Abstract
Contamination of groundwater is one of the major health concerns in the rapidly urbanizing and industrializing world. Since groundwater is one of the most important resources for the domestic, industrial, and agricultural purposes, the quality and quantity is of prime importance. Nitrite which is a reduced form of nitrate ion is one of the potential contaminants in the groundwater. The detection of nitrite ion is one of the laborious works and also it gets easily oxidized to nitrate ion and hence modeling approaches for the nitrite concentration will be one of the resilient quantification techniques. In the present study, the effective performance of the linear and non-linear models such as multiple linear regression (MLR), principal component regression (PCR), artificial neural network (ANN), and the integrated technique of principal components and artificial neural network (PC-ANN) is evaluated in the prediction of the nitrite concentration. The MLR and PCR showed better results either in generation step or in the validation step but not both. ANN shows better results in both generation and validation steps but the results in the validation steps, though good but accuracy is comparatively lower than the generation step. In the case of PC-ANN, the prediction of the model is found to be good both in the generation and in the validation steps. The Nash–Sutcliffe efficiency test clearly illustrates better performance of PC-ANN in comparison with other models in the present study for the quantification of nitrite concentration in groundwater.
Similar content being viewed by others
References
Arunprakash M, Giridharan L, Krishnamurthy RR, Jayaprakash M (2014) Impact of urbanization in groundwater of south Chennai City, Tamil Nadu, India. Environmental Earth Sciences 71(2):947–950
Ballukraya PN, Ravi R (1998) Natural fresh water ridge as barrier against sea water intrusion in Chennai City. J GeolSoc India 52(3):279–286
Bowerman BL, O’Connell RT (1990) Linear statistical models: an applied approach, Second edn. Duxbury Press, Belmont, CA
Brion GM, Lingireddy S (1999) A neural network approach to identifying non-point sources of microbial contamination. Water Res 33(14):3099–3106
Bucinski A, Baczek T, Wasniewski T, Stefanowicz M (2005) Clinical data analysis with the use of artificial neural networks (ANN) and principal component analysis (PCA) of patients with endometrial carcinoma. Reports on Practical Oncology and Radiotherapy 10:239–248
Capolo M, Andreussi P, Soldati A (1999) River filled forecasting with a neural network model. Water Resource Res 35:1191–1197
Chauhan S, Sharma M, Arora MK, Gupta NK (2010) Landslide susceptibility zonation through ratings derived from artificial neural network. Int J Appl Earth Obs Geoinf 12:340–350
Chen RM, Huang YM (2001) Competitive neural network to solve scheduling problems. Neurocomputing 37:177–196
Cho KH, Sthiannopkao S, Pachepsky YA, Kim KW, Kim JH (2011) Prediction of contamination potential of groundwater arsenic in Cambodia, Laos, and Thailand using artificial neural network. Water Res 45(17):5535–5544
Fausett L (1994) Fundamentals of neural network architecture, algorithms, and applications. Prentice-Hall, UK
Ghasemloo N, Mobasheri MR, Rezaei Y (2011) Vegetation species determination using spectral characteristics and artificial neural network (SCANN). J Agr Sci Tech 13(Suppl):1223–1232
Haykin S (1999) Neural networks: a comprehensive foundation. Macmillan College, London
Hornik K (1991) Approximation capability of multi-layer feedforward networks. Neural Netw 4:241–257
Jayaprakash M, Nagarajan R, Velmurugan PM, Sathiyamoorthy J, Krishnamurthy RR, Urban B (2012) Assessment of trace metal contamination in a historical freshwater canal (Buckingham Canal), Chennai, India. Environ Monit Assess 184(12):7407–7424
Jolliffe IT (2002) Principal components analysis. Springer-Verlag, New York, p 488p
Lee I M, Lee J H(2006) Prediction of pile bearing capacity using artificial neural networks. Comput Geotech 18(3):189–200
Liu G, Yi Z, Yang S (2007) A hierarchical intrusion detection model based on the PCA neural networks. Neurocomputing 70:1561–1568
Maedeh A, Mehrdadi N, Nabi Bidhendi GR, Zare Abyaneh H (2013) Application of artificial neural network to predict total dissolved solids variations in groundwater of Tehran plain. Iran Int J Environment and Sustainability 2(1):10–20
Marengo E, Bobba M, Robotti E, Liparota MC (2006) Modeling of the polluting emissions from a cement production plant by partial least-squares. Principal Component Regression and Artificial Neural Networks Environ Sci Technol 2006(40):272–280
Myers R (1990) Classical and modern regression with applications, Second edn. Duxbury Press, Boston, MA
O’Farrella M, Lewisa E, Flanagana C, Lyonsa WB, Jackman N (2005) Combining principal component analysis with an artificial neural network to perform online quality assessment of food as it cooks in a large-scale industrial oven. Sensors Actuators B 107:104–112
Ravi V, Pramodh C (2008) Threshold accepting trained principal component neural network and feature subset selection: application to bankruptcy prediction in banks. Appl Soft Comput 8:1539–1548
Rawlings JO, Pantula SG, Dickey DA (1998) Applied regression analysis: a research tool. Springer, New York
Sarala Thambavani D, Uma Mageswari TSR (2015) Comparative application of ANN and PCA in modeling of ground water. J Adv Chem Sci 1(1):22–26
Sousa SIV, Martins FG, Alvim-Ferraz MCM, Pereira MC (2007) Multiple linear regression and artificial neural networks based on principal components to predict ozone concentrations. Environ Model Softw 22:97–103
Yazdani MR, Saghafian B, Mahdian MH, Soltani S (2009) Monthly runoff estimation using artificial neural networks. J Agr SciTech 11(3):355–362
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Charulatha, G., Srinivasalu, S., Uma Maheswari, O. et al. Evaluation of ground water quality contaminants using linear regression and artificial neural network models. Arab J Geosci 10, 128 (2017). https://doi.org/10.1007/s12517-017-2867-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12517-017-2867-6