长江流域资源与环境 >> 2017, Vol. 26 >> Issue (04): 591-597.doi: 10.11870/cjlyzyyhj201704012

• 生态环境 • 上一篇    下一篇

基于神经网络的土壤重金属预测及生态风险评价

李杨1, 李海东1, 施卫省2, 何俊德1, 胡亚文1   

  1. 1. 昆明理工大学现代农业工程学院, 云南 昆明 650500;
    2. 昆明理工大学建筑与城市规划学院, 云南 昆明 650500
  • 收稿日期:2016-08-16 修回日期:2016-10-30 出版日期:2017-04-20
  • 通讯作者: 施卫省 E-mail:shiweisheng888@163.com
  • 作者简介:李杨(1992~),男,硕士研究生,主要从事土壤环境科学及GIS的研究.E-mail:2711241679@qq.com
  • 基金资助:
    国家自然科学基金项目(20264002);云南省科技厅基金项目(2011FB032)

PREDICTION AND ECOLOGICAL RISK ASSESSMENT OF HEAVY METALS IN SOIL BASED ON NEURAL NETWORK

LI Yang1, LI Hai-dong1, SHI Wei-sheng2, HE Jun-de1, HU Ya-wen1   

  1. 1. Faculty of Modern Agriculture Engineering, Kunming University of Science and Technology, Kunming 650500, China;
    2. Faculty of Architecture and City Planning, Kunming University of Science and Technology, Kunming 650500, China
  • Received:2016-08-16 Revised:2016-10-30 Online:2017-04-20
  • Supported by:
    National Natural Science Foundation of China (20264002);Yunnan provincial science and Technology Department fund project (2011FB032)

摘要: 采用单隐层RBF神经网络模型预测土壤重金属Cr、As、Ni、Pb、Zn 5种元素的含量,实测35组数据做为训练数据,另用6组做验证数据,该模型是以利用采样的10组数据预测其后的连续5组数据,输入层的神经元个数是10,输出层是5,隐含层的传递函数为径向基函数radbas,输出层的传递函数为线性函数Purelin,其结果表明:采用RBF神经网络模型预测有较高的精度。通过多元统计分析采样样品与预测样品,研究区域As、Ni、Zn的均值超过了上海市土壤环境背景值,As元素达到高度变异,Pb、Zn、Ni 3种元素达到中度变异。通过因子分析,前2个因子基本包含了全部元素变量的主要信息,第1因子中载荷最高是元素Ni(0.946),第2因子中则为元素As(0.930)。通过潜在生态风险指数评价,研究区域整体呈轻度生态风险水平。采用RBF神经网络模型可以降低采样分析成本,更好的评价区域土壤重金属的生态风险。

关键词: RBF神经网络, 重金属, 预测, 生态风险

Abstract: The Radial Basis Function (RBF) neural network was used to predict the contents of soil heavy metals of Cr, As, Hg, Ni, Pb, Zn in study area. We selected 35 groups of measured data as training data, with other 6 groups as validation data. The model was constituted continuous data of the 5 groups followed 10 groups of data based on continuous sampling. The number of neurons in the input layer is 10, and the output layer is 5. The transfer function of the hidden layer is the radial basis function radbas, and the transfer function of the output layer is linear function Purelin. The results showed that:RBF neural network prediction model has higher precision., Through multivariate statistical analysis on measured samples and prediction samples, the average values of As, Ni, Zn in the study area were found to exceed the background values of the soil environment in Shanghai City, and the As elements reached a high degree of variation, and Pb, Zn and Ni reached moderate variation. Through factor analysis, the first 2 factors basically contain the main information of all the elements. Among the first factors, the maximum load is the element Ni (0.946), and the second factor is the element As (0.930). Through the evaluation of potential ecological risk index, the study area is found to in a slight ecological risk level. The RBF neural network model can be used to reduce the cost of sampling and analysis, and to evaluate the ecological risk of heavy metals in the regional soil.

Key words: RBF neutral network, heavy metals, prediction, ecological risk

中图分类号: 

