自适应FCM土壤表层重金属污染评价——以南京市炼油厂及生活区为例

Evaluation of heavy metal pollution in the soil surface of adaptive FCM——Taking the Nanjing refinery and its living area as an example

采用自适应模糊C均值聚类(FCM)挖掘土壤重金属的污染程度信息,以实现污染程度分类数的自动获取,确保类别划分的合理性,真实地反映重金属污染的空间聚集特征.以江苏省南京市炼油厂及生活区为研究对象,采集土壤中Cr、Cd、Ni、Pb、Zn、Cu重金属浓度值,首先运用自适应FCM对浓度值进行聚类分析,然后利用地统计学空间插值,揭示污染的空间聚集性.结果表明,研究区存在不同程度的污染,自适应FCM算法比传统聚类算法能更合理地划分重金属污染程度,挖掘出样本潜在的污染信息,可为分析污染成因及土壤环境治理修复提供参考.

Adaptive Fuzzy C-Mean Clustering(FCM)was used to excavate the pollution degree information of heavy metals in soil to achieve automatic acquisition of the classification of pollution degrees,in order to ensure the rationality of classification and truly reflect the spatial aggregation characteristics of heavy metal pollution.Taking the refinery and living area of Nanjing,Jiangsu Province as the research object,the heavy metal concentration values of Cr,Cd,Ni,Pb,Zn and Cu in the soil were collected.Firstly,the concentration values were analyzed by adaptive FCM,and then the spatial interpolation of geostatistical science was used to reveal the spatial agglomeration of pollution.The results indicated that there were different degrees of pollution in the study area;the degree of heavy metal pollution could be divided by the adaptive FCM algorithm more than the traditional clustering algorithm,the potential pollution information of the samples could be excavated,which could provide a reference for analyzing the causes of pollution and soil environmental remediation.