10.57647/j.jap.2025.0901.13

Groundwater Quality Assessment and Refining Vulnerability Index through Machine Learning and Pollution Index Integration: A Case Study of the Koohpayeh Plain in Central Iran.

PDF
  • Navideh Najafpour*1,
  • Shahrokh Soltaninia2,
  1. Department of Civil Engineering, Lecturer of Water Science Engineering, Khomeynishahr Branch, , Islamic Azad University, Esfahan, Iran
  2. Department of Civil Engineering, Faculty of Civil Engineering, Khomeynishahr Branch, , Islamic Azad University, Esfahan, Iran

Received: 2025-05-13

Revised: 2025-05-24

Accepted: 2025-06-14

Published in Issue 2025-07-01

Copyright (c) 2025 Navideh Najafpour, Shahrokh Soltaninia (Author)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Najafpour, N., & Soltaninia, S. (2025). Groundwater Quality Assessment and Refining Vulnerability Index through Machine Learning and Pollution Index Integration: A Case Study of the Koohpayeh Plain in Central Iran. Anthropogenic Pollution, 9(1). https://doi.org/10.57647/j.jap.2025.0901.13
Crossref
Scopus
Google Scholar
Europe PMC

PDF views: 43

Abstract

Groundwater contamination is a critical issue, especially in arid regions where it serves as the main water supply. This study emphasizes the importance of integrating traditional methods with machine learning techniques to enhance groundwater vulnerability assessments in the Koohpayeh aquifer, central Iran. Groundwater quality was assessed using the Pollution Index of Groundwater (PIG) and Water Quality Index (WQI). WQI values ranged from less than 15 to 55, indicating poor water quality, particularly in central and southeastern regions, due to contaminants from agriculture and urban activities. The PIG index revealed severe pollution in 45% of the area, showing a strong correlation between high PIG and low WQI values. Machine learning methods, including Random Forest (RF), Gradient Boosting (GB), and Support Vector Regression (SVR), were used to refine the DRASTIC model. RF emerged as the most effective model, achieving an MSE of 0.05 and an R² of 0.89, outperforming GB, which had a slightly higher R² of 0.91 but a greater MSE of 0.08. A strong correlation between nitrate levels and the optimized vulnerability indices validated the improved DRASTIC model’s accuracy. The enhanced DRASTIC model provides a more reliable tool for identifying high-risk areas and developing targeted groundwater management strategies. This study underscores the value of combining traditional assessments with machine learning to improve groundwater quality monitoring and protect public health. These findings can support decision-makers in prioritizing pollution control strategies, optimizing groundwater monitoring programs, and designing sustainable management plans in vulnerable arid and semi-arid regions.

Keywords

  • Water resource,
  • Data-driven approach,
  • ; Modified DRASTIC,
  • Spatial analysis,
  • Water quality index
PDF

