Modelling frontal discontinuities in wind fields

Dan Cornford, Ian T. Nabney, Christopher K. I. Williams

Research output: Contribution to journalArticle

Abstract

A Bayesian procedure for the retrieval of wind vectors over the ocean using satellite borne scatterometers requires realistic prior near-surface wind field models over the oceans. We have implemented carefully chosen vector Gaussian Process models; however in some cases these models are too smooth to reproduce real atmospheric features, such as fronts. At the scale of the scatterometer observations, fronts appear as discontinuities in wind direction. Due to the nature of the retrieval problem a simple discontinuity model is not feasible, and hence we have developed a constrained discontinuity vector Gaussian Process model which ensures realistic fronts. We describe the generative model and show how to compute the data likelihood given the model. We show the results of inference using the model with Markov Chain Monte Carlo methods on both synthetic and real data.
Original languageEnglish
Pages (from-to)43-58
Number of pages16
JournalJournal of Nonparametric Statistics
Volume14
Issue number1-2
DOIs
Publication statusPublished - 2002

Fingerprint

Discontinuity
Modeling
Gaussian Model
Gaussian Process
Ocean
Process Model
Retrieval
Generative Models
Model
Markov Chain Monte Carlo Methods
Likelihood
Process model
Gaussian process

Bibliographical note

This is an electronic version of an article published in Cornford, Dan; Nabney, Ian T. and Williams, Christopher K. I. (2002). Modelling frontal discontinuities in wind fields. Journal of Nonparametric Statistics, 14 (1-2), pp. 43-58. Journal of Nonparametric Statistics is available online at: http://www.informaworld.com/openurl?genre=article&issn=1048-5252&volume=14&issue=1-2&spage=43

Keywords

  • Gaussian processes
  • Discontinuities
  • Wind fields
  • Fronts

Cite this

Cornford, Dan ; Nabney, Ian T. ; Williams, Christopher K. I. / Modelling frontal discontinuities in wind fields. In: Journal of Nonparametric Statistics. 2002 ; Vol. 14, No. 1-2. pp. 43-58.
@article{257bcdf81d1c44cea6adeed59b767998,
title = "Modelling frontal discontinuities in wind fields",
abstract = "A Bayesian procedure for the retrieval of wind vectors over the ocean using satellite borne scatterometers requires realistic prior near-surface wind field models over the oceans. We have implemented carefully chosen vector Gaussian Process models; however in some cases these models are too smooth to reproduce real atmospheric features, such as fronts. At the scale of the scatterometer observations, fronts appear as discontinuities in wind direction. Due to the nature of the retrieval problem a simple discontinuity model is not feasible, and hence we have developed a constrained discontinuity vector Gaussian Process model which ensures realistic fronts. We describe the generative model and show how to compute the data likelihood given the model. We show the results of inference using the model with Markov Chain Monte Carlo methods on both synthetic and real data.",
keywords = "Gaussian processes, Discontinuities, Wind fields, Fronts",
author = "Dan Cornford and Nabney, {Ian T.} and Williams, {Christopher K. I.}",
note = "This is an electronic version of an article published in Cornford, Dan; Nabney, Ian T. and Williams, Christopher K. I. (2002). Modelling frontal discontinuities in wind fields. Journal of Nonparametric Statistics, 14 (1-2), pp. 43-58. Journal of Nonparametric Statistics is available online at: http://www.informaworld.com/openurl?genre=article&issn=1048-5252&volume=14&issue=1-2&spage=43",
year = "2002",
doi = "10.1080/10485250211392",
language = "English",
volume = "14",
pages = "43--58",
journal = "Journal of Nonparametric Statistics",
issn = "1048-5252",
publisher = "Taylor & Francis",
number = "1-2",

}

Cornford, D, Nabney, IT & Williams, CKI 2002, 'Modelling frontal discontinuities in wind fields', Journal of Nonparametric Statistics, vol. 14, no. 1-2, pp. 43-58. https://doi.org/10.1080/10485250211392

Modelling frontal discontinuities in wind fields. / Cornford, Dan; Nabney, Ian T.; Williams, Christopher K. I.

In: Journal of Nonparametric Statistics, Vol. 14, No. 1-2, 2002, p. 43-58.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Modelling frontal discontinuities in wind fields

AU - Cornford, Dan

AU - Nabney, Ian T.

AU - Williams, Christopher K. I.

N1 - This is an electronic version of an article published in Cornford, Dan; Nabney, Ian T. and Williams, Christopher K. I. (2002). Modelling frontal discontinuities in wind fields. Journal of Nonparametric Statistics, 14 (1-2), pp. 43-58. Journal of Nonparametric Statistics is available online at: http://www.informaworld.com/openurl?genre=article&issn=1048-5252&volume=14&issue=1-2&spage=43

PY - 2002

Y1 - 2002

N2 - A Bayesian procedure for the retrieval of wind vectors over the ocean using satellite borne scatterometers requires realistic prior near-surface wind field models over the oceans. We have implemented carefully chosen vector Gaussian Process models; however in some cases these models are too smooth to reproduce real atmospheric features, such as fronts. At the scale of the scatterometer observations, fronts appear as discontinuities in wind direction. Due to the nature of the retrieval problem a simple discontinuity model is not feasible, and hence we have developed a constrained discontinuity vector Gaussian Process model which ensures realistic fronts. We describe the generative model and show how to compute the data likelihood given the model. We show the results of inference using the model with Markov Chain Monte Carlo methods on both synthetic and real data.

AB - A Bayesian procedure for the retrieval of wind vectors over the ocean using satellite borne scatterometers requires realistic prior near-surface wind field models over the oceans. We have implemented carefully chosen vector Gaussian Process models; however in some cases these models are too smooth to reproduce real atmospheric features, such as fronts. At the scale of the scatterometer observations, fronts appear as discontinuities in wind direction. Due to the nature of the retrieval problem a simple discontinuity model is not feasible, and hence we have developed a constrained discontinuity vector Gaussian Process model which ensures realistic fronts. We describe the generative model and show how to compute the data likelihood given the model. We show the results of inference using the model with Markov Chain Monte Carlo methods on both synthetic and real data.

KW - Gaussian processes

KW - Discontinuities

KW - Wind fields

KW - Fronts

UR - http://www.scopus.com/inward/record.url?scp=0036556090&partnerID=8YFLogxK

UR - http://www.informaworld.com/openurl?genre=article&issn=1048-5252&volume=14&issue=1-2&spage=43

U2 - 10.1080/10485250211392

DO - 10.1080/10485250211392

M3 - Article

VL - 14

SP - 43

EP - 58

JO - Journal of Nonparametric Statistics

JF - Journal of Nonparametric Statistics

SN - 1048-5252

IS - 1-2

ER -