澳门半岛近岸海域水质时空变异分析

Identification of Spatio-Temporal Variation in the Seaside Water Quality Along Macao Peninsula

采用聚类分析和判别分析技术对澳门半岛近岸海域22个监测点2000-2005年期间的监测数据进行水质时空分析,旨在识别澳门半岛近岸海域水质时空变化特征,从而为澳门半岛水质监测网络的优化和近岸海域水质的控制提供支持.监测点位取样时间聚类结果可分为6-9月和1-5月、10-12月2组,与传统的4-9月和10-3月的丰、枯水期划分存在差异;按采样点位的空间聚类结果显示,第1组的监测站点都位于西侧,第2组的监测站点都位于东侧和南侧.通过后退式判别分析,表征空间差异性的显著性指标为pH、氯化物、TSS、颜色;表征时间差异性的显著指标为总磷、氯化物、颜色、氨氮、溶解氧、化学需氧量.空间与时间差异性判别的正确率分别达到84.82%和76.57%,显示后退式判别分析具有较好的指标降维能力和判别能力.

Cluster analysis（CA） and discriminant analysis（DA） were coupled to identify the spatial and temporal variation of the seaside water quality for 14 parameters and 22 different sites along Macao Peninsula,so as to identify the temporal and spatial variation for further optimizing the monitoring network and controlling the seaside water quality along Macao Peninsula.The results show that 12 months could be grouped into two periods,June-September and the remaining months,and the entire area was divided into two clusters,one located at western sides of Macao Peninsula,and another one is in southeast and southern sides of the Macao peninsula.Through backward stepwise DA,pH,Cl^-,TSS,color and TP,Cl^-, color,NH4^＋,DO,COD were identified as the discriminant variables of spatial and temporal variation,with 84.82% and 76.57% correct assignments,respectively.This study illustrates the application of multivariate statistical techniques is beneficial for understanding the temporal and spatial variation of seaside water quality and further effective water quality management.