A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters

This paper proposes a hierarchical, multi-resolution framework for the identification of model parameters and their spatially variability from noisy measurements of the response or output. Such parameters are frequently encountered in PDE-based models and correspond to quantities such as density or...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:arXiv.org 2008-10
1. Verfasser: Koutsourelakis, P S
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Koutsourelakis, P S
description This paper proposes a hierarchical, multi-resolution framework for the identification of model parameters and their spatially variability from noisy measurements of the response or output. Such parameters are frequently encountered in PDE-based models and correspond to quantities such as density or pressure fields, elasto-plastic moduli and internal variables in solid mechanics, conductivity fields in heat diffusion problems, permeability fields in fluid flow through porous media etc. The proposed model has all the advantages of traditional Bayesian formulations such as the ability to produce measures of confidence for the inferences made and providing not only predictive estimates but also quantitative measures of the predictive uncertainty. In contrast to existing approaches it utilizes a parsimonious, non-parametric formulation that favors sparse representations and whose complexity can be determined from the data. The proposed framework in non-intrusive and makes use of a sequence of forward solvers operating at various resolutions. As a result, inexpensive, coarse solvers are used to identify the most salient features of the unknown field(s) which are subsequently enriched by invoking solvers operating at finer resolutions. This leads to significant computational savings particularly in problems involving computationally demanding forward models but also improvements in accuracy. It is based on a novel, adaptive scheme based on Sequential Monte Carlo sampling which is embarrassingly parallelizable and circumvents issues with slow mixing encountered in Markov Chain Monte Carlo schemes.
doi_str_mv 10.48550/arxiv.0810.0744
format Article
fullrecord <record><control><sourceid>proquest_arxiv</sourceid><recordid>TN_cdi_arxiv_primary_0810_0744</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2081662423</sourcerecordid><originalsourceid>FETCH-LOGICAL-a513-83d8802ff0ca5d32b48ab5b435390e82b621236aed19be17986110631992faa23</originalsourceid><addsrcrecordid>eNotkEtrwzAQhEWh0JDm3lMR9BqlejryMQ19QaCX3M3alopS23IlO23-feUmp12GmWH4ELpjdCW1UvQRwq87rqhOAl1LeYVmXAhGtOT8Bi1iPFBKebbmSokZ8hvcjs3gSDDRN-PgfLfEne9IDwFaMwRXLfETnEx00GE7aT8-fGHrA3a16QZnXQVTDHuLY59eaJoTOUI4ue4Tt742Db6UmRBv0bWFJprF5c7R_uV5v30ju4_X9-1mR0AxQbSotabcWlqBqgUvpYZSlVIokVOjeZlxxkUGpmZ5adg61xljNBMsz7kF4GKO7s-1_zCKPrg2DSomKMUEJRkezoY--O_RxKE4-DF0aVLBkyvLuEzU_gDhUGXZ</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2081662423</pqid></control><display><type>article</type><title>A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters</title><source>Freely Accessible Journals</source><source>arXiv.org</source><creator>Koutsourelakis, P S</creator><creatorcontrib>Koutsourelakis, P S</creatorcontrib><description>This paper proposes a hierarchical, multi-resolution framework for the identification of model parameters and their spatially variability from noisy measurements of the response or output. Such parameters are frequently encountered in PDE-based models and correspond to quantities such as density or pressure fields, elasto-plastic moduli and internal variables in solid mechanics, conductivity fields in heat diffusion problems, permeability fields in fluid flow through porous media etc. The proposed model has all the advantages of traditional Bayesian formulations such as the ability to produce measures of confidence for the inferences made and providing not only predictive estimates but also quantitative measures of the predictive uncertainty. In contrast to existing approaches it utilizes a parsimonious, non-parametric formulation that favors sparse representations and whose complexity can be determined from the data. The proposed framework in non-intrusive and makes use of a sequence of forward solvers operating at various resolutions. As a result, inexpensive, coarse solvers are used to identify the most salient features of the unknown field(s) which are subsequently enriched by invoking solvers operating at finer resolutions. This leads to significant computational savings particularly in problems involving computationally demanding forward models but also improvements in accuracy. It is based on a novel, adaptive scheme based on Sequential Monte Carlo sampling which is embarrassingly parallelizable and circumvents issues with slow mixing encountered in Markov Chain Monte Carlo schemes.