Acta Scientiarum Naturalium Universitatis Pekinensis ›› 2017, Vol. 53 ›› Issue (5): 948-956.DOI: 10.13209/j.0479-8023.2017.113

• Orginal Article • Previous Articles     Next Articles

Integrated PCA-BN Approach for Identifying the Water Quality Response Patterns for Lakes in Yunnan Plateau

Qingsong JIANG1, Zhongyao LIANG1, Lei ZHAO2, Yuzhao LI1, Sifeng WU1, Yong LIU1()   

  1. 1. Key Laboratory of Water and Sediment Sciences (MOE), College of Environmental Science and Engineering, Peking University, Beijing 100871
    2. Yunnan Key Laboratory of Pollution Process and Management of Plateau Lake-Watershed, Kunming 650034;
  • Received:2016-05-12 Revised:2016-09-04 Online:2017-09-09 Published:2017-09-20

云南高原湖泊群的统计学聚类识别及水质响应模式研究

蒋青松1, 梁中耀1, 赵磊2, 李玉照1, 吴思枫1, 刘永1()   

  1. 1. 水沙科学教育部重点实验室, 北京大学环境科学与工程学院, 北京 100871
    2. 云南高原湖泊流域污染过程与管理重点实验室, 昆明 650034
  • 基金资助:
    国家重点基础研究发展计划(2015CB458900)和国家自然科学基金(41222002)资助

Abstract:

An integrated approach of principle components analysis (PCA) and Bayesian network (BN) for identify- ing the response pattern of different clusters were developed to understand sensitive relationships of water quality in lakes of Yunnan Plateau. The model includes four steps: data preconditioning, lakes clustering with PCA, Bayesian network learning and lake water quality response modeling. The results demonstrate that the 26 lakes can be clustered into two groups; the Chl a concentration responds more significantly to Total Nitrogen (TN) and Total Phosphorus (TP) in the first group, mainly resulting from much higher watershed disturbances; the Dissolved Oxygen (DO) in the first group with higher water temperature is close to saturation and have little change with Chl a increasing, while the second group is not; and there is good consistency on the relationship between Transpa-rency (SD)and Chl a in both groups.

Key words: plateau lakes, water quality, clustering, response pattern, principle components analysis, Bayesian network

摘要:

为探究湖泊群水质变量的响应模式, 构建适用于监测数据匮乏的湖泊群聚类和响应模式识别方法体系(PCA-BN), 包括4个步骤: 数据预处理、PCA降维与湖泊聚类、贝叶斯网络构建及参数学习、湖泊响应关系模拟。以云南高原湖泊群为例开展研究, 结果表明: 所研究的26个湖泊可分为两类; 由于第一类湖泊受到的人为干扰更严重, 因而叶绿素a对总氮和总磷的响应比第二类湖泊更敏感; 第一类湖泊表层水温高, 溶解氧趋近饱和, 随叶绿素a变化不显著, 第二类湖泊溶解氧随叶绿素a升高而显著升高; 两类湖泊的透明度与叶绿素a的关系一致。

关键词: 湖泊群, 水质, 聚类, 响应模式, 主成分分析, 贝叶斯网络