Assessing water quality is essential for acquiring a better understanding of the importance of water in human society. In this study, the quality of groundwater resources in Jiroft city, Iran, using artificial intelligence methods to estimate the groundwater quality index (GWQI) was evaluated. The analysis of hydrochemical parameters, including arsenic (As), fluoride (F), nitrate (NO₃), and nitrite (NO₂), in 408 samples revealed that concentrations of F, NO₃, and NO₂ were below the WHO standard threshold, but levels of As exceeded the permissible value. The random forest model with the highest accuracy (R² = 0.986) was the best prediction model, while logistic regression (R² = 0.98), decision tree (R² = 0.979), K-nearest neighbor (R² = 0.968), artificial neural network (R² = 0.955), and support vector machine (R² = 0.928) predicted GWQI with lower accuracy. The non-carcinogenic risk assessment revealed that children had the highest hazard quotient for oral and dermal intake, with values ranging from 0.47 to 13.53 for oral intake and 0.001 to 0.05 for dermal intake. The excess lifetime cancer risk of arsenic for children, adult females, and males was found to be from 2.5 × 10^–4 to 7.2 × 10^–3, 1.2 × 10^–4 to 3.6 × 10^–3, and 4.3 × 10^–5 to 1.2 × 10^–3, respectively. This study suggests that any effort to reduce the arsenic levels in the Jiroft population should take into account the health hazards associated with exposure to arsenic through drinking water.

评估水质对于更好地了解水在人类社会中的重要性至关重要。在这项研究中，使用人工智能方法估计地下水质量指数 （GWQI） 评估了伊朗吉罗夫特市的地下水资源质量。对 408 个样品中的水化学参数，包括砷 （As）、氟化物 （F）、硝酸盐 （NO₃） 和亚硝酸盐 （NO₂））的分析表明，F、NO₃ 和 NO₂ 的浓度低于 WHO 标准阈值，但 As 的水平超过允许值。准确率最高的随机森林模型 （R² = 0.986） 是最好的预测模型，而逻辑回归 （R² = 0.98）、决策树 （R² = 0.979）、K 最近邻 （R² = 0.968）、人工神经网络 （R² = 0.955） 和支持向量机 （R²= 0.928） 预测 GWQI 的准确率较低。非致癌风险评估显示，儿童经口和皮肤摄入的危险商最高，经口摄入为 0.47 至 13.53，皮肤摄入量为 0.001 至 0.05。发现儿童、成年女性和男性的砷超额终生癌症风险分别为 2.5 × ^10-4 至 7.2 × ^10-3、1.2 × ^10-4 至 3.6 × ^10-3，以及 4.3 × ^10-5 至 1.2 ×至 ^10-3。这项研究表明，任何降低 Jiroft 人群砷含量的努力都应考虑与通过饮用水接触砷相关的健康危害。