Non-zero mean Gaussian process prior wind field models

Dan Cornford

Research output: Working paperTechnical report

Abstract

This report outlines the derivation and application of a non-zero mean, polynomial-exponential covariance function based Gaussian process which forms the prior wind field model used in 'autonomous' disambiguation. It is principally used since the non-zero mean permits the computation of realistic local wind vector prior probabilities which are required when applying the scaled-likelihood trick, as the marginals of the full wind field prior. As the full prior is multi-variate normal, these marginals are very simple to compute.
Original languageEnglish
Place of PublicationBirmingham
PublisherAston University
Number of pages16
ISBN (Print)NCRG/98/020
Publication statusPublished - 1998

Fingerprint

Polynomials

Keywords

  • polynomial-exponential covariance function
  • Gaussian process
  • local wind vector
  • multi-variate

Cite this

Cornford, D. (1998). Non-zero mean Gaussian process prior wind field models. Birmingham: Aston University.
Cornford, Dan. / Non-zero mean Gaussian process prior wind field models. Birmingham : Aston University, 1998.
@techreport{d8b7a0daa29349f08978e96e01bf046c,
title = "Non-zero mean Gaussian process prior wind field models",
abstract = "This report outlines the derivation and application of a non-zero mean, polynomial-exponential covariance function based Gaussian process which forms the prior wind field model used in 'autonomous' disambiguation. It is principally used since the non-zero mean permits the computation of realistic local wind vector prior probabilities which are required when applying the scaled-likelihood trick, as the marginals of the full wind field prior. As the full prior is multi-variate normal, these marginals are very simple to compute.",
keywords = "polynomial-exponential covariance function, Gaussian process, local wind vector, multi-variate",
author = "Dan Cornford",
year = "1998",
language = "English",
isbn = "NCRG/98/020",
publisher = "Aston University",
type = "WorkingPaper",
institution = "Aston University",

}

Cornford, D 1998 'Non-zero mean Gaussian process prior wind field models' Aston University, Birmingham.

Non-zero mean Gaussian process prior wind field models. / Cornford, Dan.

Birmingham : Aston University, 1998.

Research output: Working paperTechnical report

TY - UNPB

T1 - Non-zero mean Gaussian process prior wind field models

AU - Cornford, Dan

PY - 1998

Y1 - 1998

N2 - This report outlines the derivation and application of a non-zero mean, polynomial-exponential covariance function based Gaussian process which forms the prior wind field model used in 'autonomous' disambiguation. It is principally used since the non-zero mean permits the computation of realistic local wind vector prior probabilities which are required when applying the scaled-likelihood trick, as the marginals of the full wind field prior. As the full prior is multi-variate normal, these marginals are very simple to compute.

AB - This report outlines the derivation and application of a non-zero mean, polynomial-exponential covariance function based Gaussian process which forms the prior wind field model used in 'autonomous' disambiguation. It is principally used since the non-zero mean permits the computation of realistic local wind vector prior probabilities which are required when applying the scaled-likelihood trick, as the marginals of the full wind field prior. As the full prior is multi-variate normal, these marginals are very simple to compute.

KW - polynomial-exponential covariance function

KW - Gaussian process

KW - local wind vector

KW - multi-variate

M3 - Technical report

SN - NCRG/98/020

BT - Non-zero mean Gaussian process prior wind field models

PB - Aston University

CY - Birmingham

ER -

Cornford D. Non-zero mean Gaussian process prior wind field models. Birmingham: Aston University. 1998.