Bayesian modeling for physical processes in industrial hygiene using misaligned workplace data

João V D Monteiro, Sudipto Banerjee, Gurumurthy Ramachandran

Research output: Contribution to journalArticle

Abstract

In industrial hygiene, a workers exposure to chemical, physical, and biological agents is increasingly being modeled using deterministic physical models that study exposures near and farther away from a contaminant source. However, predicting exposure in the workplace is challenging and simply regressing on a physical model may prove ineffective due to biases and extraneous variability. A further complication is that data from the workplace are usually misaligned. This means that not all timepoints measure concentrations near and far from the source. We recognize these challenges and outline a flexible Bayesian hierarchical framework to synthesize the physical model with the field data. We reckon that the physical model, by itself, is inadequate for enhanced inferential and predictive performance and deploy (multivariate) Gaussian processes to capture uncertainties and associations. We propose rich covariance structures for multiple outcomes using latent stochastic processes. This article has supplementary material available online.

Original languageEnglish (US)
Pages (from-to)238-247
Number of pages10
JournalTechnometrics
Volume56
Issue number2
DOIs
StatePublished - Apr 3 2014
Externally publishedYes

Fingerprint

Industrial hygiene
Bayesian Modeling
Physical process
Physical Model
Multiple Outcomes
Latent Process
Covariance Structure
Deterministic Model
Complications
Random processes
Gaussian Process
Stochastic Processes
Impurities
Uncertainty

Keywords

  • Bayesian melding
  • Cross-covariances
  • Gaussian processes
  • Linear ordinary differential equations
  • Markov chain Monte Carlo
  • Occupational exposure models

ASJC Scopus subject areas

  • Modeling and Simulation
  • Statistics and Probability
  • Applied Mathematics

Cite this

Bayesian modeling for physical processes in industrial hygiene using misaligned workplace data. / Monteiro, João V D; Banerjee, Sudipto; Ramachandran, Gurumurthy.

In: Technometrics, Vol. 56, No. 2, 03.04.2014, p. 238-247.

Research output: Contribution to journalArticle

@article{79bae5101d874831859c646bcd33465a,
title = "Bayesian modeling for physical processes in industrial hygiene using misaligned workplace data",
abstract = "In industrial hygiene, a workers exposure to chemical, physical, and biological agents is increasingly being modeled using deterministic physical models that study exposures near and farther away from a contaminant source. However, predicting exposure in the workplace is challenging and simply regressing on a physical model may prove ineffective due to biases and extraneous variability. A further complication is that data from the workplace are usually misaligned. This means that not all timepoints measure concentrations near and far from the source. We recognize these challenges and outline a flexible Bayesian hierarchical framework to synthesize the physical model with the field data. We reckon that the physical model, by itself, is inadequate for enhanced inferential and predictive performance and deploy (multivariate) Gaussian processes to capture uncertainties and associations. We propose rich covariance structures for multiple outcomes using latent stochastic processes. This article has supplementary material available online.",
keywords = "Bayesian melding, Cross-covariances, Gaussian processes, Linear ordinary differential equations, Markov chain Monte Carlo, Occupational exposure models",
author = "Monteiro, {Jo{\~a}o V D} and Sudipto Banerjee and Gurumurthy Ramachandran",
year = "2014",
month = "4",
day = "3",
doi = "10.1080/00401706.2013.836988",
language = "English (US)",
volume = "56",
pages = "238--247",
journal = "Technometrics",
issn = "0040-1706",
publisher = "American Statistical Association",
number = "2",

}

TY - JOUR

T1 - Bayesian modeling for physical processes in industrial hygiene using misaligned workplace data

AU - Monteiro, João V D

AU - Banerjee, Sudipto

AU - Ramachandran, Gurumurthy

PY - 2014/4/3

Y1 - 2014/4/3

N2 - In industrial hygiene, a workers exposure to chemical, physical, and biological agents is increasingly being modeled using deterministic physical models that study exposures near and farther away from a contaminant source. However, predicting exposure in the workplace is challenging and simply regressing on a physical model may prove ineffective due to biases and extraneous variability. A further complication is that data from the workplace are usually misaligned. This means that not all timepoints measure concentrations near and far from the source. We recognize these challenges and outline a flexible Bayesian hierarchical framework to synthesize the physical model with the field data. We reckon that the physical model, by itself, is inadequate for enhanced inferential and predictive performance and deploy (multivariate) Gaussian processes to capture uncertainties and associations. We propose rich covariance structures for multiple outcomes using latent stochastic processes. This article has supplementary material available online.

AB - In industrial hygiene, a workers exposure to chemical, physical, and biological agents is increasingly being modeled using deterministic physical models that study exposures near and farther away from a contaminant source. However, predicting exposure in the workplace is challenging and simply regressing on a physical model may prove ineffective due to biases and extraneous variability. A further complication is that data from the workplace are usually misaligned. This means that not all timepoints measure concentrations near and far from the source. We recognize these challenges and outline a flexible Bayesian hierarchical framework to synthesize the physical model with the field data. We reckon that the physical model, by itself, is inadequate for enhanced inferential and predictive performance and deploy (multivariate) Gaussian processes to capture uncertainties and associations. We propose rich covariance structures for multiple outcomes using latent stochastic processes. This article has supplementary material available online.

KW - Bayesian melding

KW - Cross-covariances

KW - Gaussian processes

KW - Linear ordinary differential equations

KW - Markov chain Monte Carlo

KW - Occupational exposure models

UR - http://www.scopus.com/inward/record.url?scp=84900837735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900837735&partnerID=8YFLogxK

U2 - 10.1080/00401706.2013.836988

DO - 10.1080/00401706.2013.836988

M3 - Article

AN - SCOPUS:84900837735

VL - 56

SP - 238

EP - 247

JO - Technometrics

JF - Technometrics

SN - 0040-1706

IS - 2

ER -