An adaptive spatial model for precipitation data from multiple satellites over large regions

Handle URI:
http://hdl.handle.net/10754/552390
Title:
An adaptive spatial model for precipitation data from multiple satellites over large regions
Authors:
Chakraborty, Avishek; De, Swarup; Bowman, Kenneth P.; Sang, Huiyan; Genton, Marc G. ( 0000-0001-6467-2998 ) ; Mallick, Bani K.
Abstract:
Satellite measurements have of late become an important source of information for climate features such as precipitation due to their near-global coverage. In this article, we look at a precipitation dataset during a 3-hour window over tropical South America that has information from two satellites. We develop a flexible hierarchical model to combine instantaneous rainrate measurements from those satellites while accounting for their potential heterogeneity. Conceptually, we envision an underlying precipitation surface that influences the observed rain as well as absence of it. The surface is specified using a mean function centered at a set of knot locations, to capture the local patterns in the rainrate, combined with a residual Gaussian process to account for global correlation across sites. To improve over the commonly used pre-fixed knot choices, an efficient reversible jump scheme is used to allow the number of such knots as well as the order and support of associated polynomial terms to be chosen adaptively. To facilitate computation over a large region, a reduced rank approximation for the parent Gaussian process is employed.
KAUST Department:
Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Citation:
An adaptive spatial model for precipitation data from multiple satellites over large regions 2013, 25 (2):389 Statistics and Computing
Publisher:
Springer Nature
Journal:
Statistics and Computing
Issue Date:
1-Mar-2015
DOI:
10.1007/s11222-013-9439-8
Type:
Article
ISSN:
0960-3174; 1573-1375
Additional Links:
http://link.springer.com/10.1007/s11222-013-9439-8
Appears in Collections:
Articles; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

Full metadata record

DC FieldValue Language
dc.contributor.authorChakraborty, Avisheken
dc.contributor.authorDe, Swarupen
dc.contributor.authorBowman, Kenneth P.en
dc.contributor.authorSang, Huiyanen
dc.contributor.authorGenton, Marc G.en
dc.contributor.authorMallick, Bani K.en
dc.date.accessioned2015-05-06T13:32:15Zen
dc.date.available2015-05-06T13:32:15Zen
dc.date.issued2015-03-01en
dc.identifier.citationAn adaptive spatial model for precipitation data from multiple satellites over large regions 2013, 25 (2):389 Statistics and Computingen
dc.identifier.issn0960-3174en
dc.identifier.issn1573-1375en
dc.identifier.doi10.1007/s11222-013-9439-8en
dc.identifier.urihttp://hdl.handle.net/10754/552390en
dc.description.abstractSatellite measurements have of late become an important source of information for climate features such as precipitation due to their near-global coverage. In this article, we look at a precipitation dataset during a 3-hour window over tropical South America that has information from two satellites. We develop a flexible hierarchical model to combine instantaneous rainrate measurements from those satellites while accounting for their potential heterogeneity. Conceptually, we envision an underlying precipitation surface that influences the observed rain as well as absence of it. The surface is specified using a mean function centered at a set of knot locations, to capture the local patterns in the rainrate, combined with a residual Gaussian process to account for global correlation across sites. To improve over the commonly used pre-fixed knot choices, an efficient reversible jump scheme is used to allow the number of such knots as well as the order and support of associated polynomial terms to be chosen adaptively. To facilitate computation over a large region, a reduced rank approximation for the parent Gaussian process is employed.en
dc.publisherSpringer Natureen
dc.relation.urlhttp://link.springer.com/10.1007/s11222-013-9439-8en
dc.rightsThe final publication is available at Springer via http://dx.doi.org/10.1007/s11222-013-9439-8en
dc.subjectLarge data computationen
dc.subjectNonstationary spatial modelen
dc.subjectPrecipitation modelingen
dc.subjectPredictive processen
dc.subjectRandom knotsen
dc.subjectReversible jump Markov chain Monte Carloen
dc.subjectSatellite measurementsen
dc.titleAn adaptive spatial model for precipitation data from multiple satellites over large regionsen
dc.typeArticleen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.identifier.journalStatistics and Computingen
dc.eprint.versionPost-printen
dc.contributor.institutionDepartment of Statistics, Texas A&M University, College Station, TX, 77843-3143, USAen
dc.contributor.institutionSAS Research & Development (India) Pvt. Ltd, Pune, 411013, Indiaen
dc.contributor.institutionDepartment of Atmospheric Sciences, Texas A&M University, College Station, TX, 77843-3150, USAen
kaust.authorGenton, Marc G.en
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.