A Markov Chain Monte Carlo Scheme for parameter estimation and inference in conceptual rainfall‐runoff modeling

By B. Bates, E. Campbell. 2001

369 citations recorded by the source corpus.

Subfields: Global and Planetary Change, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/f41bb88b93dedc1d09d04a5a1fc9c46546d86c35

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

A formal likelihood function for parameter and predictive inference of hydrologic models with correlated, heteroscedastic, and non‐Gaussian errors (2010, methodology): “ Bates and Campbell [2001] AR(p) Homoscedastic after Box‐Cox transformation Gaussian after Box‐Cox transformation b =0”
Estimating epistemic and aleatory uncertainties during hydrologic modeling: An information theoretic approach (2013, background): “Recently, formal Bayesian approaches have been proposed for the quantification of model uncertainty [Bates and Campbell, 2001; Thiemann et al., 2001; Kaheil et al., 2006], and, particularly, for the explicit integration of multiple sources of uncertainty [Kavetski et al., 2006a, 2006b; Ajami et…”
Corruption of accuracy and efficiency of Markov chain Monte Carlo simulation by inaccurate numerical implementation of conceptual hydrologic models (2010, background): “These algorithms are especially useful for the parameter inference of nonlinear hydrologic models, for which analytical expressions of the posterior parameter distributions are not available [Kuczera and Parent, 1998; Bates and Campbell, 2001; Vrugt et al., 2003; Engeland et al., 2005; Smith and Mar”
Ancient numerical daemons of conceptual hydrological modeling: 2. Impact of time stepping schemes on model analysis and prediction (2010, methodology): “MCMC methodsofferconsiderableflexibilityinadaptingtotheshape of the distribution they are applied to and, provided care is taken to monitor their convergence, can approximate probability distributions that are intractable using alternative approaches (e.g., see Gelman et al. [2003] for further theor”
Treatment of input uncertainty in hydrologic modeling: Doing hydrology backward with Markov chain Monte Carlo simulation (2008, background): “4. Bayesian Statistics and Markov Chain Monte Carlo Simulation [17] In the last decade, Bayesian statistics have increasingly found use in the field of hydrology for statistical inference of parameters, state variables, and model output prediction [Kuczera and Parent, 1998; Bates and Campbell, 2001”
Equifinality of formal (DREAM) and informal (GLUE) Bayesian approaches in hydrologic modeling? (2009, background): “…is admirably suited for systematically addressing and quantifying the various error sources within a single cohesive, integrated, and hierarchical manner (Kuczera and Parent 1998; Bates and Campbell 2001; Engeland and Gottschalk 2002; Vrugt et al. 2003; Marshall et al. 2004; Liu and Gupta 2007).”
Beyond gradual warming: extreme weather events alter flower phenology of European grassland and heath species (2009, methodology): “The significance of differences between weather manipulation and control were evaluated using Markov Chain Monte Carlo sampling with the level of significance set to Po0.05 in 1000 iterations ( Bates & Campbell, 2001 ).”
Quantifying hydrological modeling errors through a mixture of normal distributions (2007, methodology): “(1996), for the Metropolis–Hastings algorithm refer to Chib and Greenberg (1995) and for its application in conceptual hydrological modeling for example to Kuczera and Parent (1998), Bates and Campbell (2001) or Marshall et al.”
Role of the calibration process in reducing model predictive error (2005, methodology): “... are calculated as the inverse of their ‘‘uncertainty.’’ Though acknowledgment is often given to the fact that measurement noise is overshadowed by structural noise, the latter is mostly assumed to exhibit no spatial or temporal correlation or (in the case of hydrologic models) to possess a corre”
Hydrological modelling of the Chaohe Basin in China: Statistical model formulation and Bayesian inference (2007, methodology): “These errors, together with the measurement errors of response, can be accounted for by an overall additive autoregressive error model (e.g. Kuczera 1983, Bates and Campbell, 2001) or by considering the error sources separately and propagating them through the model.”
Comparing uncertainty analysis techniques for a SWAT application to the Chaohe Basin in China (2008, methodology): “…1 k1 k1 6¼ 0 lnðy þ k2Þ k1 ¼ 0 ( ; g 1ðzÞ ¼ ðk1zþ 1Þ 1=k1 k2 k1 6¼ 0 expðzÞ k2 k1 ¼ 0 ( ; dg dy ¼ ðy þ k2Þk1 1 ð12Þ This model extends earlier works with discrete-time autoregressive error models in hydrological applications (e.g., Kuczera, 1983; Duan et al., 1988; Bates and Campbell, 2001).”
Bayesian calibration of a large‐scale geothermal reservoir model by a new adaptive delayed acceptance Metropolis Hastings algorithm (2011, methodology): “…conditioning a permeability field by pressure data [Oliver et al., 1997], calibrating conceptual rainfallrunoff models [Kuczera and Parent, 1998; Bates and Campbell, 2001; Renard et al., 2010; Schoups et al., 2010], estimating the permeability distribution for a two phase flow model [Efendiev…”
Uncertainty and sensitivity assessments of an agricultural–hydrological model (RZWQM2) using the GLUE method (2016, background): “The denseness of the initial parameter sampling space plays an important role in whether the GLUE sampling scheme ensures sufficient statistical precision (Bates and Campbell, 2001).”
Comparison of joint versus postprocessor approaches for hydrological uncertainty estimation accounting for error autocorrelation and heteroscedasticity (2014, methodology): “For example, heteroscedasticity is often taken into account by transforming observed and predicted streamflows using logarithmic or Box-Cox transformations before applying constant-variance statistical error models [e.g., Kuczera, 1983; Bates and Campbell, 2001; Morawietz et al., 2011].”