Artificial Intelligence-Driven Integrated Assessment, Prediction, and Health Risk Analysis of Groundwater Quality in Solapur District, Maharashtra: A Multi-Model Ensemble and Shap EX-Plainability Framework
About this article
Keywords:
Artificial Intelligence; Deccan Basalt; Groundwater Quality; GSDA; Health Risk Index; Nitrate SHAP Explainability; Solapur District; Water QualityAbstract
Groundwater quality deterioration across the semi-arid Deccan Basalt terrain of Solapur District, Maharashtra poses an escalating crisis for over 4.3 million residents dependent on hard-rock aquifer systems. This study presents the most comprehensive Artificial Intelligence-based integrated framework for groundwater quality assessment, spatiotemporal prediction, and public health risk quantification yet conducted for this region. Leveraging a robust dataset of 534 observations from 89 GSDA-monitored wells across 11 talukas (2022–2024, bi-annual pre- and post-monsoon campaigns), we developed and validated a weighted stacking ensemble model combining Random Forest (RF), XGBoost, Deep Artificial Neural Network (ANN), and Long Short-Term Memory (LSTM) networks. The proposed ensemble achieves outstanding predictive performance: R²=0.967, RMSE=2.43 WQI units, MAE=1.92, and NSE=0.964 on a 30% holdout test set (n=160), outperforming all nine individual benchmark models and reducing RMSE by 73% versus Multiple Linear Regression. Water Quality Index analysis reveals that Akkalkot, Mangalvedhe, and Sangola talukas are classified as "Very Poor" (WQI) and "Critical" on the Health Risk Index, with fluoride reaching 2.82 mg/L (188% of BIS Maximum Permissible Limit), nitrate 84.2 mg/L (187% of BIS MPL), and TDS 1382 mg/L — creating compound health risks including dental and skeletal fluorosis, methaemoglobinaemia, and enhanced arsenic bioavail-ability. SHAP (SHapley Additive exPlanations) analysis identifies fluoride (24.2%), nitrate (20.2%), and TDS (17.6%) as dominant WQI predictors. A composite Health Risk Index (HRI) framework targeting three contaminants (F⁻, NO₃⁻, As) identifies three talukas requiring urgent defluoridation and denitrification infrastructure. Seasonal post-monsoon WQI improvement of 5.6–7.1 WQI units (p < 0.001) is documented in Atal Bhujal Yojana recharge intervention zones. The framework is operationally integrated with GSDA Solapur Division's Early Warning Indicator (EWI) system and Maharashtra's District Water Security Plan, enabling real-time contamination alerts, remediation prioritisation, and climate-adaptive water governance.
References
[1] Ayoob, S., & Gupta, A.K. (2006). Fluoride in Drinking Water: A Review on the Status and Stress Effects. Critical Reviews in Envi-ronmental Sci-ence and Technology, 36(6), 433–487. https://doi.org/10.1080/10643380600678112.
[2] Bisht, D.C.S., Raju, N.J. & Agrawal, M. (2018). Random Forest-Based Water Quality Index Prediction in Himalayan River Basins. Environmental Monitoring and Assessment, 190(9), 547.
[3] Brown, R.M., McClelland, N.I., Deininger, R.A. & Tozer, R.G. (1972). A Water Quality Index — Do We Dare? Water and Sewage Works, 119, 339–343.
[4] CGWB. (2013). District Groundwater Information Booklet, Solapur District, Maharashtra. Central Ground Water Board, Central Region, Nagpur.
[5] Central Ground Water Board (CGWB). (2024). Annual Groundwater Quality Report 2024. Ministry of Jal Shakti, Government of India, New Delhi.
View more references (28)
[6] CGWB. (2024). Groundwater Quality Bulletin — Pre-Monsoon 2024. CGWB, Ministry of Jal Shakti, Faridabad.
[7] Deolankar, S.B. (1980). The Deccan Basalts of Maharashtra, India — Their Potential as Aquifers. Ground Water, 18(5), 434–437. https://doi.org/10.1111/j.1745-6584.1980.tb03416.x.
[8] Fewtrell, L. (2004). Drinking-Water Nitrate, Methaemoglobinaemia, and Global Burden of Disease: A Discussion. Environmental Health Perspec-tives, 112(14), 1371–1374. https://doi.org/10.1289/ehp.7216.
[9] Gibbs, R.J. (1970). Mechanisms Controlling World Water Chemistry. Science, 170(3962), 1088–1090. https://doi.org/10.1126/science.170.3962.1088.
[10] GSDA Solapur Division. (2023). Annual Groundwater Report — Solapur District 2022–23. Government of Maharashtra, Ground-water Survey and Development Agency.
[11] Haggerty, R., Sun, J., Yu, H. & Li, Y. (2023). Application of Machine Learning in Groundwater Quality Modelling — A Comprehensive Review. Water Research, 233, 119745. https://doi.org/10.1016/j.watres.2023.119745.
[12] Jose, A. & Yasala, S. (2024). Machine Learning-Based Ensemble Model for Groundwater Quality Prediction: A Case Study from Kanyakumari Dis-trict, Tamil Nadu. Water Practice and Technology, 19(6), 2364–2375. https://doi.org/10.2166/wpt.2024.139.
[13] Kulkarni, H., & Deolankar, S.B. (1995). Hydrogeology of Deccan Basalt Aquifers in India. Journal of the Geological Society of India, 45(6), 641–654.
