基于支持向量机模型的水质评价研究  

Assessment of Water Quality Based on Support Vector Machine Model

作　　者：黄鹤[1] 卢文喜[1] 伊燕平[1] 罗建男[1] 

机构地区：[1]吉林大学环境与资源学院,吉林长春130021

出　　处：《节水灌溉》2012年第2期57-59,63,共4页Water Saving Irrigation

基　　金：国家自然科学基金资助项目(41072171)

摘　　要：将支持向量机方法应用到水质评价中,建立了RBF核函数支持向量机评价模型。根据石头口门水库水质特征,选择溶解氧、化学需氧量、高锰酸盐指数等五项指标作为输入因子进行评价,并与综合水质评价法、模糊综合评价法比较。研究结果表明石头口门水库主要为Ⅱ类和Ⅲ类水,呈汛期较差、非汛期较好的变化规律。通过实例验证,说明支持向量机方法能够较好的解决分类评价问题,评价结果良好,符合客观事实,具有很好的研究价值和推广前景。In this paper,the RBF kernel support vector machine is built to assess water quality.According to the study on surface water quality characteristics in shitoukoumen reservoir,the DO,COD,CODMn and other five factors are selected as quality evaluation factors.The results are compared with those of the comprehensive water quality assessment method and fuzzy evaluation method.The results show that the type of water is mainly Ⅱ and Ⅲ in shitoukoumen reservoir,and is poor in flood season,while a good variation in non-flood season.Through the example confirmation,it is explained that the support vector machines method can solute the classification appraisal question well,conforms to the fact,and has very good research value and promotion prospect.

关 键 词：支持向量机 核函数 水质评价 石头口门水库 

分 类 号：X824[环境科学与工程—环境工程]