In the present research, geographic information system-based analytical hierarchy process (AHP) and data-driven evidential belief function (EBF) models were used for groundwater potential mapping (GPM) in the lower Dwarkeswar basin, India. For the purpose of GPM, a total of 38 groundwater wells locations with high discharge rate (3 l s⁻¹) were selected to prepare a well-inventory map. These locations were randomly divided into training (70%) and validation (30%) datasets. Considering the physical characteristics of the study area, nine groundwater conditioning factors, namely lithology, distance to lineaments, geomorphology, distance to streams, land use and landcover, slope, drainage density, curvature, and soil texture were derived from various sources. The training locations were used to determine the spatial relationship between these conditioning factors and the presence of groundwater. Then, groundwater potential maps were prepared using AHP and EBF models. Finally, an ensemble approach has been introduced for GPM by combing the results of the AHP and EBF models. The area under the curve method was used to validate the models and compare their performance. Validation results indicated that the ensemble model had the highest prediction accuracy (AUC = 84.18%) in groundwater potential mapping, followed by the EBF (AUC = 83.28%) and APH (AUC = 76.33%) models. According to the ensemble model, the south-eastern part of the study area has high potential for groundwater due to the gentle slope, permeable lithology and very low drainage density.

在本研究中，基于地理信息系统的层次分析法 (AHP) 和数据驱动的证据信念函数 (EBF) 模型被用于印度 Dwarkeswar 盆地下游的地下水潜力测绘 (GPM)。就 GPM 而言，共有 38 个具有高排放率（3 l s ^-1) 被选中来准备一个良好的库存图。这些位置被随机分为训练 (70%) 和验证 (30%) 数据集。考虑到研究区的物理特征，从不同来源推导出九个地下水调节因子，即岩性、与线状体的距离、地貌、与河流的距离、土地利用和土地覆盖、坡度、排水密度、曲率和土壤质地。训练地点用于确定这些调节因素与地下水存在之间的空间关系。然后，使用 AHP 和 EBF 模型绘制地下水潜力图。最后，通过结合 AHP 和 EBF 模型的结果，为 GPM 引入了集成方法。曲线下面积用于验证模型并比较它们的性能。验证结果表明，集成模型在地下水潜力测绘中具有最高的预测精度（AUC = 84.18%），其次是EBF（AUC = 83.28%）和APH（AUC = 76.33%）模型。根据集合模型，研究区东南部由于坡度平缓、岩性渗透性好、排水密度极低，具有较高的地下水潜力。