An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation Analysis

To quantify the uncertainties in multi-dimensional flow field correlated responses caused by uncertain model parameters, this paper presents an adaptive multi-fidelity model based on gappy proper orthogonal decomposition (Gappy-POD), which integrates the two conventional approaches for enhancing the...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei Xiao, Yingying Shen, Jiao Zhao, Luogeng Lv, Jiangtao Chen, Wei Zhao
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/6/3359
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850205279190253568
author Wei Xiao
Yingying Shen
Jiao Zhao
Luogeng Lv
Jiangtao Chen
Wei Zhao
author_facet Wei Xiao
Yingying Shen
Jiao Zhao
Luogeng Lv
Jiangtao Chen
Wei Zhao
author_sort Wei Xiao
collection DOAJ
description To quantify the uncertainties in multi-dimensional flow field correlated responses caused by uncertain model parameters, this paper presents an adaptive multi-fidelity model based on gappy proper orthogonal decomposition (Gappy-POD), which integrates the two conventional approaches for enhancing the efficiency of surrogate modeling, namely, multi-fidelity modeling and adaptive sampling algorithms. The challenges surrounding the selection of initial high-fidelity samples and the subsequent incremental augmentation of these samples are addressed. The <i>k</i>-means clustering algorithm is employed to identify locations within the parameter space for conducting high-fidelity simulations, leveraging insights gained from low-fidelity responses. An adaptive sampling criterion, leveraging the low-fidelity projection error derived from the Gappy-POD method, is implemented to progressively augment high-fidelity samples. The results demonstrate that the adaptive model consistently outperforms random sampling methods, highlighting its superiority in terms of accuracy and reliability, providing an efficient and reliable prediction model for uncertainty quantification.
format Article
id doaj-art-40563a78aaa6404e8b8af8e50256993c
institution OA Journals
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-40563a78aaa6404e8b8af8e50256993c2025-08-20T02:11:08ZengMDPI AGApplied Sciences2076-34172025-03-01156335910.3390/app15063359An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation AnalysisWei Xiao0Yingying Shen1Jiao Zhao2Luogeng Lv3Jiangtao Chen4Wei Zhao5China Aerodynamics Research and Development Center, Mianyang 621000, ChinaChina Aerodynamics Research and Development Center, Mianyang 621000, ChinaChina Aerodynamics Research and Development Center, Mianyang 621000, ChinaChina Aerodynamics Research and Development Center, Mianyang 621000, ChinaChina Aerodynamics Research and Development Center, Mianyang 621000, ChinaChina Aerodynamics Research and Development Center, Mianyang 621000, ChinaTo quantify the uncertainties in multi-dimensional flow field correlated responses caused by uncertain model parameters, this paper presents an adaptive multi-fidelity model based on gappy proper orthogonal decomposition (Gappy-POD), which integrates the two conventional approaches for enhancing the efficiency of surrogate modeling, namely, multi-fidelity modeling and adaptive sampling algorithms. The challenges surrounding the selection of initial high-fidelity samples and the subsequent incremental augmentation of these samples are addressed. The <i>k</i>-means clustering algorithm is employed to identify locations within the parameter space for conducting high-fidelity simulations, leveraging insights gained from low-fidelity responses. An adaptive sampling criterion, leveraging the low-fidelity projection error derived from the Gappy-POD method, is implemented to progressively augment high-fidelity samples. The results demonstrate that the adaptive model consistently outperforms random sampling methods, highlighting its superiority in terms of accuracy and reliability, providing an efficient and reliable prediction model for uncertainty quantification.https://www.mdpi.com/2076-3417/15/6/3359adaptive samplingmulti-fidelity modelmulti-dimensional correlated responsesmachine learningflow field reduction
spellingShingle Wei Xiao
Yingying Shen
Jiao Zhao
Luogeng Lv
Jiangtao Chen
Wei Zhao
An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation Analysis
Applied Sciences
adaptive sampling
multi-fidelity model
multi-dimensional correlated responses
machine learning
flow field reduction
title An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation Analysis
title_full An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation Analysis
title_fullStr An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation Analysis
title_full_unstemmed An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation Analysis
title_short An Adaptive Multi-Fidelity Surrogate Model for Uncertainty Propagation Analysis
title_sort adaptive multi fidelity surrogate model for uncertainty propagation analysis
topic adaptive sampling
multi-fidelity model
multi-dimensional correlated responses
machine learning
flow field reduction
url https://www.mdpi.com/2076-3417/15/6/3359
work_keys_str_mv AT weixiao anadaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT yingyingshen anadaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT jiaozhao anadaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT luogenglv anadaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT jiangtaochen anadaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT weizhao anadaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT weixiao adaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT yingyingshen adaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT jiaozhao adaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT luogenglv adaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT jiangtaochen adaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis
AT weizhao adaptivemultifidelitysurrogatemodelforuncertaintypropagationanalysis