References

  1. Al-Adamat RAN, Foster IDL, Baban SMJ (2003) Groundwater vulnerability and risk mapping for the Basaltic aquifer of the Azraq Basin of Jordan using GIS, remote sensing, and DRASTIC. Appl Geogr 23(4):303–324. https://doi.org/10.1016/j.apgeog.2003.08.007
  2. Alam A, Kumar A, Singh A (2024) A GIS approach for groundwater quality evaluation with entropy method and fluoride exposure with health risk assessment. Environ Geochem Health 46(47):1–23. https://doi.org/10.1007/s10653-023-01822-2
  3. Aller L, Bennett T, Lehr JH, Petty RJ, Hackett G (1987) A standardized system for evaluating groundwater pollution potential using hydrogeologic settings. EPA/600/2-87/035, U.S. Environmental Protection Agency, Washington, D.C.
  4. Allouche N, Maanan M, Gontara M, Rollo N, Jmal I (2017) A global risk approach to assessing groundwater vulnerability. J Environ Model Softw 88:168. https://doi.org/10.1016/j.envsoft.2016.11.023
  5. Amanah H, Purwanto S, Hadihardaja IK (2019) Application of cluster analysis and principal component analysis for assessment of groundwater quality, A study in Semarang, Central Java, Indonesia. Earth Environ Sci Conf Ser 248:012009. https://doi.org/10.1088/1755-1315/248/1/012063
  6. APHA (2012) Standard methods for the examination of water and wastewater, 22nd edn. American Public Health Association, Washington, D.C.
  7. Asghari Moghadam A, Fijani E, Nadiri A (2015) Optimization of DRASTIC Model by Artificial Intelligence for Groundwater Vulnerability Assessment in Maragheh-Bonab Plain, Optimization of DRASTIC Model by Artificial Intelligence for Groundwater Vulnerability Assessment in Maragheh-Bonab Plain, Scientific Quarterly Journal of Geoscience, 152:154–166. https://doi.org/10.22071/gsj.2015.43279
  8. Baba A, Tayfur G (2011) Groundwater contamination and its effect on health in Turkey. Environ Monit Assess 83(1):77–86. https://doi.org/10.1007/s10661-011-1907-z.
  9. Babiker IS, Mohamed MAA, Hiyama T (2007) Assessing groundwater quality using GIS. Water Resour Manag 11:669. https://doi.org/10.1007/s11269-006-9059-6
  10. Baghapour MA, Talebbeydokhti N, Tabatabaee SHR, Fadaei Nobandegani a (2014) Assessment of groundwater nitrate pollution and determination of groundwater protection zones using DRASTIC and Composite DRASTIC (CD) models: The case of Shiraz unconfined aquifer. J Health Sci Surveill Syst 2(2):65.
  11. Barzegar R, Razzagh S, Quilty J, Adamowski J, Kheyrollah Pour H, Booij MJ (2021) Improving GALDIT-based groundwater vulnerability predictive mapping using coupled resampling algorithms and machine learning models. J Hydrol 598:126370. https://doi.org/10.1016/j.jhydrol.2021.126370
  12. Breiman L (2001) Random forests. Mach Learn 45(1):5–32. DOI: https://doi.org/10.1023/A:1010933404324
  13. Chitsazan N, Nadiri AA, Tsai FTC (2015) Prediction and structural uncertainty analyses of artificial neural networks using hierarchical Bayesian model averaging. J Hydrol 528:52–62. https://doi.org/10.1016/j.jhydrol.2015.06.026
  14. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297. https://doi.org/10.1007/BF00994018
  15. Davoodi Memar Otagvar, L., Fataei, E., Tajiabadi, M., & Naeimi, B. (2024). Spatio-temporal assessment of changes in groundwater quality in Qazvin Plain. Journal of Range and Watershed Managment, 77(3), 353-369. DOI:10.22059/jrwm.2024.370962.1744
  16. Elzain EH, Chung SY, Venkatramanan S, Selvam S, Ahmed HA, Seo KK (2023) Novel machine learning algorithms to predict the groundwater vulnerability index to nitrate pollution at two levels of modeling. Chemosphere 314:137671. https://doi.org/10.1016/j.chemosphere.2022.137671
  17. EPA (2007) Method 7000B: Flame atomic absorption spectrophotometry. U.S. Environmental Protection Agency, Washington, D.C.
  18. Farhadi, H., Fataei, E., Kharrat Sadeghi, M. (2020), The relationship between nitrate distribution in groundwater and agricultural landuse (case study: Ardabil plain, Iran), Anthropogenic Pollution, 4(1):50-6, DOI:10.22034/ap.2020.1885788.1059
  19. Friedman JH (2001) Greedy function approximation: A gradient boosting machine. Ann Stat 29(5):1189–1232. https://doi.org/10.1214/AOS/113203451.
