Groundwater quality assessment and health risk evaluation for schoolchildren in Mujibnagar, Bangladesh: safe consumption guidelines using artificial neural network modeling.

Groundwater is a vital source of drinking water in Bangladesh, with tubewells commonly used, particularly in schools. This study assessed the quality of tubewell water in the southwest region, focusing on iron (Fe), arsenic (As), pH, electrical conductivity (EC), and total dissolved solids (TDS). Using artificial neural network (ANN) modeling, daily safe water intake limits for children were estimated based on Fe and As levels. A total of 75 school-based water samples were collected. Fe and As were measured using a Hanna Iron Checker and Hach Arsenic Test Kit. Findings showed that 68% and 48% of samples exceeded WHO and USEPA limits for Fe and As, respectively. In contrast, only 32% and 26.7% of samples surpassed the Bangladesh Water Quality Standards (BDWS) for Fe and As, respectively. Spatial mapping identified Mahajanpur, Bagoan, and Dariapur as hotspots for contamination. TDS showed a strong positive correlation with conductivity (r = 0.92) and a moderate one with salinity (r = 0.7), indicating their interdependence. As and Fe had a weak positive correlation (r = 0.22). PC1 and PC2 explained 56.74% of variance, with Fe and As weakly correlated in PC1 but negatively loaded in PC2, suggesting distinct behaviours influenced by TDS, conductivity, and salinity. Further, Linear regression showed Fe (r = -0.34) and As (r = -0.71) decreased with depth. High health risks were identified for Fe in Mahajanpur and As in Baguan and Dariapur. ANN and Decision Tree Regression models showed 87% accuracy in estimating safe water intake, highlighting Monakhali Union as the most vulnerable area. To avoid health impacts in children, safe consumption levels in Baguan and Monakhali were notably low at 0.59 L/day and 0.39 L/day, respectively. These findings underscore the urgent need for regular monitoring and limiting tubewell water consumption by schoolchildren in the region.