Multi-level restricted maximum likelihood covariance estimation and kriging for large non-gridded spatial datasets

Handle URI:
http://hdl.handle.net/10754/582461
Title:
Multi-level restricted maximum likelihood covariance estimation and kriging for large non-gridded spatial datasets
Authors:
Castrillon, Julio; Genton, Marc G. ( 0000-0001-6467-2998 ) ; Yokota, Rio
Abstract:
We develop a multi-level restricted Gaussian maximum likelihood method for estimating the covariance function parameters and computing the best unbiased predictor. Our approach produces a new set of multi-level contrasts where the deterministic parameters of the model are filtered out thus enabling the estimation of the covariance parameters to be decoupled from the deterministic component. Moreover, the multi-level covariance matrix of the contrasts exhibit fast decay that is dependent on the smoothness of the covariance function. Due to the fast decay of the multi-level covariance matrix coefficients only a small set is computed with a level dependent criterion. We demonstrate our approach on problems of up to 512,000 observations with a Matérn covariance function and highly irregular placements of the observations. In addition, these problems are numerically unstable and hard to solve with traditional methods.
KAUST Department:
Center for Uncertainty Quantification in Computational Science and Engineering (SRI-UQ); Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
Multi-level restricted maximum likelihood covariance estimation and kriging for large non-gridded spatial datasets 2015 Spatial Statistics
Publisher:
Elsevier BV
Journal:
Spatial Statistics
Issue Date:
10-Nov-2015
DOI:
10.1016/j.spasta.2015.10.006
Type:
Article
ISSN:
22116753
Additional Links:
http://linkinghub.elsevier.com/retrieve/pii/S2211675315000834
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorCastrillon, Julioen
dc.contributor.authorGenton, Marc G.en
dc.contributor.authorYokota, Rioen
dc.date.accessioned2015-11-22T07:10:17Zen
dc.date.available2015-11-22T07:10:17Zen
dc.date.issued2015-11-10en
dc.identifier.citationMulti-level restricted maximum likelihood covariance estimation and kriging for large non-gridded spatial datasets 2015 Spatial Statisticsen
dc.identifier.issn22116753en
dc.identifier.doi10.1016/j.spasta.2015.10.006en
dc.identifier.urihttp://hdl.handle.net/10754/582461en
dc.description.abstractWe develop a multi-level restricted Gaussian maximum likelihood method for estimating the covariance function parameters and computing the best unbiased predictor. Our approach produces a new set of multi-level contrasts where the deterministic parameters of the model are filtered out thus enabling the estimation of the covariance parameters to be decoupled from the deterministic component. Moreover, the multi-level covariance matrix of the contrasts exhibit fast decay that is dependent on the smoothness of the covariance function. Due to the fast decay of the multi-level covariance matrix coefficients only a small set is computed with a level dependent criterion. We demonstrate our approach on problems of up to 512,000 observations with a Matérn covariance function and highly irregular placements of the observations. In addition, these problems are numerically unstable and hard to solve with traditional methods.en
dc.language.isoenen
dc.publisherElsevier BVen
dc.relation.urlhttp://linkinghub.elsevier.com/retrieve/pii/S2211675315000834en
dc.rightsNOTICE: this is the author’s version of a work that was accepted for publication in Spatial Statistics. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in Spatial Statistics, 10 November 2015. DOI: 10.1016/j.spasta.2015.10.006en
dc.subjectFast Multipole Methoden
dc.subjectHierarchical basisen
dc.subjectHigh performance computingen
dc.subjectSparsification of covariance matricesen
dc.titleMulti-level restricted maximum likelihood covariance estimation and kriging for large non-gridded spatial datasetsen
dc.typeArticleen
dc.contributor.departmentCenter for Uncertainty Quantification in Computational Science and Engineering (SRI-UQ)en
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalSpatial Statisticsen
dc.eprint.versionPost-printen
dc.contributor.institutionTokyo Institute of Technology Global Scientific and Computing Center, 2-12-1 i7-2 O-okayama Meguro-ku, 152-8550, Tokyo, Japanen
dc.contributor.affiliationKing Abdullah University of Science and Technology (KAUST)en
kaust.authorCastrillon, Julioen
kaust.authorGenton, Marc G.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.