基于神经网络模型的青岛市城区土壤重金属污染源定位  

Location of the Heavy Metal Pollution Source in the Soil Based on GA and BPANN

作　　者：吴育文[1] 徐英凯[2] 刘通[3] 林晖[4] 

机构地区：[1]东北大学秦皇岛分校数学与统计学院,河北秦皇岛066004 [2]南京航空航天大学理学院,南京211106 [3]南京航空航天大学自动化学院,南京211106 [4]沙洲职业工学院机电系,江苏张家港215600

出　　处：《湖北农业科学》2013年第3期685-687,695,共4页Hubei Agricultural Sciences

摘　　要：建立基于遗传算法的BP神经网络系统,该模型可以有效描绘区域中重金属元素的分布情况,并由此通过各元素浓度极大值点求出污染源近似坐标,实现对污染源的定位。将该模型运用于青岛市,根据青岛市不同功能区的土壤重金属含量调查结果,实现了对可能重金属元素污染源位置的预测。A model based on genetic algorithm and back propagation artificial neural network(BPANN) was developed to effectively depict the distribution of heavy metal in certain area and accurately locate the pollution source by picking out the coordinate that contented the maximum quantity of heavy metal according to the sampled data.Qingdao was took for instance.It detected the distribution of heavy metal in the soil of different areas in Qingdao,thus located the possible pollution source.

关 键 词：城区土壤 重金属污染 遗传算法 BP神经网络 

分 类 号：S[农业科学]