Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling?

Jasper A. Vrugt, Cajo J F ter Braak, Hoshin Vijai Gupta, Bruce A. Robinson

Research output: Contribution to journalArticle

265 Citations (Scopus)

Abstract

In recent years, a strong debate has emerged in the hydrologic literature regarding what constitutes an appropriate framework for uncertainty estimation. Particularly, there is strong disagreement whether an uncertainty framework should have its roots within a proper statistical (Bayesian) context, or whether such a framework should be based on a different philosophy and implement informal measures and weaker inference to summarize parameter and predictive distributions. In this paper, we compare a formal Bayesian approach using Markov Chain Monte Carlo (MCMC) with generalized likelihood uncertainty estimation (GLUE) for assessing uncertainty in conceptual watershed modeling. Our formal Bayesian approach is implemented using the recently developed differential evolution adaptive metropolis (DREAM) MCMC scheme with a likelihood function that explicitly considers model structural, input and parameter uncertainty. Our results demonstrate that DREAM and GLUE can generate very similar estimates of total streamflow uncertainty. This suggests that formal and informal Bayesian approaches have more common ground than the hydrologic literature and ongoing debate might suggest. The main advantage of formal approaches is, however, that they attempt to disentangle the effect of forcing, parameter and model structural error on total predictive uncertainty. This is key to improving hydrologic theory and to better understand and predict the flow of water through catchments.

Original languageEnglish (US)
Pages (from-to)1011-1026
Number of pages16
JournalStochastic Environmental Research and Risk Assessment
Volume23
Issue number7
DOIs
StatePublished - 2009

Fingerprint

Markov chain
modeling
Markov processes
streamflow
watershed
catchment
Flow of water
metropolis
Uncertainty
Watersheds
Catchments
parameter
water
distribution
effect

ASJC Scopus subject areas

  • Environmental Engineering
  • Environmental Science(all)
  • Environmental Chemistry
  • Water Science and Technology
  • Safety, Risk, Reliability and Quality

Cite this

Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling? / Vrugt, Jasper A.; ter Braak, Cajo J F; Gupta, Hoshin Vijai; Robinson, Bruce A.

In: Stochastic Environmental Research and Risk Assessment, Vol. 23, No. 7, 2009, p. 1011-1026.

Research output: Contribution to journalArticle

@article{6623f813455b4b3697a83ebdb2a2a08f,
title = "Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling?",
abstract = "In recent years, a strong debate has emerged in the hydrologic literature regarding what constitutes an appropriate framework for uncertainty estimation. Particularly, there is strong disagreement whether an uncertainty framework should have its roots within a proper statistical (Bayesian) context, or whether such a framework should be based on a different philosophy and implement informal measures and weaker inference to summarize parameter and predictive distributions. In this paper, we compare a formal Bayesian approach using Markov Chain Monte Carlo (MCMC) with generalized likelihood uncertainty estimation (GLUE) for assessing uncertainty in conceptual watershed modeling. Our formal Bayesian approach is implemented using the recently developed differential evolution adaptive metropolis (DREAM) MCMC scheme with a likelihood function that explicitly considers model structural, input and parameter uncertainty. Our results demonstrate that DREAM and GLUE can generate very similar estimates of total streamflow uncertainty. This suggests that formal and informal Bayesian approaches have more common ground than the hydrologic literature and ongoing debate might suggest. The main advantage of formal approaches is, however, that they attempt to disentangle the effect of forcing, parameter and model structural error on total predictive uncertainty. This is key to improving hydrologic theory and to better understand and predict the flow of water through catchments.",
author = "Vrugt, {Jasper A.} and {ter Braak}, {Cajo J F} and Gupta, {Hoshin Vijai} and Robinson, {Bruce A.}",
year = "2009",
doi = "10.1007/s00477-008-0274-y",
language = "English (US)",
volume = "23",
pages = "1011--1026",
journal = "Stochastic Environmental Research and Risk Assessment",
issn = "1436-3240",
publisher = "Springer New York",
number = "7",

}

TY - JOUR

T1 - Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling?

AU - Vrugt, Jasper A.

AU - ter Braak, Cajo J F

AU - Gupta, Hoshin Vijai

AU - Robinson, Bruce A.

PY - 2009

Y1 - 2009

N2 - In recent years, a strong debate has emerged in the hydrologic literature regarding what constitutes an appropriate framework for uncertainty estimation. Particularly, there is strong disagreement whether an uncertainty framework should have its roots within a proper statistical (Bayesian) context, or whether such a framework should be based on a different philosophy and implement informal measures and weaker inference to summarize parameter and predictive distributions. In this paper, we compare a formal Bayesian approach using Markov Chain Monte Carlo (MCMC) with generalized likelihood uncertainty estimation (GLUE) for assessing uncertainty in conceptual watershed modeling. Our formal Bayesian approach is implemented using the recently developed differential evolution adaptive metropolis (DREAM) MCMC scheme with a likelihood function that explicitly considers model structural, input and parameter uncertainty. Our results demonstrate that DREAM and GLUE can generate very similar estimates of total streamflow uncertainty. This suggests that formal and informal Bayesian approaches have more common ground than the hydrologic literature and ongoing debate might suggest. The main advantage of formal approaches is, however, that they attempt to disentangle the effect of forcing, parameter and model structural error on total predictive uncertainty. This is key to improving hydrologic theory and to better understand and predict the flow of water through catchments.

AB - In recent years, a strong debate has emerged in the hydrologic literature regarding what constitutes an appropriate framework for uncertainty estimation. Particularly, there is strong disagreement whether an uncertainty framework should have its roots within a proper statistical (Bayesian) context, or whether such a framework should be based on a different philosophy and implement informal measures and weaker inference to summarize parameter and predictive distributions. In this paper, we compare a formal Bayesian approach using Markov Chain Monte Carlo (MCMC) with generalized likelihood uncertainty estimation (GLUE) for assessing uncertainty in conceptual watershed modeling. Our formal Bayesian approach is implemented using the recently developed differential evolution adaptive metropolis (DREAM) MCMC scheme with a likelihood function that explicitly considers model structural, input and parameter uncertainty. Our results demonstrate that DREAM and GLUE can generate very similar estimates of total streamflow uncertainty. This suggests that formal and informal Bayesian approaches have more common ground than the hydrologic literature and ongoing debate might suggest. The main advantage of formal approaches is, however, that they attempt to disentangle the effect of forcing, parameter and model structural error on total predictive uncertainty. This is key to improving hydrologic theory and to better understand and predict the flow of water through catchments.

UR - http://www.scopus.com/inward/record.url?scp=70349739462&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=70349739462&partnerID=8YFLogxK

U2 - 10.1007/s00477-008-0274-y

DO - 10.1007/s00477-008-0274-y

M3 - Article

AN - SCOPUS:70349739462

VL - 23

SP - 1011

EP - 1026

JO - Stochastic Environmental Research and Risk Assessment

JF - Stochastic Environmental Research and Risk Assessment

SN - 1436-3240

IS - 7

ER -