Ensemble Kalman filter regularization using leave-one-out data cross-validation

Handle URI:
http://hdl.handle.net/10754/552767
Title:
Ensemble Kalman filter regularization using leave-one-out data cross-validation
Authors:
Rayo Schiappacasse, Lautaro Jerónimo; Hoteit, Ibrahim ( 0000-0002-3751-4393 )
Abstract:
In this work, the classical leave-one-out cross-validation method for selecting a regularization parameter for the Tikhonov problem is implemented within the EnKF framework. Following the original concept, the regularization parameter is selected such that it minimizes the predictive error. Some ideas about the implementation, suitability and conceptual interest of the method are discussed. Finally, what will be called the data cross-validation regularized EnKF (dCVr-EnKF) is implemented in a 2D 2-phase synthetic oil reservoir experiment and the results analyzed.
KAUST Department:
Marine Science Program; Physical Sciences and Engineering (PSE) Division
Citation:
Ensemble Kalman filter regularization using leave-one-out data cross-validation, AIP Conference Proceedings 1479 , 1247 (2012); doi: 10.1063/1.4756379
Publisher:
AIP Publishing
Conference/Event name:
International Conference of Numerical Analysis and Applied Mathematics, ICNAAM 2012
Issue Date:
19-Sep-2012
DOI:
10.1063/1.4756379
Type:
Conference Paper
Additional Links:
http://scitation.aip.org/content/aip/proceeding/aipcp/10.1063/1.4756379
Appears in Collections:
Conference Papers; Marine Science Program; Physical Sciences and Engineering (PSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorRayo Schiappacasse, Lautaro Jerónimoen
dc.contributor.authorHoteit, Ibrahimen
dc.date.accessioned2015-05-14T06:43:11Zen
dc.date.available2015-05-14T06:43:11Zen
dc.date.issued2012-09-19en
dc.identifier.citationEnsemble Kalman filter regularization using leave-one-out data cross-validation, AIP Conference Proceedings 1479 , 1247 (2012); doi: 10.1063/1.4756379en
dc.identifier.doi10.1063/1.4756379en
dc.identifier.urihttp://hdl.handle.net/10754/552767en
dc.description.abstractIn this work, the classical leave-one-out cross-validation method for selecting a regularization parameter for the Tikhonov problem is implemented within the EnKF framework. Following the original concept, the regularization parameter is selected such that it minimizes the predictive error. Some ideas about the implementation, suitability and conceptual interest of the method are discussed. Finally, what will be called the data cross-validation regularized EnKF (dCVr-EnKF) is implemented in a 2D 2-phase synthetic oil reservoir experiment and the results analyzed.en
dc.publisherAIP Publishingen
dc.relation.urlhttp://scitation.aip.org/content/aip/proceeding/aipcp/10.1063/1.4756379en
dc.rightsArchived with thanks to AIP Conference Proceedingsen
dc.titleEnsemble Kalman filter regularization using leave-one-out data cross-validationen
dc.typeConference Paperen
dc.contributor.departmentMarine Science Programen
dc.contributor.departmentPhysical Sciences and Engineering (PSE) Divisionen
dc.conference.date2012-09-19 to 2012-09-25en
dc.conference.nameInternational Conference of Numerical Analysis and Applied Mathematics, ICNAAM 2012en
dc.conference.locationKos, GRCen
dc.eprint.versionPublisher's Version/PDFen
kaust.authorHoteit, Ibrahimen
kaust.authorRayo Schiappacasse, Lautaro Jerónimoen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.