在研究区域采集227个土壤样品,对其Cu、Zn、Pb、Cd和As含量进行测定,并分别应用单因子指数法、GA-SVM模型和内梅罗综合污染指数法计算、评价了各采样点的土壤环境质量等级.结果表明:GA-SVM模型的最佳惩罚参数C为21.939,RBF核函数的最优参数g为12.995,均方百分比误差MSPE为1.3958,该模型对训练集(150个样本)、测试集的平均分类精度达到97.33％;GA-SVM模型对77个测试样本的土壤环境质量等级评价结果与单因子指数法的评价结果一致,与内梅罗综合污染指数法评价结果的变化趋势一致.%A total of 227 soil samples were collected in the study area,and the contents of heavy metal elements Cu,Zn,Pb,Cd and As in these soil samples were measured.By using single-factor index method,GA-SVM (Support Vector Machine)model and Nemero's comprehensive pollution index method,the soil environmental quality level of each sample was calculated and evaluated respectively.The results indicated that:the optimal punishment parameter C of GA-SVM model was 21.939;the optimum parameter g of RBF kernel function was 12.995;the mean square percentage error MSPE was 1.3958;the average classification accuracy of this model for training set (150 samples) and test set (77 samples) reached 97.33％;the results of environmental quality level of 77 tested soil samples evaluated by GA-SVM model were the same as those did by single-factor index method,and they had the same change trend as those did by Nemero's comprehensive pollution index method.
展开▼
