Identifying the release history of a groundwater contaminant source based on an ensemble surrogate model

Abstract In identifying groundwater contaminant sources, given that the simulation model is computationally inefficient, an ensemble surrogate model is proposed to improve the accuracy and robustness of results. The proposed ensemble surrogate model in this paper consists of the following three individual surrogate models: Kriging, radial basis functions and least squares support vector machines. The Adaptive Metropolis-Markov Chain Monte Carlo method is used to assign weights to the three models. Accuracy and robustness of the ensemble surrogate model were tested on not only conservative contaminants but also contaminants containing chemical reaction. The results indicated that the proposed ensemble surrogate model is an effective method to solve the inverse contaminant source identification problems with a high degree of accuracy and short computation time.

[1]  Bithin Datta,et al.  Optimal Identification of Ground-Water Pollution Sources and Parameter Estimation , 2001 .

[2]  M. Rais-Rohani,et al.  Ensemble of metamodels with optimized weight factors , 2008 .

[3]  C. J. Stone,et al.  Discussion: Multivariate Adaptive Regression Splines , 1991 .

[4]  T. Simpson,et al.  Comparative studies of metamodelling techniques under multiple modelling criteria , 2001 .

[5]  Hsien-Chie Cheng,et al.  Assessing a Response Surface-Based Optimization Approach for Soil Vapor Extraction System Design , 2009 .

[6]  G. G. Wang,et al.  Adaptive Response Surface Method Using Inherited Latin Hypercube Design Points , 2003 .

[7]  I. Butera,et al.  Simultaneous identification of the pollutant release history and the source location in groundwater by means of a geostatistical approach , 2013, Stochastic Environmental Research and Risk Assessment.

[8]  R. Neupauer,et al.  Adjoint‐derived location and travel time probabilities for a multidimensional groundwater system , 2001 .

[9]  L. Tierney.  Markov Chains for Exploring Posterior Distributions , 1994 .

[10]  Divya Srivastava,et al.  Groundwater System Modeling for Simultaneous Identification of Pollution Sources and Parameters with Uncertainty Characterization , 2015, Water Resources Management.

[11]  George F. Pinder,et al.  Application of the Digital Computer for Aquifer Evaluation , 1968 .

[12]  A. Bagtzoglou,et al.  Application of particle methods to reliable identification of groundwater pollution sources , 1992 .

[13]  R. S. Govindaraju,et al.  Artificial Neural Networks in Hydrology , 2010 .

[14]  Shuai Li,et al.  Chance-constrained multi-objective optimization of groundwater remediation design at DNAPLs-contaminated sites using a multi-algorithm genetically adaptive method. , 2017, Journal of contaminant hydrology.

[15]  Gintaras V. Reklaitis,et al.  Simulation-based optimization with surrogate models - Application to supply chain management , 2005, Comput. Chem. Eng..

[16]  A. Barron,et al.  Discussion: Multivariate Adaptive Regression Splines , 1991 .

[17]  S. Chib,et al.  Understanding the Metropolis-Hastings Algorithm , 1995 .

[18]  J. Gómez-Hernández,et al.  Simultaneous identification of a contaminant source and hydraulic conductivity via the restart normal-score ensemble Kalman filter , 2018 .

[19]  H. Haario,et al.  An adaptive Metropolis algorithm , 2001 .

[20]  Amvrossios C. Bagtzoglou,et al.  Radial basis function neural network for hydrologic inversion: an appraisal with classical and spatio-temporal geostatistical techniques in the context of site characterization , 2009 .

[21]  B. Datta,et al.  Identification of groundwater pollution sources using GA-based linked simulation optimization model , 2006 .

[22]  Wenxi Lu,et al.  A mixed-integer non-linear programming with surrogate model for optimal remediation design of NAPLs contaminated aquifer , 2014 .

[23]  D. Rubin,et al.  Inference from Iterative Simulation Using Multiple Sequences , 1992 .

[24]  Ranji S. Ranjithan,et al.  A parallel evolutionary strategy based simulation–optimization approach for solving groundwater source identification problems , 2009 .

[25]  Ying Zhao,et al.  Surrogate Model-Based Simulation-Optimization Approach for Groundwater Source Identification Problems , 2015 .

[26]  Wenxi Lu,et al.  A Kriging surrogate model coupled in simulation-optimization approach for identifying release history of groundwater sources. , 2016, Journal of contaminant hydrology.

