| 基于BP神经网络的污染场地土壤重金属和PAHs含量预测 |
| |
| 引用本文： | 任加国,龚克,马福俊,谷庆宝,武倩倩.基于BP神经网络的污染场地土壤重金属和PAHs含量预测[J].环境科学研究,2021,34(9):2237-2247. |
| |
| 作者姓名： | 任加国 龚克 马福俊 谷庆宝 武倩倩 |
| |
| 作者单位： | 1.山东科技大学地球科学与工程学院, 山东 青岛 266590 |
| |
| 基金项目： | 国家自然科学基金项目41202165国家自然科学基金项目41102149 |
| |
| 摘 要： | 受土壤检测成本和项目周期等因素制约，污染场地土壤经常存在检测数据缺失的现象，如何利用有限的检测数据获得更全面的信息成为当前研究热点.以某金属加工厂污染场地为研究对象，运用多元统计方法分析土壤样品中重金属(As、Zn、Cu、Pb、Ni、Cd、Cr)和多环芳烃(polycyclic aromatic hydrocarbons，PAHs)〔苯并a]芘(BaP)、二苯并a，h]蒽(DBA)、苯并k]荧蒽(BkF)、苯并b]荧蒽(BbF)、苯并a]蒽(BaA)、萘(Nap)、?(Chr)〕之间的关联性，并以此为基础，利用已知数据建立BP神经网络模型，预测缺失土壤样本中重金属和PAHs的含量.结果表明:与GB 36600—2018《土壤环境质量建设用地土壤污染风险管控标准(试行)》中的风险筛选值对比，重金属超标率表现为w(Ni)>w(Cu)>w(As)>w(Pb)>w(Zn)=w(Cd)>w(Cr)，除w(Chr)未超标外，其他6种PAHs按超标率排序为w(BaP)>w(DBA)>w(BbF)=w(BaA)>w(Nap)>w(BkF).重金属Zn与Pb、As与Cd关联性较好，Cu与Ni关联性较好，Cr与其他6种重金属关联性较差，PAHs中除Nap外，BaP、DBA、BkF、BbF、BaA和Chr彼此关联性均较好；构建的BP神经网络模型的污染物浓度预测值与实测值的决定系数(R2)范围为0.812~0.993，模拟效率系数(NSE)范围为0.779~0.959，均方根误差(RMSE)和平均绝对误差(MAE)均较小.研究显示，研究区土壤重金属和PAHs含量整体存在不同程度的超标现象，构建的BP神经网络模型对污染物浓度预测结果准确可靠，利用该模型对土壤污染进行空间分析与评价具有可行性，且关联性较弱的因子作为输入参数能进一步提高预测模型的精度.
|
| 关 键 词： | 污染土壤 重金属 多环芳烃(PAHs) BP神经网络 污染预测 |
| 收稿时间： | 2020-12-22 |
Prediction of Heavy Metal and PAHs Content in Polluted Soil Based on BP Neural Network |
| |
| Affiliation: | 1.School of Earth Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China2.State Key Laboratory of Environmental Criteria and Risk Assessment, Chinese Research Academy of Environmental Sciences, Beijing 100012, China |
| |
| Abstract: | Due to the constraints of soil monitoring cost and project cycle, there are often monitoring data missing on contaminated soil sites. Accordingly, how to obtain more information from limited data is the focus of current study. This paper studied a site contaminated by metal sheds and used multivariate statistical methods to analyze the correlation between heavy metals (As, Zn, Cu, Pb, Ni, Cd, Cr) and polycyclic aromatic hydrocarbons (PAHs) (BaP, DBA, BkF, BbF, BaA, Nap, Chr) in soil samples. On this basis, a BP neural network model was established by using the known data to predict the content of heavy metals and PAHs in missing soil samples. The results suggested that: compared with the risk screening values in Soil Environment Quality Risk Control Standard for Soil Contamination of Development Land (GB 36600-2018), the rate of heavy metals exceeding the standard was w(Ni) > w(Cu) > w(As) > w(Pb) > w(Zn)=w(Cd) > w(Cr). Except that w(Chr) did not exceed the standard, the over-standard rate of the other six PAHs was w(BaP) > w(DBA) > w(BbF)=w(BaA) > w(Nap) > w(BkF). Zn and Pb, As and Cd correlated better, Cu and Ni correlated better, Cr correlated poorly with the other six heavy metals. Except for Nap, BaP, DBA, BkF, BbF, BaA and Chr had good correlation with each other in PAHs. The coefficient of determination (R2) of the actual values of contaminant concentrations and the predicted values of the BP neural network model was in the range of 0.812-0.993. The Nash efficiency coefficient (NSE) was in the range of 0.779-0.959. The root means square error (RMSE) and mean absolute error (MAE) were small. The research showed that the contents of heavy metals and PAHs generally exceeded the standard to different degrees in the study area. The BP neural network prediction model was accurate and reliable to predict contaminant concentration. It was feasible to use BP neural network model for spatial analysis and evaluation of soil pollution. And weakly correlated factors as input parameters could equip the prediction model with higher precision. |
| |
| Keywords: | |
|
| 点击此处可从《环境科学研究》浏览原始摘要信息 |
|
点击此处可从《环境科学研究》下载全文 |
|
