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

By Jasper A. Vrugt, C. T. ter Braak, Hoshin V. Gupta, Bruce A. Robinson. 2009

497 citations recorded by the source corpus.

Subfields: Global and Planetary Change, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/2c5cc4d467ed7b73c2463844be621c79388c44c0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Global and Planetary Change

In Water Science and Technology

Citations in the corpus

On the colour and spin of epistemic error (and what we might do about it) (2011, background): “In hydrological modelling this would be the case when a rainfall input is so poorly represented by a set of raingauges that there is no way that a model could conceivably provide a good estimate of the resulting discharge (see the example in Beven, 2009a).”
A formal likelihood function for parameter and predictive inference of hydrologic models with correlated, heteroscedastic, and non‐Gaussian errors (2010, methodology): “DREAM‐ZS is based on the original DREAM algorithm [Vrugt et al., 2009] but uses sampling from an archive of past states to generate candidate points in each individual chain.”
What Role Does Hydrological Science Play in the Age of Machine Learning? (2020, background): “There has been an enormous amount of attention paid to this topic in the hydrological sciences (e.g., Beven, 2006a, 2009, 2016; Beven & Binley, 2014; Beven et al., 2007, 2008, 2011, 2012; Clark et al., 2011; Kumar, 2011; Mantovan & Todini, 2006; Montanari, 2007; Montanari & Koutsoyiannis, 2012; Near”
Markov chain Monte Carlo simulation using the DREAM software package: Theory, concepts, and MATLAB implementation (2016, methodology): “…et al. (2001) 12 † Gaussian likelihood: homos/heteroscedastic data error Equation (6) 13 ‡ Gaussian likelihood: with AR-1 model of error residuals Vrugt et al. (2009) 14 § Generalized likelihood function Schoups and Vrugt (2010a) 15 Whittle’s likelihood (spectral analysis) Whittle (1953)…”
Characterising performance of environmental models (2013, methodology): “While this is often a useful measure of model performance, related methods have already been reviewed elsewhere (e.g., Beven, 2008; Keesman et al., 2011; Vrugt et al., 2009).”
Development of a formal likelihood function for improved Bayesian inference of ephemeral catchments (2010, methodology): “[6] Despite this criticism, the use of Bayesian methods has become increasingly common [e.g., Kuczera and Parent, 1998; Marshall et al., 2004; Samanta et al., 2007; Smith and Marshall, 2008, 2010; Vrugt et al., 2009].”
GLUE: 20 years on (2014, methodology): “The inverse of this problem is seen in some recent studies that try to identify input errors as part of a Bayesian identification methodology (e.g. the BATEA studies of Thyer et al., 2009 and the DREAM studies of Vrugt et al., 2009b but see also Beven, 2009b, in respect of the latter).”
Bridging the gap between GLUE and formal statistical approaches: approximate Bayesian computation (2013, background): “Recent developments include simple randomized adaptation (Mazi et al., 2004; Tol-son and Shoemaker, 2007), multimethod ensemble (Vrugt and Robinson, 2007; Vrugt et al., 2009b), and ﬁltering based (Pauwels, 2008) parameter estimation methods that further improve search efﬁciency and reliability.”
Toward diagnostic model calibration and evaluation: Approximate Bayesian computation (2013, methodology): “The value of ̂ can be specified a priori based on knowledge of the measurements errors, or alternatively its value can be inferred simultaneously with the values of [Vrugt et al., 2008b; Laloy and Vrugt, 2012].”
Evaluation of the subjective factors of the GLUE method and comparison with the formal Bayesian method in uncertainty assessment of hydrological models (2010, unknown): “respect to their philosophies and the mathematical rigor they rely on (Gupta et al., 2003; Beven, 2006; Mantovan and Todini, 2006; Todini, 2007; Beven et al., 2008; Yang et al., 2008; Vrugt et al., 2009; Jin et al., 2010).”
Parameter and modeling uncertainty simulated by GLUE and a formal Bayesian method for a conceptual hydrological model (2010, methodology): “…approaches attempt to disentangle the effect of input, output, parameter and model structural error which, on one hand, are important to improve our hydrologic theory of how water flows through watersheds; on the other hand these attempts make statistical inference difficult (Vrugt et al., 2008).”