Swarm intelligence machine-learning-assisted progressive global optimization of DNAPL-contaminated aquifer remediation strategy

Abstract

Abstract Remediation projects of DNAPL-contaminated groundwater generally face difficulties of low contaminant removal rate and high remediation cost. Hence, a machine-learning-assisted mixed-integer multi-objective optimization technique was presented for efficiently programming remediation strategies. A swarm intelligence multi-kernel extreme learning machine (SI-MKELM) was proposed to build a reliable intelligent surrogate model of the multiphase flow numerical simulation model for reducing the computational cost of repetitive CPU-demanding remediation efficiency evaluations, and a hyper-heuristic homotopy algorithm was developed for progressively searching the global optimum of the remediation strategy. The results showed that: (1) The multi-kernel extreme learning machine improved by swarm intelligence algorithm significantly improved the approximation accuracy to the numerical model, and the mean residual and mean relative error were only 0.7596% and 1.0185%, respectively. (2) It only took 0.1 s to run the SI-MKELM. Replacing the numerical model with SI-MKELM considerably reduced the computational burden of the simulation–optimization process and maintained high computational accuracy for optimizing the DNAPL-contaminated aquifer remediation strategy. (3) The hyper-heuristic homotopy algorithm was capable of progressively searching the global optimum, and avoiding premature convergence in the optimization process. It effectively improved the searching ability of the traditional heuristic algorithms.