Laboratory of Analytical Chemistry, Department of Chemistry, National and Kapodistrian University of Athens, Panepistimioupolis Zografou, 15771 Athens, Greece.
Environ Monit Assess. 2012 Dec;184(12):7635-52. doi: 10.1007/s10661-012-2524-1. Epub 2012 Jan 21.
The aim of the present study is to compare the application of unsupervised and supervised pattern recognition techniques for the quality assessment and classification of the reservoirs used as the source for the domestic and industrial water supply of the city of Athens, Greece. A new optimization strategy for sampling, monitoring, and water management is proposed. During the period of October 2006 to April 2007, 89 samples were collected from the three water reservoirs (Iliki, Mornos, and Marathon), and 13 parameters (metals and metalloids) were analytically determined. Generally, all the elements were found to fluctuate at very low levels, especially for Mornos that comprises the main water reservoir of Athens. Iliki and Marathon showed relatively elevated values, compared to Mornos, but below the legislative limits. Multivariate unsupervised statistical techniques, such as factor analysis/principal components analysis, and cluster analysis and supervised ones, like discriminant analysis and classification trees, were applied to the data set, and their classification abilities were compared. All the chemometric techniques successfully revealed the critical variables and described the similarities and dissimilarities among the sampling points, emphasizing the individual characteristics in every sample and revealing the sources of elements in the region. New data from posterior samplings (November and December 2007) were used for the validation of the supervised techniques. Finally, water management strategies were proposed concerning the sampling points and representative parameters.
本研究旨在比较无监督和监督模式识别技术在评估和分类用于供应希腊雅典市居民和工业用水的水库质量方面的应用。提出了一种新的采样、监测和水资源管理优化策略。2006 年 10 月至 2007 年 4 月期间，从三个水库（伊利基、莫尔诺斯和马拉松）采集了 89 个样本，并对 13 个参数（金属和类金属）进行了分析测定。总体而言，所有元素的含量都非常低，特别是作为雅典主要水源的莫尔诺斯水库。伊利基和马拉松水库的元素含量相对较高，但低于法定限量。多元无监督统计技术，如因子分析/主成分分析和聚类分析，以及监督技术，如判别分析和分类树，都被应用于数据集，并比较了它们的分类能力。所有化学计量技术都成功地揭示了关键变量，并描述了采样点之间的相似性和差异性，强调了每个样本的个体特征，并揭示了该地区元素的来源。来自后续采样（2007 年 11 月和 12 月）的数据用于验证监督技术。最后，提出了关于采样点和代表性参数的水资源管理策略。
