Efficient particle filtering through residual nudging

Handle URI:
http://hdl.handle.net/10754/562765
Title:
Efficient particle filtering through residual nudging
Authors:
Luo, Xiaodong; Hoteit, Ibrahim ( 0000-0002-3751-4393 )
Abstract:
We introduce an auxiliary technique, called residual nudging, to the particle filter to enhance its performance in cases where it performs poorly. The main idea of residual nudging is to monitor and, if necessary, adjust the residual norm of a state estimate in the observation space so that it does not exceed a pre-specified threshold. We suggest a rule to choose the pre-specified threshold, and construct a state estimate accordingly to achieve this objective. Numerical experiments suggest that introducing residual nudging to a particle filter may (substantially) improve its performance, in terms of filter accuracy and/or stability against divergence, especially when the particle filter is implemented with a relatively small number of particles. © 2013 Royal Meteorological Society.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division; Physical Sciences and Engineering (PSE) Division; Environmental Science and Engineering Program; Earth Fluid Modeling and Prediction Group
Publisher:
Wiley
Journal:
Quarterly Journal of the Royal Meteorological Society
Issue Date:
15-May-2013
DOI:
10.1002/qj.2152
ARXIV:
arXiv:1303.2698
Type:
Article
ISSN:
00359009
Sponsors:
We thank Dr M. Bocquet, Dr C. Snyder and two anonymous reviewers for their constructive and inspiring comments and suggestions. We have also benefited from useful discussions with Dr Geir Naevdal and Dr Andreas Stordal at IRIS. Luo acknowledges partial financial support from the Research Council of Norway and industrial partners through the project 'Transient well flow modelling and modern estimation techniques for accurate production allocation'.
Additional Links:
http://arxiv.org/abs/arXiv:1303.2698v1
Appears in Collections:
Articles; Environmental Science and Engineering Program; Physical Sciences and Engineering (PSE) Division; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorLuo, Xiaodongen
dc.contributor.authorHoteit, Ibrahimen
dc.date.accessioned2015-08-03T11:04:54Zen
dc.date.available2015-08-03T11:04:54Zen
dc.date.issued2013-05-15en
dc.identifier.issn00359009en
dc.identifier.doi10.1002/qj.2152en
dc.identifier.urihttp://hdl.handle.net/10754/562765en
dc.description.abstractWe introduce an auxiliary technique, called residual nudging, to the particle filter to enhance its performance in cases where it performs poorly. The main idea of residual nudging is to monitor and, if necessary, adjust the residual norm of a state estimate in the observation space so that it does not exceed a pre-specified threshold. We suggest a rule to choose the pre-specified threshold, and construct a state estimate accordingly to achieve this objective. Numerical experiments suggest that introducing residual nudging to a particle filter may (substantially) improve its performance, in terms of filter accuracy and/or stability against divergence, especially when the particle filter is implemented with a relatively small number of particles. © 2013 Royal Meteorological Society.en
dc.description.sponsorshipWe thank Dr M. Bocquet, Dr C. Snyder and two anonymous reviewers for their constructive and inspiring comments and suggestions. We have also benefited from useful discussions with Dr Geir Naevdal and Dr Andreas Stordal at IRIS. Luo acknowledges partial financial support from the Research Council of Norway and industrial partners through the project 'Transient well flow modelling and modern estimation techniques for accurate production allocation'.en
dc.publisherWileyen
dc.relation.urlhttp://arxiv.org/abs/arXiv:1303.2698v1en
dc.subjectData assimilationen
dc.subjectParticle filteren
dc.subjectResidual nudgingen
dc.titleEfficient particle filtering through residual nudgingen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.contributor.departmentPhysical Sciences and Engineering (PSE) Divisionen
dc.contributor.departmentEnvironmental Science and Engineering Programen
dc.contributor.departmentEarth Fluid Modeling and Prediction Groupen
dc.identifier.journalQuarterly Journal of the Royal Meteorological Societyen
dc.contributor.institutionInternational Research Institute of Stavanger, Bergen, Norwayen
dc.identifier.arxividarXiv:1303.2698en
kaust.authorHoteit, Ibrahimen
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.