantification, computationally demanding. Multi-fidelity methods, which construct a surrogate model using data from an ensemble of models of varying cost and accuracy, can substantially reduce the cost of outer-loop analysis. However, these methods can be difficult to apply when the model ensemble does not admit a clear hierarchy a priori and the correlations between models are low. Consequently, in this paper, we present a multi-fidelity method that leverages dimension reduction to enhance the correlation between models, thereby reducing the amount of data needed to train a surrogate from an unordered ensemble of models. Our method utilizes basis adaptation to build low-dimensional polynomial chaos expansions of each model and employs Multi-fidelity Networks to encode the relationships among models. We show that the resulting method exhibit two notable advantages over its counterpart: (1) enhanced accuracy (both reduced bias and variance); and (2) reduced dependency on the graph structure encoding relationships among models. We demonstrate the approach on an analytical test problem and a challenging finite element model for a spent nuclear fuel. Our method produces a surrogate model that is significantly more accurate than either a single-fidelity surrogate or a multi-fidelity surrogate constructed without basis adaptation.

Research Organization:
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
Sponsoring Organization:
USDOE National Nuclear Security Administration (NNSA)
Grant/Contract Number:
NA0003525
OSTI ID:
2502152
Report Number(s):
SAND2025--00436J
Journal Information:
Computer Methods in Applied Mechanics and Engineering, Journal Name: Computer Methods in Applied Mechanics and Engineering Journal Issue: n/a Vol. 436; ISSN 0045-7825
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (61)

