APPLICATION OF ARTIFICIAL NEURAL NETWORK MODELS FOR PREDICTING WATER QUALITY INDEX
DOI:
https://doi.org/10.11113/mjce.v16.15664Keywords:
Artificial Neural Network, Multiple Linear Regression, Water Quality Index (WQI).Abstract
This study discusses the development and validation of an Artificial Neural
Network (ANN) model in estimating water quality index (WQI) in the Langat River
Basin, Malaysia. The ANN model has been developed and tested using data from 30
monitoring stations. The modeling data was divided into two sets. For the first set, ANNs
were trained, tested and validated using six independent water quality variables as input
parameters. Consequently, Multiple Linear Regression (MLR) was applied to eliminate
independent variables that exhibit the lowest contribution in variance. Independent
variables that accounted for approximately 71% of the variance in WQI are Dissolved
Oxygen (DO), Biochemical Oxygen Demand (BOD), Suspended Solids (SS) and
Ammoniacal-Nitrate (AN). The Chemical Oxygen Demand (COD) and pH contributed
only 8% and 2% to the variance, respectively. Thus, in the second data set, only four
independent variables were used to train, test and validate the ANNs. We found that the
correlation coefficient given by six independent variables (0.92) is only slightly better in
estimating WQI compared to four independent variables (0.91) which demonstrates that
ANN is capable of estimating WQI with acceptable accuracy when it is trained by
eliminating COD and pH as independent variables.
References
Calder, I.R., (1999). The Blue Revolution: Land Use and Integrated Water Resources
Management. Earthscan Publications Ltd: London
Dale, W.L. (1959) The rainfall of Malaya, Part 1. Journal Tropical Geography, 13: 23-
Hafizan J., Sharifuddin M. Z., M. Nazari J. and Zainal A. (2004) Water discharge
modeling by neural networks. Application of second order backpropagation method to
improve river management at Langat River, Malaysia. Proceedings of the Water
Environmental Planning: Towards Integrated Planning and Management of Water
Resources for Environmental Risks. Bureau of Consultancy & Entrepreneurship,
International Islamic University Kuala Lumpur, p. 307-324
Hafizan J., Sharifudin M. Z., Mohd Ekhwan T., M. Nazari J. and Klaewtanong, W.
(2003) Performance of autoregressive integrated moving average and neural network
approaches for forecasting dissolved oxygen at Langat River. In Noorazuan M.H. and
Ruslan R. (eds.) Urban ecosystem studies in Malaysia: A study of change. Florida:
Universal Publishers, p. 145-165.
Horton, R.K. (1965) An index number system for rating water quality. Journal of Water
Pollution Control Fed., 37(3): 300-305
Jain, A. and Prasad Indurthy, S. K. V. (2003) Comparative analysis of event-based
rainfall-runoff modeling techniques-deterministic, statistical, and artificial neural
networks, Journal of Hydrologic Engineering, 8: 93-98.
Mohd Ekhwan T. (2002) Investigations into channel instability and river morphological
change: The Langat River, Peninsular Malaysia. Ph.D Thesis. Faculty of Science,
Agriculture and Engineering, University of Newcastle Upon Tyne, 255 pp.
Mohd Ekhwan T. and Hafizan J. (2003) Artificial neural network modeling for Langat
River discharge: Implication for river restoration. In Ajib C.K., Awang Hasmadi
A.M., Baszley Bee, B.B. Idris, Fuziah Kartini A., H.B. Rozmi I. and Mohd Safar H
(eds.). Abstract of Inovation and Research Expo, Universiti Kebangsaan Malaysia
(Gold medal), B17.
Rojas, R. (1955). Neural networks: A Systematic introduction, Springer-Verlag, Berlin,
-448.
Stambuk-Giljanovic, N (1999). Water quality evaluation by index in Dalmatia. Water
Resources, 33:3423-3440.
Sudheer, K.P., Nayak, P.C and Ramasastri, K.S. (2003) Improving peak flow estimates in
Artificial Neural Network river flow models. Hydrological Processes, 17: 677-687.
UPUM (2002) Draf Laporan Akhir: Program Pencegahan Pencemaran dan Peningkatan
Kualiti Air Sungai Langat. Unit Perundingan Universiti Malaya.
Zhang, Q. and Stanley, S. J. (1997) Forecasting raw-water quality parameters for North
Saskatchewan River by neural network modeling. Water Resources, 31: 2340-2350.