Atashi Yazdi Seyedeh Sofia, Motamedvaziri Baharak, Hosseini Seyed Zeynalabedin, Ahmadi Hassan
Department of Nature Engineering, Faculty of Natural Resources and Environment, Science and Research Branch, Islamic Azad University, Tehran, Iran.
Faculty of Natural Resources and Desert Studies, Yazd University, Yazd, Iran.
Environ Sci Pollut Res Int. 2023 Mar;30(14):39586-39604. doi: 10.1007/s11356-022-24810-y. Epub 2023 Jan 4.
Heuristic and statistical groundwater quality assessment models are efficient tools in the zoning of groundwater vulnerability to contamination. An important reciprocal methodology, yet neglected in Iran, was conducted to assess the performance of three groundwater vulnerability models, namely GODS, SI, and DRASTIC, and a data mining model for groundwater potential, maximum entropy (MaxEnt). For both the training and validation stages for the MaxEnt model, the Mahalanobis distance technique was adopted. The vulnerability rates obtained from the DRASTIC model with a coefficient of determination (R) value of 0.76 had a statistically significant correlation with nitrate concentrations in the 21 wells, compared to SI and GODS. The DRASTIC model can better reflect the vulnerability of groundwater resources to contamination. The impact of the vadose zone with an average effective weight of 33 is more important than other parameters, followed by depth than groundwater (D) (32.01), net recharge (R) (28.95), and the aquifer media (A) (18.1). These weights may not be changed. MaxEnt showed significant performance in both the training and validation stages with the respective area under the receiver operating characteristic curve (AUROC) values of 0.907 and 0.901. A reciprocal analysis between the vulnerability map in the superior model and the groundwater potential map derived from MaxEnt revealed that areas with high groundwater potential are still in safe state but require more attention as the top priority for amendment practices. In addition, approximately 8.7% of the entire study area has a high vulnerability to contamination, which requires immediate pragmatic actions.
启发式和统计地下水质量评估模型是划分地下水污染脆弱性的有效工具。在伊朗被忽视但很重要的一种相互方法被用于评估三种地下水脆弱性模型（即GODS、SI和DRASTIC）以及一种地下水潜力数据挖掘模型——最大熵（MaxEnt）的性能。对于MaxEnt模型的训练和验证阶段，均采用了马氏距离技术。与SI和GODS相比，DRASTIC模型得出的脆弱性率与21口井中的硝酸盐浓度具有统计学显著相关性，其决定系数（R）值为0.76。DRASTIC模型能更好地反映地下水资源的污染脆弱性。平均有效权重为33的包气带的影响比其他参数更重要，其次是深度比地下水（D）（32.01）、净补给量（R）（28.95）和含水层介质（A）（18.1）。这些权重可能不会改变。MaxEnt在训练和验证阶段均表现出显著性能，其在接收者操作特征曲线（AUROC）下的面积分别为0.907和0.901。对最佳模型中的脆弱性图与源自MaxEnt的地下水潜力图进行的相互分析表明，高地下水潜力区域仍处于安全状态，但作为修正措施的首要优先事项需要更多关注。此外，整个研究区域约8.7%的区域对污染具有高脆弱性，这需要立即采取务实行动。
