Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models

Marc Mignolet, Pol D. Spanos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The determination of autoregressive (AR) and autoregressive moving average (ARMA) algorithms for simulating realizations of two-dimensional random fields with a specified (target) power spectrum is examined. The form of both of these models is justified first by considering infinite-variate vector processes of appropriate spectral matrix. Next, the AR parameters are selected to achieve the minimum of a positive integral. Then, a technique is formulated to derive an ARMA simulation algorithm from the prior AR approximation by relying on the minimization of frequency domain errors. Finally, these procedures are critically assessed and an example of application is presented.

Original languageEnglish (US)
Title of host publicationAmerican Society of Mechanical Engineers (Paper)
Editors Anon
PublisherPubl by ASME
Pages1-10
Number of pages10
StatePublished - 1991
EventASME Winter Annual Meeting - Atlanta, GA, USA
Duration: Dec 1 1991Dec 6 1991

Other

OtherASME Winter Annual Meeting
CityAtlanta, GA, USA
Period12/1/9112/6/91

Fingerprint

Power spectrum

ASJC Scopus subject areas

  • Mechanical Engineering

Cite this

Mignolet, M., & Spanos, P. D. (1991). Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models. In Anon (Ed.), American Society of Mechanical Engineers (Paper) (pp. 1-10). Publ by ASME.

Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models. / Mignolet, Marc; Spanos, Pol D.

American Society of Mechanical Engineers (Paper). ed. / Anon. Publ by ASME, 1991. p. 1-10.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mignolet, M & Spanos, PD 1991, Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models. in Anon (ed.), American Society of Mechanical Engineers (Paper). Publ by ASME, pp. 1-10, ASME Winter Annual Meeting, Atlanta, GA, USA, 12/1/91.
Mignolet M, Spanos PD. Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models. In Anon, editor, American Society of Mechanical Engineers (Paper). Publ by ASME. 1991. p. 1-10
Mignolet, Marc ; Spanos, Pol D. / Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models. American Society of Mechanical Engineers (Paper). editor / Anon. Publ by ASME, 1991. pp. 1-10
@inproceedings{ca5b7b7981c845e3a6582233d8776759,
title = "Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models",
abstract = "The determination of autoregressive (AR) and autoregressive moving average (ARMA) algorithms for simulating realizations of two-dimensional random fields with a specified (target) power spectrum is examined. The form of both of these models is justified first by considering infinite-variate vector processes of appropriate spectral matrix. Next, the AR parameters are selected to achieve the minimum of a positive integral. Then, a technique is formulated to derive an ARMA simulation algorithm from the prior AR approximation by relying on the minimization of frequency domain errors. Finally, these procedures are critically assessed and an example of application is presented.",
author = "Marc Mignolet and Spanos, {Pol D.}",
year = "1991",
language = "English (US)",
pages = "1--10",
editor = "Anon",
booktitle = "American Society of Mechanical Engineers (Paper)",
publisher = "Publ by ASME",

}

TY - GEN

T1 - Simulation of homogeneous two-dimensional random fields. Part I. AR and ARMA models

AU - Mignolet, Marc

AU - Spanos, Pol D.

PY - 1991

Y1 - 1991

N2 - The determination of autoregressive (AR) and autoregressive moving average (ARMA) algorithms for simulating realizations of two-dimensional random fields with a specified (target) power spectrum is examined. The form of both of these models is justified first by considering infinite-variate vector processes of appropriate spectral matrix. Next, the AR parameters are selected to achieve the minimum of a positive integral. Then, a technique is formulated to derive an ARMA simulation algorithm from the prior AR approximation by relying on the minimization of frequency domain errors. Finally, these procedures are critically assessed and an example of application is presented.

AB - The determination of autoregressive (AR) and autoregressive moving average (ARMA) algorithms for simulating realizations of two-dimensional random fields with a specified (target) power spectrum is examined. The form of both of these models is justified first by considering infinite-variate vector processes of appropriate spectral matrix. Next, the AR parameters are selected to achieve the minimum of a positive integral. Then, a technique is formulated to derive an ARMA simulation algorithm from the prior AR approximation by relying on the minimization of frequency domain errors. Finally, these procedures are critically assessed and an example of application is presented.

UR - http://www.scopus.com/inward/record.url?scp=0026376831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026376831&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026376831

SP - 1

EP - 10

BT - American Society of Mechanical Engineers (Paper)

A2 - Anon, null

PB - Publ by ASME

ER -