  • X825
[1] 蔡立梅,马瑾,周永章,等.东莞市农业土壤重金属的空间分布特征及来源解析[J].环境科学,2008,29(12):3496-3502.[CAI L M,MA J,ZHOU Y Z,et al.Multivariate geostatistics and GIS-based approach to study the spatial distribution and sources of heavy metals in agricultural soil in the Pearl River Delta,China[J].Environmental Science,2008,29(12):3496-3502.]
[2] YALCIN M G,ILHAN S.Multivariate analyses to determine the origin of potentially harmful heavy metals in beach and dune sediments from Kizkalesi coast (Mersin),Turkey[J].Bulletin of Environmental Contamination and Toxicology,2008,81(1):57-68.
[3] 庞妍,同延安,梁连友,等.矿区农田土壤重金属分布特征与污染风险研究[J].农业机械学报,2014,45(11):165-171.[PANG Y,TONG Y A,LIANG L Y,et al.Distribution of farmland heavy metals and pollution assessment in mining area[J].Transactions of the Chinese Society for Agricultural Machinery,2014,45(11):165-171.]
[4] KELEPERTZIS E.Accumulation of heavy metals in agricultural soils of Mediterranean:insights from Argolida basin,Peloponnese,Greece[J].Geoderma,2014,221-222:82-90.
[5] DRAGOVIĆ R,GAJIĆ B,DRAGOVIĆ S,et al.Assessment of the impact of geographical factors on the spatial distribution of heavy metals in soils around the steel production facility in Smederevo (Serbia)[J].Journal of Cleaner Production,2014,84:550-562.
[6] 张钰,王让会,李成.基于BP神经网络的表层土壤重金属分布模拟[J].安全与环境工程,2014,21(2):51-56.[ZHANG Y,WANG R H,LI C.Distribution simulation of heavy metals in surface soil based on BP neural network[J].Safety and Environmental Engineering,2014,21(2):51-56.]
[7] PÉREZ-ROA R,CASTRO J,JORQUERA H,et al.Air-pollution modelling in an urban area:correlating turbulent diffusion coefficients by means of an artificial neural network approach[J].Atmospheric Environment,2006,40(1):109-125.
[8] LI B L,ZHANG Y F,SHI X L,et al.Spatial interpolation method based on integrated RBF neural networks for estimating heavy metals in soil of a mountain region[J].Journal of Southeast University,2015,31(1):38-45.
[9] 段宁,杨思言,魏婉婷.基于BP神经网络的铅酸蓄电池厂地下水重金属浓度预测[J].环境科学与技术,2016,39(1):194-198.[DUAN N,YANG S Y,WEI W T.Prediction of heavy metal concentrations of the groundwater from a lead-acid battery factory based on BP neural network[J].Environmental Science&Technology,2016,39(1):194-198.]
[10] 王芬,彭国照,蒋锦刚,等.基于双层神经网络与GIS可视化的土壤重金属污染评价[J].农业工程学报,2010,26(4):162-168.[WANG F,PENG G Z,JIANG J G,et al.Pollution assessment of heavy metals based on double-layer BPNN and GIS visualization[J].Transactions of the CSAE,2010,26(4):162-168.]
[11] 魏复盛,齐文启.原子吸收光谱及其在环境分析中的应用[M].北京:中国环境科学出版社,1988.
[12] 陈秋平,胥思勤,孙浩然,等.锑矿区土壤As和Sb形态分布及生态风险评价[J].地球与环境,2014,42(6):773-778.[CHEN Q P,XU S Q,SUN H R,et al.Speciation distribution and ecological risk assessment of antimony and arsenic in soils of the antimony mining area[J].Earth and Environment,2014,42(6):773-778.]
[13] 李磊,李剑,马建华.RBF神经网络在土壤重金属污染评价中的应用[J].环境科学与技术,2010,33(5):191-195.[LI L,LI J,MA J H.Pollution assessment of heavy metals in soils based on RBF neural network[J].Environmental Science&Technology,2010,33(5):191-195.]
[14] 姜菲菲,孙丹峰,李红,等.北京市农业土壤重金属污染环境风险等级评价[J].农业工程学报,2011,27(8):330-337.[JIANG F F,SUN D F,LI H,et al.Risk grade assessment for farmland pollution of heavy metals in Beijing[J].Transactions of the CSAE,2011,27(8):330-337.]
