Simulation ofCeriumand Lanthanuminthestream sedimentofEshtehard regionusingan Artificial NeuralNetwork

Authors

1 Ph.D Student, Department of Mining and metallurgical Engineering, Yazd University,Yazdو Iran

2 Associate Professor, Department of Mining and Metallurgical Engineering , Yazd University, Yazd, Iran

Abstract

      Artificial Neural Network is an advanced method that is effective in estimation dynamic and nonlinear systemes. Recently the use of Artificial Neural Network and multivariate statistical methods spread in important environmental issues such as soil and surface water pollution to toxic elements that in this case can be provided a model based on a Artificial Neural Network for simulation of rare earth element. Considering the importance of Rare Earth Elements special Ce and La, this study aims to predict these elements concentration in the Eshtehard region of Iran by means of developed Artificial Neural Network (ANN). Forward Selection (FS) method was used for selecting input variables and developing hybrid models with ANN.From45 input candidates, 23 variables were selected using FS for Ce and La, respectively. Considering the correlation coefficient (R2 )values, both models (ANN and FS-ANN)are acceptable in prediction of Ce and La concentration. However, FS-ANN is superior, because R2values for Ce and La prediction for FS-AAN model is higher than R2 values for Ce and La prediction for ANN model. It is also shown that the FS-ANN model will be preferred in predicting pollution of Ce and La due to reducing in time of calculation in consequence of having less input variables.
 

Keywords

References

Chen, S., Billings, S.A., Luo, W., 1989.Orthogonal least squares methods and their application to nonlinear system identification. International Journal of Control 50, 1873e1896.
Chen, S., Hong, X., Harris, C.J., Sharkey, P.M., 2004.Sparse modeling using orthogonal forward regression with PRESS statistic and regularization.IEEE Transactions on Systems, Man, and Cybernetics e Part B 34, 898e911.
Corcoran, J., Wilson, I., Ware, J., 2003. Predicting the geo-temporal variation of crime and disorder.International Journal of Forecasting 19, 623e634.
Cybenko, G., 1989. Approximationby superposition of a sigmoidal function.Mathematics of Control, Signals, and Systems 2, 303e314.
Eksioglu, B., Demirer, R., Capar, I., 2005. Subset selection in multiple linear regression: a new mathematical programming approach. Computers & Industrial Engineering 49, 155e167.
Jalili-Ghazizadeh, M., Noori, R., 2008.Prediction of municipal solid waste generation by use of artificial neural network: a case study of Mashhad. International Journal of Environmental Research 2, 13e22.
Khan, J.A., Aelst, S.V., Zamar, R.H., 2007.Building a robust linear model with forward selection and stepwise procedures.Computational Statistics & Data Analysis 52, 239e248.
Moghaddamnia, A., Ghafari-Gousheh, M., Piri, J., Amini, S., Han, D., 2009. Evaporation estimation using artificial neural networks and adaptive neuro-fuzzy inference system techniques.Advances in Water Resources 23, 88e97.
Noori, R., Abdoli, M.A., Ameri, A., Jalili-Ghazizadeh, M., 2009a.Prediction of municipal solid waste generation with combination of support vector machine and principal component analysis: a case study of Mashhad. Environmental Progress & Sustainable Energy 28, 249e258.
Noori, R.,Abdoli,M.A., Jalili-Ghazizadeh,M., Samifard, R.,2009c.ComparisonofANNand PCA based multivariate linear regression applied to predict the weekly municipal solid waste generation in Tehran. Iranian Journal of Public Health 38, 74e84.
Nunnari, G., Dorling, S., Schlink, U., Cawley, G., Foxall, R., Chatterton, T., 2004.Modelling SO2 concentration at a point with statistical approaches.EnvironmentalModelling& Software 19, 887e905.
Perez-Roaa, R., Castroa, J., Jorqueraa, H., Perez-Correaa, J.R., Vesovic, V., 2006.Airpollution modeling in an urban area: correlating turbulent diffusion coefficients by means of an artificial neural network approach. Atmospheric Environment 40, 109e125.
Seasholtz, M.B., Kowalski, B., 1993. The parsimony principle applied to multivariate calibration. AnalyticaChimicaActa 277, 165e177.
Wang, X.X., Chen, S., Lowe, D., Harris, C.J., 2006. Sparse support vector regression based on orthogonal forward selection for the generalised kernel model. Neurocomputing 70, 462e474.
Advanced Applied Geology
Volume 3, Issue 3 - Serial Number 9
October 2013
Pages 63-72

Files

Share

How to cite

Statistics