Optimizing surfactant-enhanced aquifer remediation based on Gaussian process surrogate model in DNAPL-contaminated sites considering different wells patterns

Abstract

Surfactant-enhanced aquifer remediation (SEAR) is an appropriate method for Dense non-aqueous phase liquids (DNAPLs) remediation. However, due to the high cost of chemicals used, choosing the suitable wells pattern and the optimal pumping scenario is necessary. In this study, the SEAR method performance for Regular (convergent) and Inverted (divergent) patterns with different wells numbers have been evaluated. The performance of 5 categories of patterns, including 35 different sub-patterns, was evaluated in a PCE-contaminated aquifer. The results show that the uniformity and appropriate surfactant distribution in the contaminated area significantly improves remediation performance. The distribution of surfactants in Regular patterns was better than Inverted patterns, and Regular patterns had lower remediation duration and cost. The best patterns that achieved a 95 % removal rate at the lowest cost were Regular. To find the optimal pumping scenario, a simulation-optimization model based on the Gaussian process regressor (GPR), as a surrogate model, has been used to reduce the optimization model's computational burden. Nine different kernels were applied and evaluated to find the best GPR. Also, the Bayesian hyperparameter optimization (BHO) method was used to optimize the surrogate model, and its performance was compared with the conventional grid search method. The results showed that the use of the Chi2 kernel and the BHO method are the best choices. A BHO-optimized multi-kernel Gaussian process (BHOMK-GP) model has also been developed, and its performance has been compared with single-kernel GPR surrogate models. The BHOMK-GP model's accuracy was significantly higher than single-kernel GPR models. The test and cross-validation RMSE of the BHOMK-GP model were 0.0385 and 0.0435, respectively. Finally, the optimal remediation scenario has been obtained by substituting the BHOMK-GP model as a surrogate model instead of the SEAR simulation model. The cost of remediation in the optimal strategy was $ 77,575.