Abstract

Assessing groundwater quality is important in India due to significant variations influenced by geographical, climatic, and anthropogenic factors. The ground water quality index (GWQI) serves as an effective tool for evaluating the suitability of groundwater for drinking purposes. This study assesses groundwater quality across 51 locations in Coimbatore district, Tamil Nadu, India, using key parameters such as iron, fluoride, total dissolved solids, pH, turbidity, conductivity, and hardness. GWQI prediction was carried out using six different machine learning (ML) algorithms, with performance optimization achieved through random search cross-validation and stratified k-fold cross-validation. To enhance interpretability, local interpretable model-agnostic explanations (LIME) and shapley additive explanations (SHAP) were employed, providing insights into the contribution of individual features to GWQI predictions. These techniques enable instance-specific explanations, thereby improving model transparency and trustworthiness. The experimental results show that the proposed GWQI model attains a high R² score of 0.999 and a minimal RMSE of 0.003, outperforming all other ML models with superior prediction accuracy. This ML-driven GWQI assessment enhances reliability and precision, ensuring a more efficient evaluation of groundwater suitability for human consumption.

Keywords

Groundwater quality index, Machine learning, Shapley additive explanations, Local interpretable model-agnostic explanations, Water quality assessment.

Cite this article

Rani UV, Velumani, Selvi, Vidhya, Ramya,. Enhancing groundwater quality assessment with explainable machine learning. International Journal of Advanced Technology and Engineering Exploration. 2025; 12(130):1379-1395

References

[1] Sharma SK, Sharma V, Mohamed HI, Khan H, Ahmed SS. Supervise the physicochemical quality of ground water using soft computing technique. Environmental Technology. 2024; 45(11):2099-107.

[2] Schwartz FW, Zhang H. Fundamentals of ground water. Environ. Geol. 2004; 45:1037-8.

[3] Anand MV, Sohitha C, Saraswathi GN, Lavanya GV. Water quality prediction using CNN. In journal of physics: conference series 2023 (pp. 1-8). IOP Publishing.

[4] Madni HA, Umer M, Ishaq A, Abuzinadah N, Saidani O, Alsubai S, et al. Water-quality prediction based on H2O autoML and explainable AI techniques. Water. 2023; 15(3):1-17.

[5] Bin JS, Abdullah S, Jaafar J, Othman Z, Baki A, Hamzah N. Characteristic and performance of polysulphone-polyethylene glycol synthetic hybrid membrane in water purification system. International Journal of Advanced Technology and Engineering Exploration. 2021; 8(76):484-95.

[6] Ferdous MN, Hoque M, Popy S, Hossain MI, Munna RI. Assessment of the groundwater quality of the Jessore municipality by using weighted arithmetic water quality index. Next Research. 2025; 2(1):100187.

[7] Sathiyamurthi S, Youssef YM, Gobi R, Ravi A, Alarifi N, Sivasakthi M, et al. Optimal land selection for agricultural purposes using hybrid geographic information system–fuzzy analytic hierarchy process–geostatistical approach in Attur taluk, India: synergies and trade-offs among sustainable development goals. Sustainability. 2025; 17(3):1-29.

[8] Sundararajan SC, Shankar YB, Selvam SP, Manogaran N, Seerangan K, Natesan D, et al. IoT-based prediction model for aquaponic fish pond water quality using multiscale feature fusion with convolutional autoencoder and GRU networks. Scientific Reports. 2025; 15(1):1-21.

[9] Renugadevi R. An optimal method of assessing the quality of water using integrated AI and blockchain methodology. In smart water technology for sustainable management in modern cities 2025 (pp. 261-84). IGI Global Scientific Publishing.

[10] Ejaz U, Khan SM, Jehangir S, Ahmad Z, Abdullah A, Iqbal M, et al. Monitoring the industrial waste polluted stream-integrated analytics and machine learning for water quality index assessment. Journal of Cleaner Production. 2024; 450:141877.

[11] Kundu S, Datta P, Pal P, Ghosh K, Das A, Das BK. Unveiling the hidden connections: using explainable artificial intelligence to assess water quality criteria in nine giant rivers. Journal of Cleaner Production. 2025; 492:144861.

[12] Maußner C, Oberascher M, Autengruber A, Kahl A, Sitzenfrei R. Explainable artificial intelligence for reliable water demand forecasting to increase trust in predictions. Water Research. 2025; 268:1-12.

[13] Pérez-beltrán CH, Robles AD, Rodríguez NA, Ortega-gavilán F, Jiménez-carvelo AM. Artificial intelligence and water quality: from drinking water to wastewater. TrAC Trends in Analytical Chemistry. 2024; 172:117597.

