基于改进主成分分析法的土壤重金属污染评价模型  被引量:8

An evaluation model for heavy metal pollution in soil based on improved PCA

在线阅读下载全文

作  者:轩诗垚 王占刚[1] XUAN Shiyao;WANG Zhangang(School of Information and Communication Engineering,Beijing Information Science&Technology University,Beijing 100101,China)

机构地区:[1]北京信息科技大学信息与通信工程学院,北京100101

出  处:《北京信息科技大学学报(自然科学版)》2021年第1期23-27,共5页Journal of Beijing Information Science and Technology University

基  金:国家重点研发计划课题资助(2018YFC1800203);北京市科技创新服务能力建设-基本科研业务费(市级)(科研类)(PXM2019_014224_000026)。

摘  要:为解决传统土壤重金属污染评价模型中主成分分析法在进行数据降维处理的过程中难以兼顾各个污染因子差异性的问题,提出了一种结合单因子指数法的改进主成分分析法评价模型。利用对研究区域土壤重金属污染物进行单因子指数分析所得到的污染指数值,使用环比评分法得到其对应的权重值,对原始数据标准化处理后再进行加权处理,得到累计贡献率最大的3个主成分。通过分析所得主成分的相关数据并对比传统主成分分析法,可知改进方法的评价结果对土壤重金属元素的差异性更加具有针对性,更加切合研究区域的污染情况。In order to solve the problem that the principal component analysis(PCA)is difficult to take into account the difference of various pollution factors in the process of data dimensionality reduction in the traditional evaluation model of heavy metal pollution in soil,an evaluation model based on improved PCA which is combined with single factor index method was proposed.Based on the pollution index value obtained by single factor index analysis of heavy metal pollutants in the soil of the study area,the corresponding weight value was obtained by using sequential scoring method.After standardized processing of original data,weighted processing was carried out to obtain the three principal components with the highest cumulative contribution rate.By analyzing the relevant data of the selected components and comparing with the traditional principal component analysis method,it can be seen that the evaluation results of the improved method are more targeted to the difference of heavy metal pollutants in the soil and more suitable for the pollution situation of the study area.

关 键 词:主成分分析 土壤重金属污染评价 单因子指数法 指数加权 

分 类 号:X826[环境科学与工程—环境工程]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象