</description><identifier>EISSN: 2331-8422</identifier><identifier>DOI: 10.48550/arxiv.0810.0744</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Bayesian analysis ; Computational fluid dynamics ; Computer simulation ; Fluid flow ; Formulations ; Markov chains ; Mathematical models ; Mathematics - Mathematical Physics ; Model accuracy ; Monte Carlo simulation ; Parallel processing ; Parameter identification ; Physics - Mathematical Physics ; Porous media ; Porous media flow ; Solid mechanics ; Solvers ; Statistics - Methodology</subject><ispartof>arXiv.org, 2008-10</ispartof><rights>2008. This work is published under http://arxiv.org/licenses/nonexclusive-distrib/1.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,781,785,886,27930</link.rule.ids><backlink>$$Uhttps://doi.org/10.48550/arXiv.0810.0744$$DView paper in arXiv$$Hfree_for_read</backlink><backlink>$$Uhttps://doi.org/10.1016/j.jcp.2009.05.016$$DView published paper (Access to full text may be restricted)$$Hfree_for_read</backlink></links><search><creatorcontrib>Koutsourelakis, P S</creatorcontrib><title>A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters</title><title>arXiv.org</title><description>This paper proposes a hierarchical, multi-resolution framework for the identification of model parameters and their spatially variability from noisy measurements of the response or output. Such parameters are frequently encountered in PDE-based models and correspond to quantities such as density or pressure fields, elasto-plastic moduli and internal variables in solid mechanics, conductivity fields in heat diffusion problems, permeability fields in fluid flow through porous media etc. The proposed model has all the advantages of traditional Bayesian formulations such as the ability to produce measures of confidence for the inferences made and providing not only predictive estimates but also quantitative measures of the predictive uncertainty. In contrast to existing approaches it utilizes a parsimonious, non-parametric formulation that favors sparse representations and whose complexity can be determined from the data. The proposed framework in non-intrusive and makes use of a sequence of forward solvers operating at various resolutions. As a result, inexpensive, coarse solvers are used to identify the most salient features of the unknown field(s) which are subsequently enriched by invoking solvers operating at finer resolutions. This leads to significant computational savings particularly in problems involving computationally demanding forward models but also improvements in accuracy. It is based on a novel, adaptive scheme based on Sequential Monte Carlo sampling which is embarrassingly parallelizable and circumvents issues with slow mixing encountered in Markov Chain Monte Carlo schemes.</description><subject>Bayesian analysis</subject><subject>Computational fluid dynamics</subject><subject>Computer simulation</subject><subject>Fluid flow</subject><subject>Formulations</subject><subject>Markov chains</subject><subject>Mathematical models</subject><subject>Mathematics - Mathematical Physics</subject><subject>Model accuracy</subject><subject>Monte Carlo simulation</subject><subject>Parallel processing</subject><subject>Parameter identification</subject><subject>Physics - Mathematical Physics</subject><subject>Porous media</subject><subject>Porous media flow</subject><subject>Solid mechanics</subject><subject>Solvers</subject><subject>Statistics - Methodology</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2008</creationdate><recordtype>article</recordtype><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GOX</sourceid><recordid>eNotkEtrwzAQhEWh0JDm3lMR9BqlejryMQ19QaCX3M3alopS23IlO23-feUmp12GmWH4ELpjdCW1UvQRwq87rqhOAl1LeYVmXAhGtOT8Bi1iPFBKebbmSokZ8hvcjs3gSDDRN-PgfLfEne9IDwFaMwRXLfETnEx00GE7aT8-fGHrA3a16QZnXQVTDHuLY59eaJoTOUI4ue4Tt742Db6UmRBv0bWFJprF5c7R_uV5v30ju4_X9-1mR0AxQbSotabcWlqBqgUvpYZSlVIokVOjeZlxxkUGpmZ5adg61xljNBMsz7kF4GKO7s-1_zCKPrg2DSomKMUEJRkezoY--O_RxKE4-DF0aVLBkyvLuEzU_gDhUGXZ</recordid><startdate>20081004</startdate><enddate>20081004</enddate><creator>Koutsourelakis, P