Groundwater quality prediction and risk assessment in Kerala, India: A machine-learning approach

Despite its critical importance for health, agriculture, and the economy, and its key role in supporting climate change adaptation, groundwater quality remains vulnerable to contamination and is often neglected until significant deterioration. The groundwater resources of Kerala, one of the southernmost states of India, are under escalating stress and scarcity, despite a high well density with 62% of the population relying on groundwater from approximately 6.5 million open wells. This study investigates the detailed hydrogeochemistry and predicts groundwater quality zones of the state using machine-learning techniques viz, extreme gradient boosting (XGBoost), support vector regression (SVR), artificial neural network (ANN) and random forest (RF) regression. The hydrogeochemical analysis reveals varying groundwater quality across the state. Among the different machine learning models, RF shows higher goodness of fit (R²: 0.922) with minimal prediction error (root mean square error: 6.29 and mean absolute error: 3.12). The predicted groundwater quality was validated using the spatially distributed stiff diagrams, visually representing water composition trends of each well. The very good, good, moderate and poor groundwater quality zones occupy 31.7%, 40.4%, 20.4%, and 7.4% of the state aligning accurately with the groundwater quality scenario of the state. Additionally, groundwater drinking risk assessment was conducted, considering that 7.4% of the state experiences poor-quality groundwater. Integrating groundwater quality maps with population data, the study assessed potential health risks due to consuming untreated water. Nearly 0.59 million people across 252 local self-government bodies (LSGs) are susceptible to consuming poor quality groundwater, which may pose potential health risks. This observation provides valuable insights for sustainable groundwater management and public health safeguarding and the findings of the present study are useful for achieving sustainable development goal (SGD) 6 (clean water and sanitation) and long-term groundwater management in Kerala.