Maximum likelihood Bayesian averaging of uncertain model predictions

By Shlomo P. Neuman. 2003

447 citations recorded by the source corpus.

Subfields: Environmental Engineering, Ocean Engineering, Water Science and Technology

View Paper: https://www.semanticscholar.org/paper/ac2c792c46d9ad7176c541910796ec27fd66933f

How researchers see this paper

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

In Environmental Engineering

In Ocean Engineering

In Water Science and Technology

Citations in the corpus

Uncertainty in hydrologic modeling: Toward an integrated data assimilation framework (2007, methodology): “In this sense, hydrologic predictions based on a single conceptual model or model structure are invariably subject to statistical bias (if an invalid model is chosen) and underestimation of uncertainty (if equivalent valid models are not included) [Neuman, 2003].”
Maximum likelihood Bayesian averaging of spatial variability models in unsaturated fractured tuff (2003, background): “Our example confirms that the nonasymptotic criterion KIC is more informative than its asymptotic limit BIC, supporting the choice of the former as the basis for MLBMA [Neuman, 2002, 2003].”
Combining multiobjective optimization and Bayesian model averaging to calibrate forecast ensembles of soil hydraulic models (2008, methodology): “…forecasting of surface temperature [Raftery et al., 2005], surface temperature and sea level pressure [Vrugt et al., 2006a], streamflow [e.g., Kuczera et al., 2006; Vrugt and Robinson, 2007b; Ajami et al., 2007], and permeability structures in groundwater hydrology [Neuman, 2003; Ye et al., 2004].”
Modeling Soil Processes: Review, Key Challenges, and New Perspectives (2016, background): “Multimodel ensemble simulations, (e.g., Neuman, 2003; Clark et al., 2008; Wohling et al., 2008; Gupta et al., 2012), such as Bayesian model averaging (BMA) are a promising approach to quantify these uncertainties; BMA reflects conceptual uncertainty through a weighted average of model-wise…”
Estimating epistemic and aleatory uncertainties during hydrologic modeling: An information theoretic approach (2013, methodology): “[55] The three spatially lumped catchment-scale hydrological models used for this case study are HyMod (used earlier in the synthetic study), the Sacramento Soil Moisture Accounting (SAC-SMA) model used by the U.S. National Weather Service for flood forecasting [Burnash et al., 1973; Brazil, 1988], ”
Ensemble predictions of runoff in ungauged catchments (2005, methodology): “The proposed procedure builds upon established Bayesian methods [Beven and Freer, 2001; Neuman, 2003] and preliminary applications of model averaging to the ungauged catchment problem [Young, 2000].”
Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: A data-driven, physics-informed Bayesian approach (2015, methodology): “The iterative ensemble Kalman method tends to underestimate uncertainties in the posterior distributions, a difficulty shared by many other maximum likelihood estimators as well [46].”
Quantification of uncertainty in pedotransfer function‐based parameter estimation for unsaturated flow modeling (2009, methodology): “Pachepsky et al. [2006] suggested that the recently developed method of Bayesian model averaging [Neuman, 2003; Ye et al., 2004, 2005a, 2008] is a promising tool for addressing the PTF model uncertainty.”
Assessment of parametric uncertainty for groundwater reactive transport modeling (2014, methodology): “…uncertainty is caused by propagation of various sources of uncertainty in model structures, parameters, driving forces, and data used in modeling [Neuman, 2003; Wagener and Gupta, 2005; Srinivasan et al., 2007; Meyer et al., 2007; Clark et al., 2011; Refsgaard et al., 2012; Gupta et al., 2012;…”
Ensemble evaluation of hydrological model hypotheses (2010, background): “As a consequence, several different model structures may exist for a given application, each with several different parameter sets, which may yield equally acceptable, yet imperfect, simulations when compared to the data available [Beven and Binley, 1992; Neuman, 2003; Beven, 2006].”
Multi-model ensemble hydrologic prediction using Bayesian model averaging (2007, methodology): “Recently, BMA methods have also been applied to hydrologic applications such as groundwater modeling by Neuman and Wierenga [27,26].”
Towards a comprehensive assessment of model structural adequacy (2012, background): “…and Gorelick, 1996; Hill, 2006; Hunt et al., 2007; Ye et al., 2007; Ye and Khaleel, 2008], and the underlying physics and driving boundary conditions are usually assumed to be correct [National Research Council, 2001; Neuman, 2003; Neuman and Wierenga, 2003; Bredehoeft, 2003, 2005, 2010].”
Variance-based global sensitivity analysis for multiple scenarios and models with implementation using sparse grid collocation (2015, background): “For the hydrological modeling, model uncertainty is often inevitable, because the open and complex hydrologic systems can be conceptually interpreted and mathematically described in multiple ways (Beven, 2002, 2006; Bredehoeft, 2003, 2005; Neuman, 2003).”
Evaluating marginal likelihood with thermodynamic integration method and comparison with several other numerical methods (2016, methodology): “While the Laplace approximation methods have been widely used in groundwater modeling [Neuman, 2003; Ye et al., 2004, 2008, 2010a,b; Lu et al., 2013; Tsai and Elshall, 2013; Elshall and Tsai, 2014; Zhang et al., 2014], it is subjective to truncation error, and linearization of nonlinear models is…”
Advancing data assimilation in operational hydrologic forecasting: progresses, challenges, and emerging opportunities (2012, background): “…et al., 2005; Franssen and Kinzelbach, 2008; Lu et al., 2010; Leisenring and Moradkhani, 2011; Nie et al., 2011) as well as the possibility of model structure identification and uncertainty estimation (e.g., Neuman, 2003; Bulygina and Gupta, 2010; Hsu et al., 2009; Parrish et al., 2012).”