A game-theoretic parameter configuration technique for aquifer restoration design

Eheart, J. Wayland; Rahman, M.Rezaur; Keith, Stevan M.; Valocchi, Albert J.

doi:10.1016/0169-7722(90)90017-b

Cited by 2 publications

(2 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to reduce the overall computational time, some researchers [ Eheart et al , 1990; Ranjithan et al , 1993; Mantoglou and Kourakos , 2005, 2007; Bayer et al , 2008] suggested that in certain classes of problems, only a few realizations out of the generated set of N realizations are significant at a particular reliability level r . These are the ones ranking between the m = nint( rN ) and the last N rank and are named “critical realizations.” Whether a realization is critical depends on several factors such as the problem characteristics, reliability level, characteristics of each realization, objective function, etc.…”

Section: Critical Realizations In Stochastic System Optimizationmentioning

confidence: 99%

“…However, in some problems, depending on the required reliability level, only a few realizations seem to have an important impact on the final outcome. These realizations are called “critical realizations.” An attempt was made by Eheart et al [1990], to determine which distributions of hydraulic conductivity values, constitute critical realizations. Ranjithan et al [1993] developed a neural network screening tool to identify the critical realizations.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Remediation of heterogeneous aquifers based on multiobjective optimization and adaptive determination of critical realizations

Kourakos

Mantoglou

2008

Water Resources Research

View full text Add to dashboard Cite

1] A method for optimal remediation of heterogeneous aquifers based on stochastic simulation with adaptive determination of critical realizations is developed. Multiple hydraulic conductivity realizations are generated using the turning bands method while Monte Carlo simulation is incorporated into a multiobjective genetic optimization algorithm. In order to reduce the computational burden of Monte Carlo simulations, an adaptive procedure is developed for identifying ''critical realizations'' which are the ones that have an effect on the optimal solution depending on desired reliability level. The adaptive procedure is embedded into the genetic optimization algorithm where noncritical realizations are eliminated step by step during the advancement of optimization. When the number of remaining realizations reaches a minimum, some new realizations are added. The specific realizations which are removed or added in the critical set are selected by an automatic procedure controlled by a similarity criterion based on rankings of realizations. This is a significant improvement over the nonadaptive methodology for identification of critical realizations and does not require using a number of initial designs and a safety threshold. The methodology is applied in a remediation problem with two objectives (reduction of contaminant mass and cleanup cost). The applications indicate significant savings in computer time without loss of performance.Citation: Kourakos, G., and A. Mantoglou (2008), Remediation of heterogeneous aquifers based on multiobjective optimization and adaptive determination of critical realizations, Water Resour. Res., 44, W12408,

show abstract

Section: Critical Realizations In Stochastic System Optimizationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Remediation of heterogeneous aquifers based on multiobjective optimization and adaptive determination of critical realizations

Kourakos

Mantoglou

2008

Water Resources Research

View full text Add to dashboard Cite

show abstract

Neural network‐based screening for groundwater reclamation under uncertainty

Ranjithan¹,

Eheart²,

Garrett³

1993

Water Resources Research

181

View full text Add to dashboard Cite

Uncertainty due to spatial variability of hydraulic conductivity is an important issue in the design of reliable groundwater remediation strategies. Using groundwater management models based on a stochastic approach to groundwater flow, where the log‐hydraulic conductivity is represented as a random field, is a frequently studied technique for the design of aquifer remediation in the presence of uncertainty. Such an approach employs the solution of a management model for a large set of equally probable realizations of the hydraulic conductivity. However, only a few out of the large set of realizations are critical to the final outcome of the design. The spatial distribution of the hydraulic conductivity values in a realization, and the degree of variation of the hydraulic conductivity values within a realization are identified as two important features that determine the level of criticalness of a realization. The association between the hydraulic conductivity pattern and the level of criticalness is not known explicitly and needs to be captured for efficient screening. The screening approach presented here utilizes the pattern classification capability of a neural network and its ability to learn from examples. It is shown that incorporation of only a few critical realizations in a groundwater management model can yield highly reliable remediation designs. The application of the screening tool in a pump‐and‐treat design problem is illustrated via two examples.

show abstract

A game-theoretic parameter configuration technique for aquifer restoration design

Cited by 2 publications

References 9 publications

Remediation of heterogeneous aquifers based on multiobjective optimization and adaptive determination of critical realizations

Remediation of heterogeneous aquifers based on multiobjective optimization and adaptive determination of critical realizations

Neural network‐based screening for groundwater reclamation under uncertainty

Contact Info

Product

Resources

About