[14] William P, Oyebode OJ, Ramu G, Gupta M, Bordoloi D, Shrivastava A. Artificial intelligence based models to support water quality prediction using machine learning approach. In international conference on circuit power and computing technologies (ICCPCT) 2023 (pp. 1496-501). IEEE.

[15] Zheng Y, Wei D, Gan J, Zou L, Zhu R, Zhang Y. Hydrochemical insights, water quality, and human health risk assessment of groundwater in a coastal area of southeastern China. Environmental Monitoring and Assessment. 2024; 196(10):959.

[16] Cui H, Tao Y, Li J, Zhang J, Xiao H, Milne R. Predicting and analyzing the algal population dynamics of a grass-type lake with explainable machine learning. Journal of Environmental Management. 2024; 354:120394.

[17] Talukdar S, Bera S, Naikoo MW, Ramana GV, Mallik S, Kumar PA, et al. Optimisation and interpretation of machine and deep learning models for improved water quality management in Lake Loktak. Journal of Environmental Management. 2024; 351:119866.

[18] Shin H, Byun Y, Kang S, Shim H, Oak S, Ryu Y, et al. Development of water quality prediction model for water treatment plant using artificial intelligence algorithms. Environmental Engineering Research. 2024; 29(2):1-13.

[19] Aldrees A, Khan M, Taha AT, Ali M. Evaluation of water quality indexes with novel machine learning and shapley additive ex planation (SHAP) approaches. Journal of Water Process Engineering. 2024; 58:104789.

[20] Mohseni U, Pande CB, Pal SC, Alshehri F. Prediction of weighted arithmetic water quality index for urban water quality using ensemble machine learning model. Chemosphere. 2024; 352:141393.

[21] Nourani V, Khajeh EB, Sharghi E. Aquifer: a comparative study of 2003. Climate Change and Water Resources in Mediterranean Countries: Climate Change and Water Crisis. 2024:191.

[22] El-rawy M, Wahba M, Fathi H, Alshehri F, Abdalla F, El ARM. Assessment of groundwater quality in arid regions utilizing principal component analysis, GIS, and machine learning techniques. Marine Pollution Bulletin. 2024; 205:116645.

[23] Krishnamoorthy L, Lakshmanan VR. Groundwater quality assessment using machine learning models: a comprehensive study on the industrial corridor of a semi-arid region. Environmental Science and Pollution Research. 2024:1-24.

[24] Döndü M, Özdemir N, Demirak A, Doğan HM, Dincer NG, Keskin F. Seasonal assessment of the impact of fresh waters feeding the bay of Gökova with water quality index (WQI) and comprehensive pollution index (CPI). Environmental Forensics. 2024; 25(1-2):68-80.

[25] Achu AL, Aju CD, Raicy MC, Bhadran A, George A, Surendran U, et al. Improved flood risk assessment using multi-model ensemble machine-learning techniques in a tropical river basin of Southern India. Physical Geography. 2025; 46(2):127-55.

[26] Karunanidhi D, Raj MR, Roy PD, Subramani T. Integrated machine learning based groundwater quality prediction through groundwater quality index for drinking purposes in a semi-arid river basin of south India. Environmental Geochemistry and Health. 2025; 47(4):119.

[27] Uddin MG, Nash S, Rahman A, Olbert AI. Performance analysis of the water quality index model for predicting water state using machine learning techniques. Process Safety and Environmental Protection. 2023; 169:808-28.

[28] Juna A, Umer M, Sadiq S, Karamti H, Eshmawi AA, Mohamed A, et al. Water quality prediction using KNN imputer and multilayer perceptron. Water. 2022; 14(17):1-19.

[29] Mangalathu S, Hwang SH, Jeon JS. Failure mode and effects analysis of RC members based on machine-learning-based shapley additive explanations (SHAP) approach. Engineering Structures. 2020; 219:110927.

[30] Knapič S, Malhi A, Saluja R, Främling K. Explainable artificial intelligence for human decision support system in the medical domain. Machine Learning and Knowledge Extraction. 2021; 3(3):740-70.

[31] Toleva B, Atanasov I, Ivanov I, Hooper V. An effective methodology for diabetes prediction in the case of class imbalance. Bioengineering. 2025; 12(1):1-17.

[32] Nagappan G, Rani VU. Disruptive technologies for sustainable development. CRC Press; 2024.

[33] Wang S, Peng H, Liang S. Prediction of estuarine water quality using interpretable machine learning approach. Journal of Hydrology. 2022; 605:127320.