Optimizing groundwater remediation designs under uncertainty using dynamic surrogate models

Keyphrases

• Monte Carlo Simulation 100%
• Groundwater Remediation 100%
• Remediation Design 100%
• Dynamic Surrogate Model 100%
• Design Uncertainty 100%
• Genetic Algorithm 66%
• Computational Cost 33%
• Computational Effort 33%
• Modeling Approach 33%
• Computational Efficiency 33%
• Hypothesis Testing 33%
• Numerical Model 33%
• Under Uncertainty 33%
• Optimization Problem 33%
• Simulation Model 33%
• Performance Prediction 33%
• Multiple Parameters 33%
• Design Case Study 33%
• Uncertainty Sources 33%
• Optimization Framework 33%
• Aquifer 33%
• Function Distribution 33%
• Hydraulic Conductivity 33%
• Genetic Algorithm Optimization 33%
• Reliable Solution 33%
• Objective Function Value 33%
• Surrogate Model 33%
• Cost-effective Solution 33%
• Water Resources Optimization 33%
• Latin Hypercube Sampling 33%
• Noisy Genetic Algorithms 33%

Engineering

• Genetic Algorithm 100%
• Surrogate Model 100%
• Objective Function 66%
• Realization 33%
• Computational Effort 33%
• Simulation Result 33%
• Computational Cost 33%
• Computational Efficiency 33%
• Hydraulics 33%
• Numerical Model 33%
• Optimisation Problem 33%
• Hypothesis Test 33%
• Water Resources 33%
• Effective Solution 33%
• Prediction Performance 33%
• Latin-Hypercube Sampling 33%

Earth and Planetary Sciences

• Genetic Algorithm 100%
• Groundwater Remediation 100%
• Distribution Function 33%
• Water Resource 33%
• Numerical Model 33%
• Hydraulic Conductivity 33%