Multifidelity approaches for optimization under uncertainty: MULTIFIDELITY APPROACHES FOR OPTIMIZATION UNDER UNCERTAINTY journal September 2014
Dominant vibration modes for broadband frequency analysis of multiscale structures with numerous local vibration modes: Dominant vibration modes of complex multiscale structures journal November 2018
Adaptive multi‐index collocation for uncertainty quantification and sensitivity analysis
  • Jakeman, John D.; Eldred, Michael S.; Geraci, Gianluca
  • International Journal for Numerical Methods in Engineering, Vol. 121, Issue 6 https://doi.org/10.1002/nme.6268
journal November 2019
A note on two problems in connexion with graphs journal December 1959
Multi-index Monte Carlo: when sparsity meets sampling journal June 2015
Dominant substructural vibration modes for fully-loaded spent nuclear fuel canisters journal November 2020
MFNets: data efficient all-at-once learning of multifidelity surrogates as directed networks of information sources journal August 2021
Multilevel Monte Carlo methods and applications to elliptic PDEs with random coefficients journal January 2011
Multi-Index Stochastic Collocation for random PDEs journal July 2016
Multilevel and multifidelity uncertainty quantification for cardiovascular hemodynamics journal June 2020
Multiscale modal analysis of fully-loaded spent nuclear fuel canisters journal August 2020
Multi-fidelity deep neural network surrogate model for aerodynamic shape optimization journal January 2021
Accelerated basis adaptation in homogeneous chaos spaces journal December 2021
Multi-fidelity regression using artificial neural networks: Efficient approximation of parameter-dependent output quantities journal February 2022
Projection pursuit adaptation on polynomial chaos expansions journal February 2023
Context-aware learning of hierarchies of low-fidelity models for multi-fidelity uncertainty quantification journal March 2023
Multi-output multilevel best linear unbiased estimators via semidefinite programming journal August 2023
Multifidelity uncertainty quantification with models based on dissimilar parameters journal October 2023
Improved multifidelity Monte Carlo estimators based on normalizing flows and dimensionality reduction techniques journal September 2024
A non-adapted sparse approximation of PDEs with stochastic inputs journal April 2011
Basis adaptation in homogeneous chaos spaces journal February 2014
Compressive sampling of polynomial chaos expansions: Convergence analysis and sampling strategies journal January 2015
A low-rank control variate for multilevel Monte Carlo simulation of high-dimensional uncertain systems journal July 2017
Combining multiple surrogate models to accelerate failure probability estimation with expensive high-fidelity models journal July 2017
Bayesian deep convolutional encoder–decoder networks for surrogate modeling and uncertainty quantification journal August 2018
Gradient-based optimization for regression in the functional tensor-train format journal December 2018
Compressive sensing adaptation for polynomial chaos expansions journal March 2019
Multifidelity probability estimation via fusion of estimators journal September 2019
A composite neural network that learns from multi-fidelity data: Application to function approximation and inverse PDE problems journal January 2020
A generalized approximate control variate framework for multifidelity uncertainty quantification journal May 2020
Estimation of distributions via multilevel Monte Carlo with stratified sampling journal October 2020
On the optimization of approximate control variates with parametrically defined estimators journal February 2022
Predicting the output from a complex computer code when fast approximations are available journal March 2000
A Formal Basis for the Heuristic Determination of Minimum Cost Paths journal January 1968
A Multilevel Stochastic Collocation Method for Partial Differential Equations with Random Input Data journal January 2015
Optimal Model Management for Multifidelity Monte Carlo Estimation journal January 2016
Survey of Multifidelity Methods in Uncertainty Propagation, Inference, and Optimization journal January 2018
Multifidelity Monte Carlo Estimation of Variance and Sensitivity Indices journal January 2018
Multifidelity Monte Carlo Estimation with Adaptive Low-Fidelity Models journal January 2019
On Multilevel Best Linear Unbiased Estimators journal January 2020
Asymptotic Analysis of Multilevel Best Linear Unbiased Estimators journal January 2021
Context-Aware Surrogate Modeling for Balancing Approximation and Sampling Costs in Multifidelity Importance Sampling and Bayesian Inverse Problems journal March 2023
Covariance Expressions for Multifidelity Sampling with Multioutput, Multistatistic Estimators: Application to Approximate Control Variates journal September 2024
A Perspective on the Use of Control Variables to Increase the Efficiency of Monte Carlo Simulations journal March 1981
Multilevel Monte Carlo Path Simulation journal June 2008
Dimensionality Reduction for Complex Models via Bayesian Compressive Sensing journal January 2014
A Multi-Fidelity Neural Network Surrogate Sampling Method for Uncertainty Quantification journal January 2020
MFNets: MULTI-FIDELITY DATA-DRIVEN NETWORKS FOR BAYESIAN LEARNING AND PREDICTION journal January 2020
On Transfer Learning of Neural Networks Using Bi-Fidelity data for Uncertainty Propagation journal January 2020
Multilevel Monte Carlo Estimators for Derivative-Free Optimization Under Uncertainty journal January 2024
Exploring important directions for multifidelity uncertainty quantification by basis adaptation method. conference February 2021
Adaptive Basis for Multifidelity Uncertainty Quantification.
  • Zeng, Xiaoshu; Geraci, Gianluca; Eldred, Michael
  • Proposed for presentation at the 16th US National Congress on Computational Mechanics held July 26-30, 2021 in , . https://doi.org/10.2172/1889016
conference July 2021
Improving Bayesian Networks Multifidelity Surrogate Construction with Basis Adaptation
  • Zeng, Xiaoshu; Geraci, Gianluca; Gorodetsky, Alex
  • AIAA SciTech 2023 - National Harbor, Maryland, United States of America - January - 2023 https://doi.org/10.2172/2432101
conference January 2023
Multifidelity Uncertainty Propagation via Adaptive Surrogates in Coupled Multidisciplinary Systems journal January 2018
A multifidelity multilevel Monte Carlo method for uncertainty propagation in aerospace applications conference January 2017
Recent advancements in Multilevel-Multifidelity techniques for forward UQ in the DARPA Sequoia project conference January 2019
Towards an integrated and efficient framework for leveraging reduced order models for multifidelity uncertainty quantification conference January 2020
Improving Multi-Model Trajectory Simulation Estimators using Model Selection and Tuning conference January 2022
Strategies for Automation of Model Tuning in Multi-fidelity Trajectory Uncertainty Propagation conference January 2023
Multi-Fidelity Aerodynamic Data Fusion with a Deep Neural Network Modeling Method journal September 2020
Optimal weighted least-squares methods journal October 2017

Similar Records

Adaptive experimental design for multi-fidelity surrogate modeling of multi-disciplinary systems
Journal Article · Mon Feb 28 23:00:00 EST 2022 · International Journal for Numerical Methods in Engineering · OSTI ID:1855808

Adaptive resource allocation for surrogate modeling of systems comprised of multiple disciplines with varying fidelity
Technical Report · Sun Jul 11 00:00:00 EDT 2021 · OSTI ID:1807453