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

Active learning with multifidelity modeling for efficient rare event simulation

Journal Article · · Journal of Computational Physics
 [1];  [2];  [1];  [1];  [1];  [1];  [2]
  1. Idaho National Lab. (INL), Idaho Falls, ID (United States)
  2. Johns Hopkins University, Baltimore, MD (United States)
+ Show Author Affiliations

Here, while multifidelity modeling provides a cost-effective way to conduct uncertainty quantification with computationally expensive models, much greater efficiency can be achieved by adaptively deciding the number of required high-fidelity (HF) simulations, depending on the type and complexity of the problem and the desired accuracy in the results. We propose a framework for active learning with multifidelity modeling emphasizing the efficient estimation of rare events. Our framework works by fusing a low-fidelity (LF) prediction with an HF-inferred correction, filtering the corrected LF prediction to decide whether to call the high-fidelity model, and for enhanced subsequent accuracy, adapting the correction for the LF prediction after every HF model call. The framework does not make any assumptions as to the LF model type or its correlations with the HF model. In addition, for improved robustness when estimating smaller failure probabilities, we propose using dynamic active learning functions that decide when to call the HF model. We demonstrate our framework using several academic case studies (including some high-dimensional problems) and two finite element model case studies: estimating Navier-Stokes velocities using the Stokes approximation and estimating stresses in a transversely isotropic model subjected to displacements via a coarsely meshed isotropic model. Across these case studies, not only did the proposed framework estimate the failure probabilities accurately, but compared with either Monte Carlo or a standard variance reduction method, it also required only a small fraction of the calls to the HF model.

Research Organization:
Idaho National Laboratory (INL), Idaho Falls, ID (United States)
Sponsoring Organization:
USDOE Office of Nuclear Energy (NE); USDOE Laboratory Directed Research and Development (LDRD) Program
Grant/Contract Number:
AC07-05ID14517
OSTI ID:
1887215
Alternate ID(s):
OSTI ID: 1962227
Report Number(s):
INL/JOU-21-62824-Rev000
Journal Information:
Journal of Computational Physics, Journal Name: Journal of Computational Physics Journal Issue: 1 Vol. 468; ISSN 0021-9991
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (40)

Active learning method combining Kriging model and multimodal‐optimization‐based importance sampling for the estimation of small failure probability journal August 2020
Analysis of dataset selection for multi-fidelity surrogates for a turbine problem journal May 2018
An active-learning method based on multi-fidelity Kriging model for structural reliability analysis journal July 2020
Multi-fidelity modeling with different input domain definitions using deep Gaussian processes journal February 2021
Estimation of small failure probabilities in high dimensions by subset simulation journal October 2001
Overview of the incompressible Navier–Stokes simulation capabilities in the MOOSE framework journal May 2018
Accelerated subset simulation with neural networks for reliability analysis journal June 2012
Multifidelity importance sampling journal March 2016
Data-driven surrogates for high dimensional models using Gaussian process regression on the Grassmann manifold journal October 2020
Subset simulation for problems with strongly non-Gaussian, highly anisotropic, and degenerate distributions journal March 2021
High-dimensional and higher-order multifidelity Monte Carlo estimators journal July 2019
Multifidelity probability estimation via fusion of estimators journal September 2019
Physics-informed CoKriging: A Gaussian-process-regression-based multifidelity method for data-model convergence journal October 2019
A generalized approximate control variate framework for multifidelity uncertainty quantification journal May 2020
Transfer learning based multi-fidelity physics informed deep neural network journal February 2021
Multi-fidelity Bayesian neural networks: Algorithms and applications journal August 2021
TRISO particle fuel performance and failure analysis with BISON journal May 2021
MCMC algorithms for Subset Simulation journal July 2015
An active learning reliability method combining Kriging constructed with exploration and exploitation of failure region and subset simulation journal August 2019
Extension of AK-MCS for the efficient computation of very small failure probabilities journal November 2020
MOOSE: Enabling massively parallel multiphysics simulation journal January 2020
AK-MCS: An active learning reliability method combining Kriging and Monte Carlo Simulation journal March 2011
Assessing small failure probabilities by combined subset simulation and Support Vector Machines journal September 2011
Assessing small failure probabilities by AK–SS: An active learning method combining Kriging and Subset Simulation journal March 2016
AK-MCSi: A Kriging-based method to deal with small failure probabilities and time-consuming models journal July 2018
Hamiltonian Monte Carlo methods for Subset Simulation in reliability analysis journal January 2019
Implementation of machine learning techniques into the Subset Simulation method journal July 2019
AK-MSS: An adaptation of the AK-MCS method for small failure probabilities journal September 2020
Improved active learning probabilistic approach for the computation of failure probability journal January 2021
Inverse Modeling of Hydrologic Systems with Adaptive Multifidelity Markov Chain Monte Carlo Simulations journal July 2018
A Multilevel Stochastic Collocation Method for Partial Differential Equations with Random Input Data journal January 2015
Multifidelity Information Fusion Algorithms for High-Dimensional Systems and Massive Data sets 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 Approximate Bayesian Computation journal January 2020
Multifidelity computing for coupling full and reduced order models journal February 2021
MFNets: MULTI-FIDELITY DATA-DRIVEN NETWORKS FOR BAYESIAN LEARNING AND PREDICTION journal January 2020
Bayesian Inference of Stochastic Reaction Networks Using Multifidelity Sequential Tempered Markov Chain Monte Carlo journal January 2020
Efficient Global Reliability Analysis for Nonlinear Implicit Performance Functions journal October 2008
Issues in Deciding Whether to Use Multifidelity Surrogates journal May 2019

Figures / Tables (26)

Figure 1(p. 7)figure Figure 1
Figure 2(p. 11)figure Figure 2
Algorithm 1(p. 12)figure Algorithm 1
Algorithm 2(p. 14)figure Algorithm 2
Table 1(p. 17)table Table 1
Figure 3(p. 18)figure Figure 3
Figure 4(p. 19)figure Figure 4
Table 2(p. 19)table Table 2
Figure 5(p. 20)figure Figure 5
Table 3(p. 20)table Table 3
Table 4(p. 21)table Table 4
Table 5(p. 21)table Table 5
Figure 6(p. 22)figure Figure 6
Table 6(p. 22)table Table 6
Figure 7(p. 23)figure Figure 7
Figure 8(p. 24)figure Figure 8
Table 7(p. 24)table Table 7
Figure 9(p. 25)figure Figure 9
Figure 10(p. 26)figure Figure 10
Table 8(p. 26)table Table 8
Figure 11(p. 27)figure Figure 11
Table 10(p. 27)table Table 10
Table 9(p. 27)table Table 9
Figure 12(p. 28)figure Figure 12
Table 11(p. 28)table Table 11
Figure 13(p. 29)figure Figure 13

Similar Records

Efficient Reliability Analysis using Generalized Multifidelity Modeling and Explainable Active Learning
Conference · Fri Jun 23 00:00:00 EDT 2023 · OSTI ID:2396330
Reliability estimation of an advanced nuclear fuel using coupled active learning, multifidelity modeling, and subset simulation
Journal Article · Wed Jul 06 00:00:00 EDT 2022 · Reliability Engineering and System Safety · OSTI ID:1887585
CAMERA: A method for cost-aware, adaptive, multifidelity, efficient reliability analysis
Journal Article · Tue Oct 18 00:00:00 EDT 2022 · Journal of Computational Physics · OSTI ID:2433825

Related Subjects

42 ENGINEERING
97 MATHEMATICS AND COMPUTING
Monte Carlo
active learning
multifidelity modeling
reliability
uncertainty quantification
variance reduction