摘要
针对湖泊流域水环境污染责任量化模糊,难以准确科学进行管理及监督的问题,采用贝叶斯网络结构和K2算法学习,通过最大支撑树(MWST)得到最大父节点数,再由深度优先搜索算法(DFS)得到节点序,提出一种可对流域不确定性污染源进行责任量化的改进MWST-DFS-K2算法。基于此算法以洱海为实例验证构建流域污染物贝叶斯网络模型图,对其进行污染物量化分析后得出结论为,江尾站对流域内其他站点的污染贡献达90%以上,四级坝站水质次于Ⅱ类的概率为82%,该站本身存在较大水质问题,后续管理过程中应重点关注洱海流域出湖处水文站点四级坝站与入湖处水文站点江尾站周围的污染源。与传统溯源方法相比,该方法不仅弥补了对污染源不确定性分析的不足,还对污染源进行了科学的污染责任量化,能够为高原湖泊流域的污染物溯源研究提供参考。
In order to address the problem of vague responsibility quantification of water environment pollution in lake basin,which is difficult to manage and supervise accurately and scientifically,this study adopts the Bayesian network structure and K2 algorithm to learn,and obtains the maximum number of parent nodes through the Maximum Support Tree(MWST),and then ob-tains the node order by the Depth-First Search Algorithm(DFS)to put forward a kind of improved MWST-DFS-K2 algorithm that can quantify the responsibility of uncertain pollution sources in the watershed.Based on this algorithm,a Bayesian network model is constructed for the Erhai Sea as an example,and after analyzing the quantification of pollutants,it is concluded that Ji-angwei station contributes more than 90%to the pollution of other stations in the watershed,and the probability that the water quality of the fourth-level dam station is less than Class II is 82%,and there are large water quality problems in the station.In the subsequent management process,attention should be focused on the pollution sources around the Fourth Level Dam Station and the Jiangwei Station,which are hydrological stations in the lake.Compared with the traditional traceability methods,this method not only makes up for the lack of uncertainty analysis of pollution sources,but also quantifies the scientific pollution re-sponsibility of pollution sources,which can provide a reference for the study of pollutant traceability in plateau lake basins.
作者
沈春颖
张蕊
程乖梅
王铭明
左黔
张宗亮
刘春旸
SHEN Chunying;ZHANG Rui;CHENG Guaimei;WANG Mingming;ZUO Qian;ZHANG Zongliang;LIU Chunyang(College of Electrical Power Engineering,Kunming University of Science and Technology,Kunming 650500,China;Shanghai Investigation,Design&Research Institute Co.,Ltd.,Shanghai 200434,China)
出处
《水文》
北大核心
2025年第1期90-96,共7页
Journal of China Hydrology
基金
国家自然科学基金项目(52069009)
昆明理工大学引进人才科研启动基金项目(KKSY201904008)。
关键词
贝叶斯网络
深度优先搜索
最大支撑树
K2算法
污染风险溯源
洱海流域
Bayesian network
depth-first search
most weight supported tree
K2 algorithm
pollution risk traceability
Erhai Basin
