Use Of Regression Model For Water Parameter Prediction Of Godwar Region

IJEP 41(8): 948-952 : Vol. 41 Issue. 8 (August 2021)

Sangeeta Parihar1*, Raina Jadhav2, Tarun Gehlot3 and Krishan Kumar Saini3

1. Jai Narain Vyas University, Department of Chemistry, Jodhpur, Rajasthan, India
2. IPS Academy, Department of Chemistry, Indore, Madhya Pradesh, India
3. MBM Engineering College, Structural Department, Jodhpur, Rajasthan, India


Water samples were collected from 20 stations of the Godwar region where human and animal activities were elevated. Multiple samples were analyzed for dissolved oxygen (DO), biochemical oxygen demand (BOD), chemical oxygen demand (COD), pH, total dissolved solids (TDS) and temperature (Temp.). The total data points were used to ascertain relationships between the parameters and data were also subjected to statistical analysis. First, a linear regression model was established between DO/BOD, COD/DO, BOD/COD, COD/pH, BOD/pH and DO/pH. A high to moderate correlation coefficient was observed as R2 ranged from 0.889 to 0.034 for these parameters. Then a multivariate linear regression model was setup for BOD and COD as dependent variables and DO, Temp., TDS and pH as four independent variables. The performance of the multivariate linear regression model was justified with statistical variables like average square root error (ASRE) and universal efficiency (UE). The predicted value of BOD and COD by model and regression analysis was in close agreement with their respective measured value. It was found that the pH parameter has more effect on BOD and COD as compared to predicting another parameter. ASRE was 37.8 mg/L for BOD prediction and 79.6 mg/L for COD prediction in a multivariate linear regression model.


Biological oxygen demand, Dissolved oxygen, Chemical oxygen demand, pH, Total dissolved solids, Temperature, Linear regression, Multivariate linear regression model


  1. Hur, J., et al. 2010. Estimation of biological oxygen demand and chemical oxygen demand for combined sewer systems using synchronous fluorescence spectra. Sensors. 10(4): 2460.
  2. Verma, A.K. and T.N. Singh. 2013. Prediction of water quality from simple field parameters. Env. Earth Sci., 69(3): 821-829.
  3. El-Korashey. 2009. Using regression analysis to estimate water quality constituents in Bahr El Baqar drain. J. Appl. Sci. Res., 5(8): 1067-1076.
  4. Elmolla, E.S., et al. 2010. The uses of artificial neural network (ANN) for modelling of COD removal from antibiotic aqueous solution by the Fenton process. 179: 127-134.
  5. Helsel, D.R. and R.M. Hirsch. 1995. Statistical methods in water resources, Studies in Environmental Sciences 49.
  6. Chapman, D. 1992. Water quality assessments Chapman and Hall, London. pp 80-81.
  7. Metcalf and Eddy. 2003. Wastewater engineering treatment and reuse (4th edn). McGraw Hill, New York, USA.
  8. Nemade, P.N. and V.S. Shrivastava. 2004. Correlation and regression analysis among the COD and BOD of industrial effluent. Poll. Res., 23(1): 187-188.