[27]  Adrian F. M. Smith,et al.  Bayesian computation via the gibbs sampler and related markov chain monte carlo methods (with discus , 1993 .

[28]  Peter C. Young,et al.  State Dependent Parameter metamodelling and sensitivity analysis , 2007, Comput. Phys. Commun..

[29]  E. Acar.  Various approaches for constructing an ensemble of metamodels using local measures , 2010 .

[30]  Micha Werner,et al.  Reduction of Monte-Carlo simulation runs for uncertainty estimation in hydrological modelling , 2003 .

[31]  XiangJun Tian,et al.  A new approach for Bayesian model averaging , 2012, Science China Earth Sciences.

[32]  M Tamer Ayvaz,et al.  A linked simulation-optimization model for solving the unknown groundwater pollution source identification problems. , 2010, Journal of contaminant hydrology.

[33]  Farrokh Mistree,et al.  Kriging Models for Global Approximation in Simulation-Based Multidisciplinary Design Optimization , 2001 .

[34]  Achille Messac,et al.  Metamodeling using extended radial basis functions: a comparative approach , 2006, Engineering with Computers.

[35]  S. Gorelick,et al.  Identifying sources of groundwater pollution: An optimization approach , 1983 .

[36]  Wenxi Lu,et al.  Comparative study of surrogate models for groundwater contamination source identification at DNAPL-contaminated sites , 2018, Hydrogeology Journal.

[37]  R. Haftka,et al.  Multiple surrogates: how cross-validation errors can help us to obtain the best predictor , 2009 .

[38]  Christine A. Shoemaker,et al.  A Stochastic Radial Basis Function Method for the Global Optimization of Expensive Functions , 2007, INFORMS J. Comput..

[39]  D. Ouazar,et al.  Ground Water Contaminant Source and Transport Parameter Identification by Correlation Coefficient Optimization , 1998 .

[40]  José Luis Rojo-Álvarez,et al.  Spectrally adapted Mercer kernels for support vector nonuniform interpolation , 2014, Signal Process..

[41]  Hao Li,et al.  Application of a novel hybrid method for spatiotemporal data imputation: A case study of the Minqin County groundwater level , 2017 .

[42]  Nash model parameter uncertainty analysis by AM-MCMC based on BFS and probabilistic flood forecasting , 2011 .

[43]  William P. Ball,et al.  Application of inverse methods to contaminant source identification from aquitard diffusion profiles at Dover AFB, Delaware , 1999 .

[44]  Bithin Datta,et al.  Identification of unknown groundwater pollution sources using classical optimization with linked simulation , 2011 .

[45]  Z. J. Kabala,et al.  Recovering the release history of a groundwater contaminant using a non-linear least-squares method. , 2000 .

[46]  Bryan A. Tolson,et al.  Review of surrogate modeling in water resources , 2012 .

[47]  Kourosh Behzadian,et al.  Stochastic sampling design using a multi-objective genetic algorithm and adaptive neural networks , 2009, Environ. Model. Softw..

[48]  Raghavan Srinivasan,et al.  Approximating SWAT Model Using Artificial Neural Network and Support Vector Machine 1 , 2009 .

[49]  HouZeyu,et al.  Selecting Parameter-Optimized Surrogate Models in DNAPL-Contaminated Aquifer Remediation Strategies , 2015 .

[50]  Ilya M. Sobol,et al.  Theorems and examples on high dimensional model representation , 2003, Reliab. Eng. Syst. Saf..

[51]  Wenxi Lu,et al.  Ensemble of surrogates-based optimization for identifying an optimal surfactant-enhanced aquifer remediation strategy at heterogeneous DNAPL-contaminated sites , 2015, Comput. Geosci..

[52]  Raphael T. Haftka,et al.  Surrogate-based Analysis and Optimization , 2005 .

[53]  A. Zanini,et al.  Laboratory sandbox validation of pollutant source location methods , 2014, Stochastic Environmental Research and Risk Assessment.

[54]  T. Skaggs,et al.  Recovering the release history of a groundwater contaminant , 1994 .

[55]  Wenxi Lu,et al.  Application of ensemble surrogates and adaptive sequential sampling to optimal groundwater remediation design at DNAPLs-contaminated sites. , 2017, Journal of contaminant hydrology.