Surrogate Model Application to the Identification of an Optimal Surfactant-Enhanced Aquifer Remediation Strategy for DNAPL-Contaminated Sites  

作　　者：罗建男 卢文喜 辛欣 初海波 

机构地区：[1]Key Laboratory of Groundwater Resources and Environment,Ministry of Education,Jilin University [2]College of Environment and Resources,Jilin University

出　　处：《Journal of Earth Science》2013年第6期1023-1032,共10页地球科学学刊（英文版）

基　　金：supported by the National Nature Science Foundation of China(No.41072171);China Geological Survey Project(No.1212011140027)

摘　　要：A surrogate model is introduced for identifying the optimal remediation strategy for Dense Non-Aqueous Phase Liquids （DNAPL）-contaminated aquifers. A Latin hypercube sampling （LHS） method was used to collect data in the feasible region for input variables. A surrogate model of the multi-phase flow simulation model was developed using a radial basis function artificial neural network （RBFANN）. The developed model was applied to a perchloroethylene （PCE）-contaminated aquifer remediation optimization problem. The relative errors of the average PCE removal rates be- tween the surrogate model and simulation model for 10 validation samples were lower than 5%, which is high approximation accuracy. A comparison of the surrogate-based simulation optimization model and a conventional simulation optimization model indicated that RBFANN surrogate model developed in this paper considerably reduced the computational burden of simulation optimization processes.A surrogate model is introduced for identifying the optimal remediation strategy for Dense Non-Aqueous Phase Liquids （DNAPL）-contaminated aquifers. A Latin hypercube sampling （LHS） method was used to collect data in the feasible region for input variables. A surrogate model of the multi-phase flow simulation model was developed using a radial basis function artificial neural network （RBFANN）. The developed model was applied to a perchloroethylene （PCE）-contaminated aquifer remediation optimization problem. The relative errors of the average PCE removal rates be- tween the surrogate model and simulation model for 10 validation samples were lower than 5%, which is high approximation accuracy. A comparison of the surrogate-based simulation optimization model and a conventional simulation optimization model indicated that RBFANN surrogate model developed in this paper considerably reduced the computational burden of simulation optimization processes.

关 键 词：DNAPL Latin hypercube sampling radial basis function artificial neural network si-mulation optimization surrogate model. 

分 类 号：O631.3[理学—高分子化学]