Comprehensive Assessment of Groundwater Quality using Water Quality Index and Machine Learning-Based Prediction for the Industrial Area of Raipur, Chhattisgarh, India

IJEP 46(1): 16-24 : Vol. 46 Issue. 1 (January 2026)

Full Text

Mridu Sahu1*, D.C. Jhariya2, Vindhyavasini Singh Baghel3 and Shivangi Diwan1

1. National Institute of Technology, Department of Information Technology, Raipur – 492 010, Chattishgarh, India
2. National Institute of Technology, Department of Applied Geology, Raipur – 492 010, Chattishgarh, India
3. Geological Survey of India, Raipur – 492 010, Chattishgarh, India

Abstract

In this study, groundwater quality in Raipur city’s industrial area was assessed using both the groundwater quality index (GWQI) and machine learning. Twenty groundwater samples were collected, analyzed and tested for factors, such as pH, total dissolved solids (TDS) and heavy metals. The GWQI categorized the water quality as either suitable for drinking or unsuitable. Systematic linear interpolation, correlation analysis and feature selection were employed. Data collection spanned from April 2021 to December 2023, followed by a one-year evaluation period. This study estimates GWQI values through artificial neural network (ANN), support vector machine (SVM), random forest (RF) and K-nearest neighbours (KNN) models. KNN achieved the highest R2 value of 0.9718, with random forest and SVM performing closely. The random forest model demonstrated strong performance, with a mean absolute error (MAE) of 0.0592. Combining GWQI with machine learning provides a reliable method for monitoring groundwater quality and offers an effective framework for environmental management in industrial areas like Raipur.

Keywords

Machine learning prediction, Physico-chemical parameters, Groundwater quality classification

