On the Construction of Uncertain Time Series Surrogates Using Polynomial Chaos and Gaussian Processes

Pierre Sochala, Mohamed Iskandarani

Research output: Contribution to journalArticle

Abstract

The analysis of time series is a fundamental task in many flow simulations such as oceanic and atmospheric flows. A major challenge is the design of a faithful and accurate time-dependent surrogate built with a tractable sample set and a manageable number of degrees of freedom. Several techniques are implemented to handle the time-dependent aspect of the quantity of interest including uncoupled approaches, low-rank approximations, auto-regressive models and global Bayesian emulators. These approaches rely on two popular methods for uncertainty quantification: polynomial chaos and Gaussian process regression. The different techniques are tested and compared on the uncertain evolution of the sea surface height forecast at two locations exhibiting contrasting levels of variance. Two ensemble sizes are considered as well as two versions of polynomial chaos (ordinary least squares or ridge regression) and Gaussian processes (squared exponential or Matérn covariance function) in order to assess their impact on the results. The conclusions focus on the advantages and the drawbacks, in terms of accuracy, flexibility and computational costs of the different techniques.

Original languageEnglish (US)
JournalMathematical Geosciences
DOIs
StatePublished - Jan 1 2019

Fingerprint

Polynomial Chaos
chaotic dynamics
Gaussian Process
Time series
time series
sea surface height
Low-rank Approximation
Uncertainty Quantification
Ridge Regression
Least Squares Regression
Ordinary Least Squares
Covariance Function
Flow Simulation
Autoregressive Model
Faithful
Forecast
Computational Cost
Ensemble
Regression
Degree of freedom

Keywords

  • Autoregressive model
  • Dynamical models
  • Low-rank decomposition
  • Sea surface height
  • Uncertainty propagation

ASJC Scopus subject areas

  • Mathematics (miscellaneous)
  • Earth and Planetary Sciences(all)

Cite this

@article{cf9f4d0d879b4db4af1e0c1864434558,
title = "On the Construction of Uncertain Time Series Surrogates Using Polynomial Chaos and Gaussian Processes",
abstract = "The analysis of time series is a fundamental task in many flow simulations such as oceanic and atmospheric flows. A major challenge is the design of a faithful and accurate time-dependent surrogate built with a tractable sample set and a manageable number of degrees of freedom. Several techniques are implemented to handle the time-dependent aspect of the quantity of interest including uncoupled approaches, low-rank approximations, auto-regressive models and global Bayesian emulators. These approaches rely on two popular methods for uncertainty quantification: polynomial chaos and Gaussian process regression. The different techniques are tested and compared on the uncertain evolution of the sea surface height forecast at two locations exhibiting contrasting levels of variance. Two ensemble sizes are considered as well as two versions of polynomial chaos (ordinary least squares or ridge regression) and Gaussian processes (squared exponential or Mat{\'e}rn covariance function) in order to assess their impact on the results. The conclusions focus on the advantages and the drawbacks, in terms of accuracy, flexibility and computational costs of the different techniques.",
keywords = "Autoregressive model, Dynamical models, Low-rank decomposition, Sea surface height, Uncertainty propagation",
author = "Pierre Sochala and Mohamed Iskandarani",
year = "2019",
month = "1",
day = "1",
doi = "10.1007/s11004-019-09806-8",
language = "English (US)",
journal = "Mathematical Geosciences",
issn = "1874-8961",
publisher = "Springer Netherlands",

}

TY - JOUR

T1 - On the Construction of Uncertain Time Series Surrogates Using Polynomial Chaos and Gaussian Processes

AU - Sochala, Pierre

AU - Iskandarani, Mohamed

PY - 2019/1/1

Y1 - 2019/1/1

N2 - The analysis of time series is a fundamental task in many flow simulations such as oceanic and atmospheric flows. A major challenge is the design of a faithful and accurate time-dependent surrogate built with a tractable sample set and a manageable number of degrees of freedom. Several techniques are implemented to handle the time-dependent aspect of the quantity of interest including uncoupled approaches, low-rank approximations, auto-regressive models and global Bayesian emulators. These approaches rely on two popular methods for uncertainty quantification: polynomial chaos and Gaussian process regression. The different techniques are tested and compared on the uncertain evolution of the sea surface height forecast at two locations exhibiting contrasting levels of variance. Two ensemble sizes are considered as well as two versions of polynomial chaos (ordinary least squares or ridge regression) and Gaussian processes (squared exponential or Matérn covariance function) in order to assess their impact on the results. The conclusions focus on the advantages and the drawbacks, in terms of accuracy, flexibility and computational costs of the different techniques.

AB - The analysis of time series is a fundamental task in many flow simulations such as oceanic and atmospheric flows. A major challenge is the design of a faithful and accurate time-dependent surrogate built with a tractable sample set and a manageable number of degrees of freedom. Several techniques are implemented to handle the time-dependent aspect of the quantity of interest including uncoupled approaches, low-rank approximations, auto-regressive models and global Bayesian emulators. These approaches rely on two popular methods for uncertainty quantification: polynomial chaos and Gaussian process regression. The different techniques are tested and compared on the uncertain evolution of the sea surface height forecast at two locations exhibiting contrasting levels of variance. Two ensemble sizes are considered as well as two versions of polynomial chaos (ordinary least squares or ridge regression) and Gaussian processes (squared exponential or Matérn covariance function) in order to assess their impact on the results. The conclusions focus on the advantages and the drawbacks, in terms of accuracy, flexibility and computational costs of the different techniques.

KW - Autoregressive model

KW - Dynamical models

KW - Low-rank decomposition

KW - Sea surface height

KW - Uncertainty propagation

UR - http://www.scopus.com/inward/record.url?scp=85066158623&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85066158623&partnerID=8YFLogxK

U2 - 10.1007/s11004-019-09806-8

DO - 10.1007/s11004-019-09806-8

M3 - Article

AN - SCOPUS:85066158623

JO - Mathematical Geosciences

JF - Mathematical Geosciences

SN - 1874-8961

ER -