[14] Kumar, A., Pande, C.B., Phaye, S. & Lal, K. (2024). Assessing Groundwater Quality for Drinking Using WQI and ML Techniques in Raipur Dis-trict, Central India. Environmental Earth Sciences, 83, 112.
[15] Lundberg, S.M. & Lee, S.I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems (NeurIPS), 30, 4765–4774.
[16] Mohseni, U., Pande, C.B., Pal, S.C. & Alshehri, F. (2024). Prediction of Weighted Arithmetic Water Quality Index Using Ensemble ML. Chemo-sphere, 352, 141393. https://doi.org/10.1016/j.chemosphere.2024.141393.
[17] Muktodeokar, S., Ahmed, M. & Birajdar, F. (2021). Hydrogeochemical Characterisation of Groundwater in Deccan Basalt Aquifers of Solapur Dis-trict. Acta Geophysica, 69(4), 1389–1408.
[18] Nash, J.E. & Sutcliffe, J.V. (1970). River Flow Forecasting Through Conceptual Models, Part I — A Discussion of Principles. Jour-nal of Hydrology, 10(3), 282–290. https://doi.org/10.1016/0022-1694(70)90255-6.
[19] National Water Mission, GOI. (2024). Atal Bhujal Yojana: Annual Progress Report 2023–24. Ministry of Jal Shakti, Government of India, New Del-hi.
[20] Shaikh, M.A., Herlekar, M.A. & Umrikar, B.N. (2019). Appraisal of Groundwater Artificial Recharge Zones in Basaltic Terrain of Upper Yerala River Basin, India. Journal of Geosciences Research, Special Volume 2, 29–36.
[21] Shaikh, M.A. & Birajdar, F. (2023). Enhancing Groundwater Awareness Through Exhibitions: A Case Study of Atal Bhujal Yojana in Solapur. In-ternational Journal of Novel Research and Development, 8(12), e81–e91.
[22] Shaikh, M.A. & Birajdar, F. (2024a). Groundwater Depletion in Agricultural Regions: Causes, Consequences, and Sustainable Management — A Case Study of Basaltic Terrain of Solapur District. EPRA International Journal of Multidisciplinary Research, 10(2), 237–242. https://doi.org/10.36713/epra15862.
[23] Shaikh, M.A. & Birajdar, F. (2024b). Artificial Intelligence in Groundwater Management: Innovations, Challenges, and Future Prospects. Internation-al Journal of Science and Research Archive, 11(1), 502–512. https://doi.org/10.30574/ijsra.2024.11.1.0105.
[24] Shaikh, M.A. & Birajdar, F. (2024c). Groundwater Exploration and Assessment in Arid and Semi-Arid Regions of Basaltic Terrain of Solapur: Les-sons Learned and Future Prospects. International Journal of Innovative Science and Research Technology, 9(4). https://doi.org/10.38124/ijisrt/IJISRT24APR2344.
[25] Shaikh, M.A. & Birajdar, F. (2024d). Ensuring Purity and Health: A Comprehensive Study of Water Quality Testing Labs in Solapur District for Community Well-being. International Journal of Innovative Science and Research Technology, 9(1), 271–281. https://doi.org/10.5281/zenodo.10622956
[26] Shaikh, M.A. & Birajdar, F. (2024e). Advancing Sustainable Water Management in Solapur Through Continuous Groundwater Monitoring with Pie-zometers and Automatic Water Level Recorders: Insights from the Atal Bhujal Yojana. International Journal of Research in Engineering, Science and Management, 7(3), 16–24.
[27] Shaikh, M.A. & Birajdar, F. (2024f). Groundwater and Public Health: Exploring the Connections and Challenges. International Journal for Innovative Science Research Trends and Innovation, 9(2), 1351–1361. https://doi.org/10.5281/zenodo.10730864
[28] Shaikh, M.A. & Birajdar, F. (2024g). Water Harvesting: Importance and Techniques for Mitigating Drought in Solapur District. International Journal of Research in Engineering, Science and Management, 7(2), 74–83. https://doi.org/10.5281/zenodo.10684207
[29] Shaikh, M.A. & Birajdar, F. (2024h). Harmony in Hydroinformatics: Integrating AI and IEC for Sustainable Groundwater Conservation in Solapur. International Journal of Science and Research Archive, 11(1), 2163–2175. https://doi.org/10.30574/ijsra.2024.11.1.0294.
[30] Smedley, P.L., & Kinniburgh, D.G. (2002). A Review of the Source, Behaviour and Distribution of Arsenic in Natural Waters. Ap-plied Geochemis-try, 17(5), 517–568. https://doi.org/10.1016/S0883-2927(02)00018-5.
[31] Vovk, V., Gammerman, A., & Shafer, G. (2005). Algorithmic Learning in a Random World. Springer, New York.
[32] World Health Organisation (WHO). (2022). Guidelines for Drinking-water Quality: Fourth Edition Incorporating the First and Second Addenda. WHO Press, Geneva.
[33] Zhu, M., Wang, J., Yang, X., Zhang, Y., Zhang, L., Ren, H., Wu, B., & Ye, L. (2022). A Review of the Application of Machine Learning in Water Quality Evaluation. Eco-Environment & Health, 1(2), 107–116. https://doi.org/10.1016/j.eehl.2022.06.001.