Back-Propagation Neural Network on Characterization of Groundwater Quality in Pingtung Champaign, Taiwan

Abstract:

Four clusters were classified according to the similarities and dissimilarities of water quality data collected from 1998 to 2008 of the 76 monitoring wells in Pingtung Champaign. The results showed that the groundwater quality of hinterland was better than that of coastal area. Some wells along the coastal areas have already been influenced by seawater intrusion incurring aquifer salinization. The overall grouping accuracy of cluster analysis (CA) for rainy and dry seasons was 95.8% and 97% according to the discriminant analysis, respectively. The results from the back-propagation neural network (BPNN) model showed no significant variations of nitrate (NO₃-N) between the estimated and observed data, however most of the estimated total organic carbon (TOC) data were higher than the observed ones. It meant that the groundwater quality may be susceptible to the impacts of organic pollutants in the future within 90% confidence intervals. The results of this study show that application of CA and BPNN can simplify complex non-linear systems, moreover, groundwater quality can be estimated and modeled via monitoring data over the years. The modeling results can be utilized to frame the corresponding strategies to reduce the monitoring cost and to enhance the cost-effective benefits. The proposed analysis methods can be referred as a management plan for groundwater resources and pollution prevention to achieve the goal of early warning.

• Periodical: Applied Mechanics and Materials (Volumes 58-60)
• Pages: 2456-2461
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.58-60.2456
• Online since: June 2011
• Authors: Yi Chu Huang, Ping Kuei Tang, Yu Chun Lee, Ya Ru Lin
• Keywords: BP Neural Network (BPNN), Cluster Analysis, Groundwater Quality

References

[1] C. W., Liu, K. H. Lin, and Y. M. Kuo, Application of factor analysis in the assessment of groundwater quality in a Blackfoot disease area in Taiwan, Sci. Total Environ., vol. 313, No. 1-3 (2003), pp.77-89.

DOI: 10.1016/s0048-9697(02)00683-6

[2] Y. C. Huang, T. N. Wu, and P. J. Cheng, Characterization of groundwater quality by multivariate statistical analysis: an example from Kaohsiung County, Taiwan. In Water and Wastewater Management for Developing Countries, eds K Mathew and I Nhapi, IWA Publishing, London (2005).

[3] K. Chen, J. J. Jiao, J. Huang, and R. Huang, Multivariate statistical evaluation of trace elements in groundwater in a coastal area in Shenzhen, China, Environ. Pollution, vol. 147 (2007), pp.771-780.

DOI: 10.1016/j.envpol.2006.09.002

[4] Y.C. Huang, C.P. Yang, Y.C. Lee, P.K. Tang, W.M. Hsu, T.N. Wu, Variation of groundwater quality in seawater intrusion area using cluster and multivariate factor analysis, Proc. 6th Natural Computation (ICNC'10), vol. 6 (2010), pp.3021-3025.

DOI: 10.1109/icnc.2010.5582334

[5] G.F. Lin, and G.R. Chen, An improved neural network approach to the determination of aquifer parameters, J. of Hydrology, vol. 316 (2006), p.281–289.

DOI: 10.1016/j.jhydrol.2005.04.023

[6] V. A. Tsihrintzis, C. S. Akratos, and J. N. E. Papaspyros, An artificial neural network model and design equations for BOD and COD removal prediction in horizontal subsurface flow constructed wetlands, Chemical Engineering J., Vol. 143 (2008).

DOI: 10.1016/j.cej.2007.12.029

[7] K.P. Singh, A. Basant1, A. Malik, and G. Jain, Artificial neural network modeling of the river water quality - A case study, Ecological Modelling, vol. 220 (2009), p.888–895.

DOI: 10.1016/j.ecolmodel.2009.01.004

[8] S.N.B. Azghadi, R. Kerachian, M.R.B. Lari, and K. Solouki, Characterizing an unknown pollution source in groundwater resources systems using PSVM and PNN, Expert Systems with Applications, vol. 37 (2010), p.7154–7161.

DOI: 10.1016/j.eswa.2010.04.019

[9] F.J. Chang, L.S. Kao, Y.M. Kuo, and C.W. Liu, Artificial neural networks for estimating regional arsenic concentrations in a Blackfoot disease area in Taiwan, J. of Hydrology, vol. 388 (2010), p.65–76.

DOI: 10.1016/j.jhydrol.2010.04.029

[10] Information on http: /163. 29. 224. 196/soilandgw.

[11] Information on http: /wqshow. epa. gov. tw.

[12] J. C. Davis, Statistics and data analysis in Geology, 2nd ed., John Wiley and Sons (1987), NY, USA.

[13] J. E. Jackson, A user's guide to principal components, John Wiley and Sons (1991), NY, USA.

[14] W. McCulloch and W. Pitts, A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, vol. 5 (1943), pp.115-133.

DOI: 10.1007/bf02478259

[15] M. Kumar, N.S. Raghuwanshi, R. Singh, W. W. Wallender and W. Pruitt, Estimating evapotranspiration using artificial neural network, J. Irrig. and Drain. Engrg., Vol. 128, No. 4 (2002), pp.224-233.

DOI: 10.1061/(asce)0733-9437(2002)128:4(224)

[16] M.E. Turan and M.A. Yurdusev, River flow estimation from upstream flow records by artificial intellience methods, J. of Hydrology, vol. 369 (2009), p.71–77.

DOI: 10.1016/j.jhydrol.2009.02.004

[17] M.L. Yesilnacar, E. Sahinkaya, M. Naz, and B. Ozkaya, Neural network prediction of nitrate in groundwater of Harrian Plain Turkey, Environ. Geology, vol. 56 (2008), pp.19-25.

DOI: 10.1007/s00254-007-1136-5