  20. Hosseini F, Malekian A, Choubin B, Rahmati O, Cipullo S, Coulon F, Pradhan B (2018) A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Sci Total Environ 644:954–962. https://doi.org/10.1016/j.scitotenv.2018.07.017.
  21. Hosseinifard SH, Mirzaei Aminiyan M (2015) Hydrochemical characterization of groundwater quality for drinking and agricultural purposes: A case study in Rafsanjan Plain, Iran. J Water Qual Explor Health 7(4):531. https://doi.org/10.1007/s12403-015-0173-0.
  22. Hassanalipour Y, Mostafazadeh R, Esmali-Ouri A, Ahmadi M, Imani R (2022) Evaluation of the effects of urban development on the quantity and quality of surface and groundwater in Ardabil plain. Journal of Environmental Science Studies, 7(3): 5374-5385. https://doi.org/10.22034/jess.2022.343220.1792.
  23. Ijlil S, Essahlaoui A, Mohajane M, Essahlaoui N, Mili EM, Rompaey AV (2022) Machine learning algorithms for modeling and mapping of groundwater pollution risk: A study to reach water security and sustainable development (SDG) goals in a Mediterranean aquifer system. J Remote Sens 14(10):2379. https://doi.org/10.3390/rs14102379.
  24. Isfahan Regional Water Authority. (2021). Water Balance Report of Koohpayeh Plain. Ministry of Energy, Iran. [In Persian]
  25. Jagannathan U, Venkatesh A, Sudharsanam A, Muniraj K (2015) Assessment of groundwater quality using GIS and statistical approaches. Asian J Earth Sci 8(4):97–113. https://doi.org/10.3923/ajes.2015.97.113.
  26. Jovanovic NZ, Adams S, Thomas A, Fey M, Beekman HE, Campbell R, Saayman I, Conrad J (2006) Improved DRASTIC method for assessment of groundwater vulnerability to generic aqueous-phase contaminants. WIT Trans Ecol Environ 92:393. https://doi.org/102495/wm060421.
  27. Khan Q, Liaqat MU, Mohamed MM (2022) A comparative assessment of modeling groundwater vulnerability using the DRASTIC method from GIS and a novel classification method using machine learning classifiers. Geocarto International 37: 5832–5850. https://doi.org/10.1080/10106049.2022.2049861
  28. Khemiri S, Khnissi A, Ben Alaya M, Saidi S, Zargouni F (2013) Using GIS for the comparison of intrinsic parametric methods assessment of groundwater vulnerability to pollution in scenarios of semi-arid climate, the case of Foussana groundwater in the central of Tunisia. Journal of Water Resources and Protection 5: 835–847. https://doi.org/10.4236/jwarp.2013.57085
  29. Khemmoudj K, Bendadouche H, Merabet S (2014) Assessment of the vulnerability of an aquifer by DRASTIC and SINTACS methods: Aquifer of Bazer–Geult Zerga area (northeast Algeria). Journal of Environmental Research and Management 5(9): 0169.
  30. Krishan G, Singh S, Khanna A (2016) Water quality index of groundwater in Haridwar district, Uttarakhand. Journal of Water Energy International 8(2): 54–60.
  31. Kulisz M, Kujawska J, Przysucha B, Cel W (2021) Forecasting water quality index in groundwater using artificial neural network. Energies 14(18): 5875. https://doi.org/10.3390/en14185875
  32. Lee S, Hyun Y, Lee S, Lee MJ (2020) Groundwater potential mapping using remote sensing and GIS-based machine learning techniques. Remote Sensing 12(8): 1200. https://doi.org/10.3390/rs12081200
  33. Li PY, Qian H, Wu JH (2010) Groundwater quality assessment based on improved water quality index in Pengyang County, Ningxia, Northwest China. Journal of Chemistry 7(S1): S209.
  34. Motlagh ZK, Derakhshani R, Sayadi MH (2023) Groundwater vulnerability assessment in central Iran: Integration of GIS-based DRASTIC model and a machine learning approach. Groundwater Sustainable Development 23: 101037. https://doi.org/10.1016/j.gsd.2023.101037
  35. Mostafazadeh R, Malaekah M, Hama P (2024) Quantitative assessment of groundwater resources depletion in Herat area, Afghanistan', Advances in Civil Engineering and Environmental Science, 1(1): 38-47. https://doi.org/10.22034/acees.2024.457658.1003
  36. Najafpour N, Torabi Poode H, Yoonesi H (2020) Evaluation of groundwater quantity and quality on aquifer pollutant (Case study: Lenjanat Plain, Isfahan). Journal of Environmental Studies 11(21): 233–248. https://doi.org/ 20.1001.1.20089597.1399.11.21.20.9