S</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope><scope>AKZ</scope><scope>EPD</scope><scope>GOX</scope></search><sort><creationdate>20081004</creationdate><title>A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters</title><author>Koutsourelakis, P S</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a513-83d8802ff0ca5d32b48ab5b435390e82b621236aed19be17986110631992faa23</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2008</creationdate><topic>Bayesian analysis</topic><topic>Computational fluid dynamics</topic><topic>Computer simulation</topic><topic>Fluid flow</topic><topic>Formulations</topic><topic>Markov chains</topic><topic>Mathematical models</topic><topic>Mathematics - Mathematical Physics</topic><topic>Model accuracy</topic><topic>Monte Carlo simulation</topic><topic>Parallel processing</topic><topic>Parameter identification</topic><topic>Physics - Mathematical Physics</topic><topic>Porous media</topic><topic>Porous media flow</topic><topic>Solid mechanics</topic><topic>Solvers</topic><topic>Statistics - Methodology</topic><toplevel>online_resources</toplevel><creatorcontrib>Koutsourelakis, P S</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection><collection>arXiv Mathematics</collection><collection>arXiv Statistics</collection><collection>arXiv.org</collection><jtitle>arXiv.org</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Koutsourelakis, P S</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters</atitle><jtitle>arXiv.org</jtitle><date>2008-10-04</date><risdate>2008</risdate><eissn>2331-8422</eissn><abstract>This paper proposes a hierarchical, multi-resolution framework for the identification of model parameters and their spatially variability from noisy measurements of the response or output. Such parameters are frequently encountered in PDE-based models and correspond to quantities such as density or pressure fields, elasto-plastic moduli and internal variables in solid mechanics, conductivity fields in heat diffusion problems, permeability fields in fluid flow through porous media etc. The proposed model has all the advantages of traditional Bayesian formulations such as the ability to produce measures of confidence for the inferences made and providing not only predictive estimates but also quantitative measures of the predictive uncertainty. In contrast to existing approaches it utilizes a parsimonious, non-parametric formulation that favors sparse representations and whose complexity can be determined from the data. The proposed framework in non-intrusive and makes use of a sequence of forward solvers operating at various resolutions. As a result, inexpensive, coarse solvers are used to identify the most salient features of the unknown field(s) which are subsequently enriched by invoking solvers operating at finer resolutions. This leads to significant computational savings particularly in problems involving computationally demanding forward models but also improvements in accuracy. It is based on a novel, adaptive scheme based on Sequential Monte Carlo sampling which is embarrassingly parallelizable and circumvents issues with slow mixing encountered in Markov Chain Monte Carlo schemes.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><doi>10.48550/arxiv.0810.0744</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2008-10
issn 2331-8422
language eng
recordid cdi_arxiv_primary_0810_0744
source Freely Accessible Journals; arXiv.org
subjects Bayesian analysis
Computational fluid dynamics
Computer simulation
Fluid flow
Formulations
Markov chains
Mathematical models
Mathematics - Mathematical Physics
Model accuracy
Monte Carlo simulation
Parallel processing
Parameter identification
Physics - Mathematical Physics
Porous media
Porous media flow
Solid mechanics
Solvers
Statistics - Methodology
title A multi-resolution, non-parametric, Bayesian framework for identification of spatially-varying model parameters
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-14T14%3A25%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_arxiv&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20multi-resolution,%20non-parametric,%20Bayesian%20framework%20for%20identification%20of%20spatially-varying%20model%20parameters&rft.jtitle=arXiv.org&rft.au=Koutsourelakis,%20P%20S&rft.date=2008-10-04&rft.eissn=2331-8422&rft_id=info:doi/10.48550/arxiv.0810.0744&rft_dat=%3Cproquest_arxiv%3E2081662423%3C/proquest_arxiv%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2081662423&rft_id=info:pmid/&rfr_iscdi=true