Surrogate-Based Stochastic Multiobjective Optimization for Coastal Aquifer Management under Parameter Uncertainty

Abstract

Linked simulation-optimization (S/O) approaches have been extensively used as tools in coastal aquifer management. However, parameter uncertainties in seawater intrusion (SI) simulation models often undermine the reliability of the derived solutions. In this study, a stochastic S/O framework is presented and applied to a real-world case of the Longkou coastal aquifer in China. The three conflicting objectives of maximizing the total pumping rate, minimizing the total injection rate, and minimizing the solute mass increase are considered in the optimization model. The uncertain parameters are contained in both the constraints and the objective functions. A multiple realization approach is utilized to address the uncertainty in the model parameters, and a new multiobjective evolutionary algorithm (EN-NSGA2) is proposed to solve the optimization model. EN-NSGA2 overcomes some inherent limitations in the traditional nondominated sorting genetic algorithm-II (NSGA-II) by introducing information entropy theory. The comparison results indicate that EN-NSGA2 can effectively ameliorate the diversity in Pareto-optimal solutions. For the computational challenge in the stochastic S/O process, a surrogate model based on the multigene genetic programming (MGGP) method is developed to substitute for the numerical simulation model. The results show that the MGGP surrogate model can tremendously reduce the computational burden while ensuring an acceptable level of accuracy.

Determining the Optimal Aquifer Exploitation under Artificial Recharge using the Combination of Numerical Models and Particle Swarm Optimization

“…In this method, which is cost efficient and needs less processing time, the simulator model is approximated to create an interface between the simulation and optimization models, and the approximated model is then used for optimization [25]. This approximation can be performed using various methods [14]: artificial neural networks (ANN) [25,26], fuzzy linear regression [27], regression models [14,28], kernel extreme learning machines (KELM) [29], SVM [30], kriging-KELM-SVM [24], response matrix method [1], and genetic programming (GP) and multigene genetic programming (MGGP) [31]. Owing to the efficient performance of the genetic algorithm (GA) in optimization problems, in this current study, an approach is developed which comprises a simulation model and gene expression programming (GEP) for the simulation-optimization process of aquifer exploitation under artificial recharge.…”

An ensemble-based approach for pumping optimization in an island aquifer considering parameter, observation and climate uncertainty

“…Real-world coastal OUU applications generally used advective-dispersive solute transport models in combination with surrogate models, evolutionary algorithms, and stochastic uncertainty quantification accounting for the uncertainty of a few models parameters (e.g., between 2 and 11 parameters in Sreekanth and Datta, 2014;Rajabi and Ketabchi, 2017;Lal and Datta, 2019;45 Mostafaei-Avandari and Ketabchi, 2020;Han et al, 2021). They were also not systematically preceded by parameter estimation (i.e., automated calibration).…”