Abstract

In-situ bioremediation is one of the most economic techniques for groundwater remediation. BIOPLUME III is used to simulate the transport and biodegradation of contaminant. During optimal design of bioremediation system, the simulated BIOPLUME III data for the entire aquifer is usually called several times by optimization algorithm to optimize the system. This is a very time consuming process and thus there is a need of proxy simulator to be used in place of BIOPLUME III. Artificial neural network is used in the present study as proxy simulator. The results show that Levenberg-Marquardt back propagation technique can be used for training neural network and thus, ANN can be used as proxy simulators.

References

• Samuel, A. 1959. Some studies in machine learning using the game of checkers. IBM Journal of Research and Development, 3(3):210–229.
• Aziz, A. and Wong, K. (1992). "Neural-Network Approach to the Determination of Aquifer Parameters. " Ground Water GRWAAP,, 30(2).
• Balkhair, K. (2002). "Aquifer parameters determination for large diameter wells using neural network approach. " Journal of Hydrology, 265(1-4), 118–128.
• Chang, L. and Chang, F. 2001. Intelligent control for modelling of real-time reservoir operation. Hydrological Processes, 15(9), 1621–1634.
• Coppola Jr, E. , Rana, A. , Poulton, M. , Szidarovszky, F. , and Uhl, V. 2005. A neural network model for predicting aquifer water level elevations. Ground Water, 43(2), 231–241.
• Prasad, R. and Mathur, S. 2006. "In-Situ Bioremediation of Contaminated Groundwater Using Artificial Neural Network. " ASCE.
• Muttil, N. and Chau, K. 2007. "Machine-learning paradigms for selecting ecologically significant input variables. " Engineering Applications of Artificial Intelligence, 20(6), 735–744.
• Morshed, J. and Kaluarachchi, J. J. 1998a. Application of artificial neural network and genetic algorithm in flow and transport simulations. Advances in Water Resources, 22(2), 145–158.
• Aly, A. H. and Peralta, R. C. 1999. "Optimal design of aquifer cleanup systems under uncertainty using a neural network and a genetic algorithm. " Water Resour. Res. , 35(8), 2523–2532.
• Johnson, V. M. and Rogers, L. L. 2000. Accuracy of neural network approximations in simulation-optimization. Journal of Water Resources Planning and Management, 126(2), 48–56.
• Borden, R. C. , Bedient, P. B. 1986. Transport of dissolved hydrocarbons influenced by oxygen-limited bioremediation. 1. Theoretical development. Water Resources Research, Vol. 22, No. 13, Pages 1973-1990
• Rifai, H. S. , Newell, C. J. , Gonzales, J. R. , Dendrou, S. , Kennedy, L. , and Wilson, J. T. 1997. BIOPLUME III natural attenuation decision support system, version 1. 0, user's manual. Air Force Center for Environmental Excellence (AFCEE), San Antonio.
• Yonaba1,H. , Anctil, F. and Fortin, V. 2010. Comparing Sigmoid Transfer Functions for Neural Network Multistep Ahead Streamflow Forecasting. Journal of Hydrologic Engineering, Vol. 15, No. 4, 275-278