  37. Najafpour N, Vahdatpour N, Aghababaei E (2024) Evaluating the capability of artificial intelligence in predicting the amount of electrical conductivity and nitrate in underground water resources (a case study of artificial neural methods ANN and ANFIS). Journal of Quality Engineering and Management 13(2): 207–230. https://doi.org/10.48313/jqem.2023.192560
  38. Nas B (2009) Geostatistical approach to assessment of spatial distribution of groundwater quality. Journal of Environmental 18(4): 1073.
  39. Nasiri Khiavi A, Mostafazadeh R, Adhami M. Groundwater quality modeling and determining critical points: a comparison of machine learning to Best-Worst Method. Environ Sci Pollut Res Int. 2023 Nov;30(54):115758-115775. https://doi.org/10.1007/s11356-023-30530-8.
  40. Panagopoulos G, Antonakos A, Lambrakis N (2005) Optimization of the DRASTIC model for groundwater vulnerability assessment by the use of simple statistical methods and GIS. Hydrogeology Journal 13(3): 922–933. https://doi.org/10.1007/s10040-004-0394-7.
  41. Ram A, Tiwari SK, Pandey HK, et al. (2021) Groundwater quality assessment using water quality index (WQI) under the GIS framework. Applied Water Science 11(46). https://doi.org/10.1007/S13201-021-01376-7.
  42. Shihab AS, Hassan ZA (2006) Classification of groundwater quality in Mosul, Iraq, using cluster analysis. Environmental Monitoring and Assessment 120(1–3): 179–196. DOI:10.1007/s10661-005-9050-5.
  43. Smola AJ, Schölkopf B (2004) A tutorial on support vector regression. Statistics and Computing 14(3): 199–222. https://doi.org/10.1023/B:STCO.0000035301.49549.88.
  44. Soper DS (2006) Mapping groundwater vulnerability using the DRASTIC index: A spatial approach integrating GIS. Journal of Hydrology 333(1–2): 234–245. https://doi.org/10.1016/j.jhydrol.2006.08.001.
  45. Stigter TY, Ribeiro L, Carvalho Dill AMM (2006) Application of a groundwater quality index as an assessment and communication tool in agro-environmental policies: Two Portuguese case studies. Journal of Hydrology 327(3–4): 578. https://doi.org/10.1016/j.jhydrol.2005.12.001.
  46. Stocklin J (1968) Structural history and tectonic of Iran: A review. AAPG Bulletin 52(7): 1229–1258. https://doi.org/10.1306/5D25C4E3-16C1-11D7-8645000102C1865D.
  47. Subba Rao N (2012) PIG: A numerical index for dissemination of groundwater contamination zones. Hydrological Processes 26: 3344–3350. https://doi.org/10.1002/hyp.8456.
  48. Subbarayan S, Thiyagarajan S, Karuppannan S, Panneerselvam B (2024) Enhancing groundwater vulnerability assessment: Comparative study of three machine learning models and five classification schemes for Cuddalore district. Environmental Research 117769. https://doi.org/10.1016/j.envres.2023.117769.
  49. Taghizadeh Mehrjardi R, Akbarzadeh S, Mahmoodi Sh, Heidari A, Sarmadian F (2008) Application of geostatistical methods for mapping groundwater quality in Azarbayjan Province, Iran. American Eurasian Journal of Agriculture and Environmental Science 3(5): 726. https://doi.org/‎ 20.1001.1.20089554.1387.2.5.7.4
  50. Tayfur G, Nadiri AA, Asghari Moghaddam A (2014) Supervised intelligent committee machine method for hydraulic conductivity estimation. Water Resources Management 28(4): 1173–1184. https://doi.org/10.1007/S11269-014-0553-y.
  51. 51. Ting KM, Witten IH (1999) Issues in stacked generalization. Journal of Artificial Intelligence Research 10: 271–289. https://doi.org/10.1613/jair.594.
  52. Wang C, Wang X, Zhang G, Zhang F, Li J, Chen S, Sauvage S, Sánchez-Pérez J, Han Y, Liu J (2023) Identification of critical effect factors for prediction of spatial and interannual variability of shallow groundwater nitrate in agricultural areas. Science of the Total Environment 891: 164342. https://doi.org/10.1016/j.scitotenv.2023.164342.
  53. Wolpert DH (1992) Stacked generalization. Neural Networks 5(2): 241–259. https://doi.org/10.1016/S0893-6080(05)80023-1.
  54. World Health Organization (WHO) (1998) Guidelines for drinking water quality, 2nd Ed., WHO, Geneva, Switzerland.