The Use of Combined Neural Networks and Genetic Algorithms for Prediction of River Water Quality

 

Y. R. Ding*¹, Y. J. Cai², P. D. Sun³ and B. Chen⁴

 

¹ Department of computer science and technology, JiangNan University, Wuxi, China. * yr_ding@jiangnan.edu.cn

² School of Biotechnology, Jiang Nan University, Wuxi, China.

³ School of Chemical and Material Engineering, JiangNan University, Wuxi, China.

⁴ Environmental Monitoring Station of Binhu District, Wuxi, China.

 

ABSTRACT

To effectively control and treat river water pollution, it is very critical to establish a water quality prediction system. Combined Principal Component Analysis (PCA), Genetic Algorithm (GA) and Back Propagation Neural Network (BPNN), a hybrid intelligent algorithm is designed to predict river water quality. Firstly, PCA is used to reduce data dimensionality. 23 water quality index factors can be compressed into 15 aggregative indices. PCA improved effectively the training speed of follow-up algorithms. Then, GA optimizes the parameters of BPNN. The average prediction rates of non-polluted and polluted water quality are 88.9% and 93.1% respectively, the global prediction rate is approximately 91%. The water quality prediction system based on the combination of Neural Networks and Genetic Algorithms can accurately predict water quality and provide useful support for realtime early warning systems.

Keywords: back propagation neural network, genetic algorithm, principal component analysis, water quality prediction.

 

DESCARGAR ARTÍCULO EN FORMATO PDF

 

Acknowledgements

This work was supported by the National Natural Science Foundation of China (21001053), the National High Technology Research and Development Program (2009AA02C210) and the Fundamental Research Funds for the Central Universities (JUSRP11126).

 

References

[1] W.C. Ip, et al., "Applications of grey relational method to river environment quality evaluation in China," Journal of Hydrology, vol. 379, no. 3-4, pp. 284-290, 2009.         [ Links ]

[2] E.M. Smeti, et al., "Treated water quality assurance and description of distribution networks by multivariate chemometrics," Water Research, vol. 43, no. 18, pp. 4676-4684, 2009.         [ Links ]

[3] D.A. Brydon and D.A. Frodsham, "A model-based approach to predicting BOD5 in settled sewage," Water Science and Technology, vol. 44, no. 2-3, pp. 915, 2001.         [ Links ]

[4] Liu Y, et al., "Water quality modeling for load reduction under uncertainty: a Bayesian approach," Water Research, vol. 42, no. 13, pp. 3305-3314, 2008.         [ Links ]

[5] V. Chandramouli, et al., "Backfilling missing microbial concentrations in a riverine database using artificial neural networks," Water Research, vol. 41, no. 1, pp. 217-227, 2007.         [ Links ]

[6] H.G. Han, et al., "An efficient self-organizing RBF neural network for water quality prediction," Neural Network, vol. 24, no. 7, pp. 717-725, 2011.         [ Links ]

[7] E. O'Connor, et al., "A neural network approach to smarter sensor networks for water quality monitoring," Sensors (Basel), vol. 12, no. 4, pp. 4605-4632, 2012.         [ Links ]

[8] O. Senkal, et al., "Precipitable water modelling using artificial neural network in Cukurova region," Environmental Monitoring and Assessment, vol. 184, No. 1, pp. 141-147, 2012.         [ Links ]

[9] J.H. Cho, et al., "A river water quality management model for optimising regional wastewater treatment using a genetic algorithm," Journal of Environmental Management, vol. 73, no. 3, pp. 229-242, 2004.         [ Links ]

[10] R. Zou and W.S. Lung, "Robust water quality model calibration using an alternating fitness genetic algorithm," Journal of Water Resources Planning and Management, vol. 130, no. 6, pp. 471-479, 2004.         [ Links ]

[11] Y. Icaga, "Genetic algorithm usage in water quality monitoring networks optimization in Gediz (Turkey) river basin," Environmental Monitoring and Assessment, vol. 108, no. 1-3, pp. 261-277, 2005.         [ Links ]

[12] L.L. Rogers, et al., "Optimal field-scale groundwater remediation using neural networks and the genetic algorithm," Environmental Science & Technology, vol. 29, no. 5, pp. 1145-1155, 1995.         [ Links ]

[13] S. Ledesma-Orozco, et al., "Hurst Parameter Estimation Using Artificial Neural Networks," Journal of Applied Research and Technology, vol. 9, no. 2, pp. 227-240, 2011.         [ Links ]

[14] A. Baharodimehr, et al., "Capacitive MEMS accelerometer wide range modeling using artificial neural network," Journal of Applied Research and Technology, vol. 7 no. 2, pp. 185-192, 2009.         [ Links ]

[15] M.R. Arab, et al., "Electroencephalogram Signals Processing for the Diagnosis of Petit mal and Grand mal Epilepsies Using an Artificial Neural Network," Journal of Applied Research and Technology, vol. 8 no.1, pp. 120-129, 2010.         [ Links ]

[16] J. Rivera-Mejía, et al., "PID based on a single artificial neural network algorithm for intelligent sensors," Journal of Applied Research and Technology, vol.10, no. 2, pp. 262-282, 2012.         [ Links ]

[17] V. Petridis, et al., "A hybrid neural-genetic multimodel parameter estimation algorithm," IEEE Transactions on Neural Networks, vol. 9, no. 5, pp. 862-876, 1998.         [ Links ]

[18] J.T. Kuo, et al., "A hybrid neural-genetic algorithm for reservoir water quality management," Water Research, vol. 40, no. 7, pp. 1367-1376, 2006.         [ Links ]

[19] S.G Dalal, et al., "Evaluation of significant sources influencing the variation of water quality of Kandla creek, Gulf of Katchchh, using PCA," Environmental Monitoring and Assessment, vol. 163, no. 1-4, pp. 49-56, 2010.         [ Links ]

[20] R.L. Olsen, et al., "Water quality sample collection, data treatment and results presentation for principal components analysis-literature review and Illinois River Watershed case study," Water Research, vol. 46, no. 9, pp. 3110-3122, 2012.         [ Links ]