Estimation of in-situ bioremediation system cost using a hybrid Extreme Learning Machine (ELM)-particle swarm optimization approach

Abstract In-situ bioremediation is the most common groundwater remediation procedure used for treating organically contaminated sites. A simulation-optimization approach, which incorporates a simulation model for groundwaterflow and transport processes within an optimization program, could help engineers in designing a remediation system that best satisfies management objectives as well as regulatory constraints. In-situ bioremediation is a highly complex, non-linear process and the modelling of such a complex system requires significant computational exertion. Soft computing techniques have a flexible mathematical structure which can generalize complex nonlinear processes. In in-situ bioremediation management, a physically-based model is used for the simulation and the simulated data is utilized by the optimization model to optimize the remediation cost. The recalling of simulator to satisfy the constraints is an extremely tedious and time consuming process and thus there is need for a simulator which can reduce the computational burden. This study presents a simulation-optimization approach to achieve an accurate and cost effective in-situ bioremediation system design for groundwater contaminated with BTEX (Benzene, Toluene, Ethylbenzene, and Xylenes) compounds. In this study, the Extreme Learning Machine (ELM) is used as a proxy simulator to replace BIOPLUME III for the simulation. The selection of ELM is done by a comparative analysis with Artificial Neural Network (ANN) and Support Vector Machine (SVM) as they were successfully used in previous studies of in-situ bioremediation system design. Further, a single-objective optimization problem is solved by a coupled Extreme Learning Machine (ELM)-Particle Swarm Optimization (PSO) technique to achieve the minimum cost for the in-situ bioremediation system design. The results indicate that ELM is a faster and more accurate proxy simulator than ANN and SVM. The total cost obtained by the ELM-PSO approach is held to a minimum while successfully satisfying all the regulatory constraints of the contaminated site.

[1]  Shahaboddin Shamshirband,et al.  A comparative evaluation for identifying the suitability of extreme learning machine to predict horizontal global solar radiation , 2015 .

[2]  Shashi Mathur,et al.  Multi-objective optimization of in-situ bioremediation of groundwater using a hybrid metaheuristic technique based on differential evolution, genetic algorithms and simulated annealing , 2015 .

[3]  Sudhir Kumar,et al.  Optimal Pumping from Skimming Wells , 2006 .

[4]  C. W. Tong,et al.  RETRACTED ARTICLE: Application of extreme learning machine for estimation of wind speed distribution , 2016, Climate Dynamics.

[5]  Barbara S. Minsker,et al.  Computational Issues for Optimal In-Situ Bioremediation Design , 1998 .

[6]  P. Bedient,et al.  Transport of dissolved hydrocarbons influenced by oxygen‐limited biodegradation: 1. Theoretical development , 1986 .

[7]  B. K. Panigrahi,et al.  Development of an artificial neural network based multi-model ensemble to estimate the northeast monsoon rainfall over south peninsular India: an application of extreme learning machine , 2014, Climate Dynamics.

[8]  J. Bahr,et al.  Nitrate-enhanced bioremediation of BTEX-contaminated groundwater: parameter estimation from natural-gradient tracer experiments. , 2002, Journal of contaminant hydrology.

[9]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[10]  Narasimhan Sundararajan,et al.  A Fast and Accurate Online Sequential Learning Algorithm for Feedforward Networks , 2006, IEEE Transactions on Neural Networks.

[11]  N. Null.  Artificial Neural Networks in Hydrology. I: Preliminary Concepts , 2000 .

[12]  Min Han,et al.  Online sequential extreme learning machine with kernels for nonstationary time series prediction , 2014, Neurocomputing.

[13]  Barbara S. Minsker,et al.  Applying Dynamic Surrogate Models in Noisy Genetic Algorithms to Optimize Groundwater Remediation Designs , 2011 .

[14]  Hongming Zhou,et al.  Extreme Learning Machine for Regression and Multiclass Classification , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[15]  James F. Barker,et al.  Biotransformation of BTEX under anaerobic, denitrifying conditions: Field and laboratory observations , 1992 .

[16]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[17]  C. Shoemaker,et al.  DYNAMIC OPTIMAL CONTROL OF IN-SITU BIOREMEDIATION OF GROUND WATER , 1998 .

[18]  Shervin Motamedi,et al.  Extreme learning machine based prediction of daily dew point temperature , 2015, Comput. Electron. Agric..

[19]  Pei Li,et al.  Forecasting Model of Coal Mine Water Inrush Based on Extreme Learning Machine , 2013 .

[20]  Yong Yu,et al.  Sales forecasting using extreme learning machine with applications in fashion retailing , 2008, Decis. Support Syst..

[21]  Anthony N. Michel,et al.  Design of optimal pump-and-treat strategies for contaminated groundwater remediation using the simulated annealing algorithm , 1992 .

[22]  R. C. Peralta,et al.  Closure to discussion on Optimal in-situ bioremediation design by hybrid genetic algorithm-simulated annealing , 2005 .

[23]  George F. Pinder,et al.  Economic parameters' effects in the optimal design of a groundwater remediation system , 2004 .

[24]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[25]  Shashi Mathur,et al.  Optimal design of an in-situ bioremediation system using support vector machine and particle swarm optimization. , 2013, Journal of contaminant hydrology.

[26]  Xia Liu,et al.  Is Extreme Learning Machine Feasible? A Theoretical Assessment (Part I) , 2015, IEEE Trans. Neural Networks Learn. Syst..

[27]  J. Guan,et al.  Optimal remediation with well locations and pumping rates selected as continuous decision variables , 1999 .

[28]  Oswer Us Epa.  How to Evaluate Alternative Cleanup Technologies for Underground Storage Tank Sites: A Guide for Corrective Action Plan Reviewers , 2014 .

[29]  Christine A. Shoemaker,et al.  Comparison of Optimization Methods for Ground-Water Bioremediation , 1999 .

[30]  H. Loáiciga,et al.  Optimal In Situ Bioremediation Design of Groundwater Contaminated with Dissolved Petroleum Hydrocarbons , 2016 .

[31]  Barbara S. Minsker,et al.  Multiscale island injection genetic algorithms for groundwater remediation , 2007 .

[32]  Paresh Chandra Deka,et al.  Support vector machine applications in the field of hydrology: A review , 2014, Appl. Soft Comput..

[33]  Shashi Mathur,et al.  Potential Well Locations in In Situ Bioremediation Design Using Neural Network Embedded Monte Carlo Approach , 2008 .

[34]  R. H. Douglass,et al.  Effect of Nitrate Addition on Biorestoration of Fuel‐Contaminated Aquifer: Field Demonstration , 1991 .

[35]  Amy B. Chan Hilton,et al.  Groundwater Remediation Design under Uncertainty Using Genetic Algorithms , 2005 .

[36]  Guang-Bin Huang,et al.  Extreme learning machine: a new learning scheme of feedforward neural networks , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[37]  Peter K. Kitanidis,et al.  In Situ BTEX Biotransformation under Enhanced Nitrate- and Sulfate-Reducing Conditions , 1997 .

[38]  Richard C. Peralta,et al.  Optimal design of aquifer cleanup systems under uncertainty using a neural network and a genetic algorithm , 1999 .