Mapping of groundwater hydrogeochemistry aspects through multivariate statistics and artificial neural networks

ABSTRACT The main objective this paper was to map the hydrogeochemistry aspects of groundwater using multivariate statistics and artificial neural networks as a subsidy to identify spatial patterns. For this, a case study was carried out in aquifers in the municipality of Lençóis (BA), in the region of Chapada Diamantina, Northeastern Brazil. Field campaigns were carried out to collect geodetic coordinates and groundwater samples. After laboratorial analysis and determination of analytical data, the environmental processes were interpreted by cluster analysis and self-organizing maps, as well as the waters classification through CONAMA Resolution no. 396/2008. For the purpose of mapping the analyzed data, geoprocessing techniques were used in GIS. The main physical and chemical constituents analyzed in two climatic periods were mapped and divided into seven clusters. Four zones that present different hydrogeochemical contexts were identified in the municipality. The zones of the east/southeastern, south (urban area) and south end sectors present the most significant changes in hydrogeochemistry and water quality. The mapping, supported by multivariate statistics and artificial neural networks, was potentially useful in contributing to the management actions of groundwater resources as delimitation of priority areas, monitoring of contamination risk zones and engineering interventions that eventually seek environmental groundwater sanitation.

摘要 本研究旨在借助多元统计分析与人工神经网络，绘制地下水水文地球化学特征分布图，以识别其空间格局。为此，以巴西东北部迪亚曼蒂纳高地地区巴伊亚州（BA）伦索伊斯市的含水层为研究对象开展案例研究。通过野外作业采集大地坐标与地下水样品，经实验室分析并确定检测数据后，采用聚类分析与自组织映射解析水文地球化学过程，并依据巴西国家环境委员会（CONAMA）第396/2008号决议对地下水进行分类。为实现分析数据的可视化制图，本研究在地理信息系统（Geographic Information System，GIS）中运用地理处理技术。对两个气候周期内检测的主要物理化学组分进行制图，并将其划分为7个聚类。研究在该市境内识别出4个具有不同水文地球化学特征的区域，其中东部/东南部、南部（城区）及南端片区的水文地球化学特征与水质变化最为显著。本研究依托多元统计分析与人工神经网络完成的制图工作，可为地下水资源管理提供重要支撑，具体包括划定优先管控区域、监测污染风险区以及实施旨在实现地下水环境净化的工程干预措施。