Data-driven uncertainty quantification for predictive flow and transport modeling using support vector machines.
Saved in:
| Title: | Data-driven uncertainty quantification for predictive flow and transport modeling using support vector machines. |
|---|---|
| Authors: | He, Jiachuan1,2 (AUTHOR), Mattis, Steven A.3 (AUTHOR), Butler, Troy D.4 (AUTHOR), Dawson, Clint N.1,2 (AUTHOR) clint@ices.utexas.edu |
| Source: | Computational Geosciences. Aug2019, Vol. 23 Issue 4, p631-645. 15p. |
| Subjects: | Support vector machines, Groundwater flow, Inverse problems, Hydraulic conductivity, Measure theory, Probability measures |
| Abstract: | Specification of hydraulic conductivity as a model parameter in groundwater flow and transport equations is an essential step in predictive simulations. It is often infeasible in practice to characterize this model parameter at all points in space due to complex hydrogeological environments leading to significant parameter uncertainties. Quantifying these uncertainties requires the formulation and solution of an inverse problem using data corresponding to observable model responses. Several types of inverse problems may be formulated under various physical and statistical assumptions on the model parameters, model response, and the data. Solutions to most types of inverse problems require large numbers of model evaluations. In this study, we incorporate the use of surrogate models based on support vector machines to increase the number of samples used in approximating a solution to an inverse problem at a relatively low computational cost. To test the global capabilities of this type of surrogate model for quantifying uncertainties, we use a framework rooted in measure theory for constructing pullback and push-forward probability measures to study the data-to-parameter-to-prediction propagation of uncertainties under minimal statistical assumptions. Additionally, we demonstrate that it is possible to build a support vector machine using relatively low-dimensional representations of the hydraulic conductivity to propagate distributions. The numerical examples further demonstrate that we can make reliable probabilistic predictions of contaminant concentration at spatial locations. [ABSTRACT FROM AUTHOR] |
| Copyright of Computational Geosciences is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
| FullText | Links: – Type: pdflink Text: Availability: 0 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 137684632 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Data-driven uncertainty quantification for predictive flow and transport modeling using support vector machines. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22He%2C+Jiachuan%22">He, Jiachuan</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Mattis%2C+Steven+A%2E%22">Mattis, Steven A.</searchLink><relatesTo>3</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Butler%2C+Troy+D%2E%22">Butler, Troy D.</searchLink><relatesTo>4</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Dawson%2C+Clint+N%2E%22">Dawson, Clint N.</searchLink><relatesTo>1,2</relatesTo> (AUTHOR)<i> clint@ices.utexas.edu</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Computational+Geosciences%22">Computational Geosciences</searchLink>. Aug2019, Vol. 23 Issue 4, p631-645. 15p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Support+vector+machines%22">Support vector machines</searchLink><br /><searchLink fieldCode="DE" term="%22Groundwater+flow%22">Groundwater flow</searchLink><br /><searchLink fieldCode="DE" term="%22Inverse+problems%22">Inverse problems</searchLink><br /><searchLink fieldCode="DE" term="%22Hydraulic+conductivity%22">Hydraulic conductivity</searchLink><br /><searchLink fieldCode="DE" term="%22Measure+theory%22">Measure theory</searchLink><br /><searchLink fieldCode="DE" term="%22Probability+measures%22">Probability measures</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: Specification of hydraulic conductivity as a model parameter in groundwater flow and transport equations is an essential step in predictive simulations. It is often infeasible in practice to characterize this model parameter at all points in space due to complex hydrogeological environments leading to significant parameter uncertainties. Quantifying these uncertainties requires the formulation and solution of an inverse problem using data corresponding to observable model responses. Several types of inverse problems may be formulated under various physical and statistical assumptions on the model parameters, model response, and the data. Solutions to most types of inverse problems require large numbers of model evaluations. In this study, we incorporate the use of surrogate models based on support vector machines to increase the number of samples used in approximating a solution to an inverse problem at a relatively low computational cost. To test the global capabilities of this type of surrogate model for quantifying uncertainties, we use a framework rooted in measure theory for constructing pullback and push-forward probability measures to study the data-to-parameter-to-prediction propagation of uncertainties under minimal statistical assumptions. Additionally, we demonstrate that it is possible to build a support vector machine using relatively low-dimensional representations of the hydraulic conductivity to propagate distributions. The numerical examples further demonstrate that we can make reliable probabilistic predictions of contaminant concentration at spatial locations. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Computational Geosciences is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=137684632 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s10596-018-9762-4 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 15 StartPage: 631 Subjects: – SubjectFull: Support vector machines Type: general – SubjectFull: Groundwater flow Type: general – SubjectFull: Inverse problems Type: general – SubjectFull: Hydraulic conductivity Type: general – SubjectFull: Measure theory Type: general – SubjectFull: Probability measures Type: general Titles: – TitleFull: Data-driven uncertainty quantification for predictive flow and transport modeling using support vector machines. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: He, Jiachuan – PersonEntity: Name: NameFull: Mattis, Steven A. – PersonEntity: Name: NameFull: Butler, Troy D. – PersonEntity: Name: NameFull: Dawson, Clint N. IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 08 Text: Aug2019 Type: published Y: 2019 Identifiers: – Type: issn-print Value: 14200597 Numbering: – Type: volume Value: 23 – Type: issue Value: 4 Titles: – TitleFull: Computational Geosciences Type: main |
| ResultId | 1 |
