Application of Artificial Neural Network to Predict the Water Quality Index of Brahmani River Basin Odisha, India

Binayini Bhagat, D. P. Satapathy


Water is one of the prime elements responsible for subsistence on the earth. The scarcity of potable water is gradually increasing with the increase in population. The surface water quality is a very crucial and sensitive issue and is also a great environmental concern worldwide. Surface water pollution by physical, chemical, radiological and biological contaminants can be considered as an epidemic at times, all over the world. The present research work aims at assessing the water quality index (WQI) in the surface water of Brahmani river basin in Odisha by monitoring five sampling locations. The surface water samples data were subjected to comprehensive physico-chemical analysis besides general parameters. The monthly water quality parameters were collected and analyzed from five selected gauging stations of Odisha during the months of January to December from 2011 to 2016. Eleven physical, chemical and biological water quality parameters viz. pH, Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), Electrical Conductivity(EC), Nitrogen as nitrate (Nitrate-N), Total Coli-form Bacteria(TC), Fecal Coli-form Bacteria(FC), Chemical Oxygen Demand (COD), Nitrogen as ammonia (NH4-N), Total Alkalinity (TA) as CaCO3, Total Hardness (TH) as CaCO3 were selected for the analysis. Analysis of water quality for Brahmani River is done by Water Quality Index (WQI). Prediction of water quality index is done by using Artificial Neural Network (ANN).  It is apparent from WQI values that Talcher and Panposh recorded the water quality as moderate to poor and nearly unsuitable during the years 2011-2016 indicating water as not safe for domestic purposes and needs treatment, the WQI values of Kamalanga ranged from good to poor and the WQI values of Aul and Pottamundai ranged from good to moderate. Eleven physico-chemical parameters were involved in this analysis as input variables and water quality index as output variable. Two models were proposed to identify the most effective model in an attempt to predict the WQI.  Correlation between the parameters was carried out to find out the significant parameters affecting WQI. The ANN developed was trained and tested successfully using the available data sets and the performance of ANN models were determined by coefficient of determination (R2) and Root Mean Square Error (RMSE). Results show that ANN-1 gives the higher value of R2 in summer, monsoon and winter season (0.989, 0.976 and 0.959) and low RMSE (2.1865, 2.0768 and1.9657) as compared to that of the second model (ANN-2) which gives R2 value as 0.933, 0.945 and 0.943 and RMSE value as 2.8765, 2.5456 and 1.2745 for summer, monsoon and winter seasons respectively. Hence this study triggered the use of Artificial Neural Network to predict the Water Quality Index (WQI) rather than using the traditional WQI equation.

Full Text:



Adamowski, J. and Chan, H. F. 2011. “A wavelet Neural Network Conjunction Model for Groundwater Level Forecasting.” Journal of Hydrology 407: 28-40.

Akkaraboyina, M.K. and Raju, B.S.N. (2012). Assessment of water Quality Index of River Godavari at Rajahmundry. Universal Journal of Environmental Research and Technology. 2(3), 161-166.

APHA, 2002: Standard Methods for the Examination of Water and Wastewater. American Public Health Association, Washington D.C.

BIS 1983 Standards of Water for drinking and other purposes, Bureau of Indian Standards, New Delhi.

BIS, 1992: Indian Standard for Drinking Water Specification – 10500. Bureau of Indian Standards, New Delhi.

Boyacioglu, H. (2006). Surface water quality assessment using factor analysis. Water SA. 32(3), 384-393.

Chaterjee,C. and Raziuddin, M.(2002). Determination of water quality index (WQI) of a degraded river in Asanol Industrial area, Raniganj, Burdwan, West Bengal. Nature, Environment and pollution Technology,1(2):181-189.

Daliakopoulos, I. N., Coulibaly, P., Tsanis, I. K. (2005), Groundwater level forecasting using artificial neural networks. Journal of Hydrology, 309, 229-240.

Najah, A.; Elshafie, A.; Karim, O.; & Jafar, O., (2009). Prediction of Johor River Water Quality Parameters Using Artificial Neural Networks. European Journal of Scientific Research, 28:422.

Nasir Mohd,; Juahir M.F., H.; Roalan, N.; Mohd, I.; Shafie, N.A.; & Ramli, N., (2011). Artificial Neural Networks Combined With Sensitivity Analysis as a Prediction Model for Water Quality Index in Juru River, Malaysia. International Journal of Environmental Protection, 1:3:1.

Rumysa K., Sharique A. A., Tariq Z., Farooq M., Bilal A., and Pinky K.,(2012) “Physico chemical status of Wular Lake in Kashmir,” Journal of Chemistry, Biology and Physics Science, 31, pp. 631–636.

Yogendra K. and Puttaiah E.T.,(2008) Determination of Water Quality Index and Suitability of an Urban Waterbody in Shimoga town, Karnataka.



  • There are currently no refbacks.