References

  1. Khan, R. and Jhariya, D.C. 2019. Assessment of groundwater pollution vulnerability using GIS based modified DRASTIC model in Raipur city, Chhattis-garh. J. Geol. Soc. India. 93: 293–304. DOI: 10.1 007/s12594-019-1177-x.
  2. Jhariya, D.C., Kumar, T., Dewangan, R., Pal, D. and Dewangan, P.K. 2017. Assessment of groundwater quality index for drinking purpose in the Durg district, Chhattisgarh using geographical information system (GIS) and multi-criteria decision analysis (MCDA) techniques. J. Geol. Soc. India. 89: 453–459. DOI: 10.1007/s12594-017-0628-5.
  3. Brindha, K. and Schneider, M. 2019. Impact of urbanization on groundwater quality (chapter 3). In GIS and geostatistical techniques for groundwater science. Ed Senapathi, V., Viswanathan, P.M. and Chung, S.Y. pp 179–196. DOI: 10.1016/B978-0-12-815413-7.00013-4.
  4. Ghosh, S. and Jha, M.K. 2023. Hydrogeochemical characterization of groundwater and critical assessment of its quality in a coastal basin. Env. Develop. Sustain., 27(1): 765-830. DOI: 10.1007/s10668-023-03874-x.
  5. Deshmukh, K.K. and Aher, S.P. 2016. Assessment of the impact of municipal solid waste on groundwater quality near the Sangamner city using GIS approach. Water Resour. Manage., 30: 2425–2443.
  6. Khan, R. and Jhariya, D.C. 2018. Hydrogeoche-mistry and groundwater quality assessment for drinking and irrigation purpose of Raipur city, Chhattisgarh. J. Geol. Soc. India. 91: 475–482. DOI: 10.1007/s12594-018-0881-2.
  7. Raju, A. and Singh, A. 2017. Assessment of groundwater quality and mapping human health risk in central Ganga alluvial plain, northern India. Env. Processes. 4(2): 375–397. DOI: 10.1007/s40710-017-0232-0.
  8. Kazemi, G.A. and Mohammadi, A. 2012. Significance of hydrogeochemical analysis in the management of groundwater resources: A case study in northeastern Iran. In Hydrogeology – A global perspective. IntechOpen. DOI: 10.5772/39214.
  9. Marghade, D., Malpe, D. B. and Zade, A. B. 2011. Geochemical characterization of groundwater from northeastern part of Nagpur urban, central India. Env. Earth Sci., 62: 1419–1430. DOI: 10.1007/s12665-010-0627-y.
  10. Tiwari, A.K., Singh, A.K., Singh, A.K. and Singh, M.P. 2017. Hydrogeochemical analysis and evaluation of surface water quality of Pratapgarh district, Uttar Pradesh, India. Appl. Water Sci., 7: 1609 –1623. DOI: 10.1007/s13201-015-0313-z.
  11. Patel, P., Raju, N.J., Reddy, B.C.S.R., Suresh, U., Sankar, D.B. and Reddy, T.V.K. 2018. Heavy metal contamination in river water and sediments of the Swarnamukhi river basin, India: Risk assessment and environmental implications. Env. Geochem. Health. 40: 609–623. DOI: 10.1007/s10653-017-0006-7.
  12. Das, S. and Nag, S.K. 2017. Application of multivariate statistical analysis concepts for assessment of hydrogeochemistry of groundwater—A study in Suri I and II blocks of Birbhum district, West Bengal, India. Appl. Water Sci., 7: 873–888.
  13. Udayalaxmi, G., Ramadass, G. and Himabindu, D. 2009. Geochemical evaluation of groundwater quality in Katedhan IDA and surrounding areas, Hydera-bad, A.P., India. J. Env. Informatics. 14(2): 100-109. DOI: 10.3808/jei.200900158.
  14. Jhariya, D.C., Khan, R. and Thakur, G.S. 2016. Impact of mining activity on water resource: An overview study. National seminar on recent practices and innovations in mining industry (RPIMI 2016), Raipur, India. Proceedings, pp 19–20.
  15. Shams, M.Y., El-Shewey, A.M., El-Kenawy, E.S.M., Ibrahim, A., Talaat, F.M. and Tarek, Z. 2024. Water quality prediction using machine learning models based on grid search method. Multimedia Tools Appl., 83(12): 35307–35334.
  16. APHA. 2012. Standard methods for the examination of water and wastewater (vol 10). American Public Health Association, Washington D.C.
  17. Li, Y., Khan, M. Y. A., Jiang, Y., Tian, F., Liao, W., Fu, S. and He, C. 2019. CART and PSO+KNN algo-rithms to estimate the impact of water level change on water quality in Poyang lake, China. Arabian J. Geosci., 12: 1–12. DOI: 10.1007/s12517-019-43 50-z.
  18. Modaresi, F. and Araghinejad, S. 2014. A comparative assessment of support vector machines, probabilistic neural networks and K-nearest neighbour algorithms for water quality classification. Water Resour. Manage., 28: 4095–4111. DOI: 10.1007/s11269-014-0730-z.
  19. Dolma, K., Rishi, M.S. and Herojeet, R. 2015. Base-line study of drinking water quality: A case of Leh town, Ladakh (J and K), India. Hydrol. Curr. Res., 6(1): 1000198. DOI: 10.4172/2157-7587.100019 8.
  20. Ebrahimijahan, A., Ordokhani, Y. and Razzaghi, M. 2024. Development of integrated radial basis function Kriging interpolation for linear and non-linear parabolic integro-differential equations. Eng. Analysis Boundary Elements. 164: 105680. DOI: 10.10 16/j.enganabound.2024.04.019.
  21. Fisher, R.A. 1915. Frequency distribution of the values of the correlation coefficient in samples from an indefinitely large population. Biometrika. 10(4): 507–521.
  22. Liang, S., Ning, Y., Li, H., Wang, L., Mei, Z., Ma, Y. and Zhao, G. 2015. Feature selection and predictors of falls with foot force sensors using KNN-based algorithms. Sensors. 15(11): 29393–29407. DOI: 10.3390/s151129393.
  23. Sakaa, B., Elbeltagi, A., Boudibi, S., Chaffaï, H., Islam, A.R.M.T., Kulimushi, L.C., Choudhari, P., Hani, A., Brouziyne, Y. and Wong, Y.J. 2022. Water quality index modelling using random forest and improved SMO algorithm for support vector machine in Saf-Saf river basin. Env. Sci. Poll. Res., 29(32): 48491–48508. DOI: 10.1007/s11356-022-18644-x.
  24. Nababan, A.A., Khairi, M. and Harahap, B.S. 2022. Implementation of K-nearest neighbours (KNN) algo-rithm in classification of data water quality. J. Mantik. 6(1): 30–35.
  25. Zupan, J. 1994. Introduction to artificial neural network (ANN) methods: What they are and how to use them. Acta Chimica Slovenica. 41(3): 327-352.
  26. Najafzadeh, M. and Niazmardi, S. 2021. A novel multiple-kernel support vector regression algorithm for estimation of water quality parameters. Natural Resour. Res., 30(5): 3761–3775. DOI: 10.1007/s11053-021-09895-5.
  27. Pratama, F.R.A. and Oktora, S.I. 2023. Synthetic minority over-sampling technique (SMOTE) for handling imbalanced data in poverty classification. Statistical J. IAOS. 39(1): 233–239. DOI: 10.3233/SJI-220080.
  28. Chai, T. and Draxler, R.R. 2014. Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature. Geosci. Model Develop. Discussions. 7(1): 1525–1534. DOI: 10.5194/gmd-7-1247-2014.
  29. IS. 10500. 2012. Drinking water- Specification. Bureau of Indian Standards, New Delhi.