[15] 戴彬,吕建树,战金成,等.山东省典型工业城市土壤重金属来源、空间分布及潜在生态风险评价[J].环境科学,2015,32(6):507-515.[DAI B,LV J S,ZHAN J Z,et al.Assessment of sources,spatial distribution and ecological risk of heavy metals in soils in a typical industry-based city of Shandong province,Eastern China[J].Environmental Science,2015,36(6):507-515.]
[16] 厉炯慧,翁珊,方婧,等.浙江海宁电镀工业园区周边土壤重金属污染特征及生态风险分析[J].环境科学,2014,35(4):1509-1515.[LI J H,WENG S,FANG J,et al.Heavy metal pollution characteristics and ecological risk analysis for soil around Haining electroplating industrial park[J].Environmental Science,2014,35(4):1509-1515.]
[17] 刘勇,岳玲玲,李晋昌.太原市土壤重金属污染及其潜在生态风险评价[J].环境科学学报,2011,31(6):1285-1293.[LIU Y,YUE L L,LI J C.Evaluation of heavy metal contamination and its potential ecological risk to the soil in Taiyuan,China[J].Acta Scientiae Circumstantiae,2011,31(6):1285-1293.]
[18] 国家环境保护总局.GB 15618-1995土壤环境质量标准[S].北京:中国标准出版社,2006.
[19] 中国环境监测总站.中国土壤元素背景值[M].北京:中国环境科学出版社,1990:330-485.
[20] LV J S,LIU Y,ZHANG Z L,et al.Factorial kriging and stepwise regression approach to identify environmental factors influencing spatial multi-scale variability of heavy metals in soils[J].Journal of Hazardous Materials,2013,261:387-397.
[21] WILDING L P.Spatial variability:its documentation,accommodation,and implication to soil surveys[M]//NIELSEN D R,BOUMA J.Soil Spatial Variability.Wageningen:Pudoc,1985:166-194.
[22] WANG H Y,LU S G.Spatial distribution,source identification and affecting factors of heavy metals contamination in urban-suburban soils of Lishui city,China[J].Environmental Earth Sciences,2011,64(7):1921-1929.
[23] 雷凌明,喻大松,陈玉鹏,等.陕西泾惠渠灌区土壤重金属空间分布特征及来源[J].农业工程学报,2014,30(6):88-96.[LEI L M,YU D S,CHEN Y P,et al.Spatial distribution and sources of heavy metals in soils of Jinghui Irrigated Area of Shaanxi,China[J].Transactions of the Chinese Society of Agricultural Engineering,2014,30(6):88-96.]
[1] 夏芳, 王秋爽, 蔡立梅, 杨超, 冯志州, 唐翠华, 卫瀛海, 许振成. 有色冶金区土壤-蔬菜系统重金属污染特征及健康风险分析[J]. 长江流域资源与环境, 2017, 26(06): 865-873.
[2] 王秀, 王振祥, 潘宝, 周春财, 刘桂建. 南淝河表层水中重金属空间分布、污染评价及来源[J]. 长江流域资源与环境, 2017, 26(02): 297-303.
[3] 刘倩倩, 陈岩. 基于粗糙集和BP神经网络的流域水资源脆弱性预测研究——以淮河流域为例[J]. 长江流域资源与环境, 2016, 25(09): 1317-1327.
[4] 龚艳冰, 戴靓靓, 胡娜, 刘高峰, 张继国. 基于云推理和模糊逻辑关系模型的干旱等级预测方法研究[J]. 长江流域资源与环境, 2016, 25(08): 1273-1278.
[5] 党丽娜, 梅杨, 廖祥森, 刘颖颖. 城市不同交通圈(带)土壤重金属多元统计分析及空间分布研究——以武汉市为例[J]. 长江流域资源与环境, 2016, 25(06): 925-931.
[6] 黄木易, 何翔. 巢湖流域土地景观格局变化及生态风险驱动力研究[J]. 长江流域资源与环境, 2016, 25(05): 743-750.
[7] 陈春丽, 戴星照, 曾桐辉, 弓晓峰, 刘春英, 左燕君. 城市内湖表层沉积物中有机氯农药残留特征及风险评价[J]. 长江流域资源与环境, 2015, 24(12): 2076-2084.
[8] 李继洲, 吴海旭, 姜万, 袁旭音, 刘斌武. 南京城区黑臭河道底泥污染特征及生态风险评价[J]. 长江流域资源与环境, 2015, 24(11): 1913-1919.
[9] 乔伟峰, 王亚华, 方斌. 基于变更平衡表的土地利用演化信息提取与预测方法研究——以苏州市为例[J]. 长江流域资源与环境, 2015, 24(09): 1514-1520.
[10] 赵源, 黄成敏. 基于RRM的市级土地利用总体规划生态风险评价[J]. 长江流域资源与环境, 2015, 24(07): 1102-1109.
[11] 蒋豫, 刘新, 高俊峰, 蔡永久. 江苏省浅水湖泊表层沉积物中重金属污染特征及其风险评价[J]. 长江流域资源与环境, 2015, 24(07): 1157-1162.
[12] 柳云龙, 章立佳, 庄腾飞, 韩晓非, 卢小遮. “城郊乡”梯度下土壤Cu、Zn、Pb含量的空间变异特征[J]. 长江流域资源与环境, 2015, 24(07): 1207-1213.
[13] 韩玉刚, 曹贤忠. 皖江区域城市能级与生态环境协调度的测度和发展趋势研究[J]. 长江流域资源与环境, 2015, 24(06): 909-916.
[14] 余光辉, 云琨, 翁建兵, 朱佳文, 张勇. 湘潭锰矿重金属环境安全及植物耐性研究[J]. 长江流域资源与环境, 2015, 24(06): 1046-1051.
[15] 弓晓峰, 孙明哲, 陈春丽, 王佳佳, 刘春英, 杨菊云, 向洪锐, 方亮. 盲数优化地积累模型评价长江中下游湖泊沉积物重金属污染[J]. 长江流域资源与环境, 2015, 24(05): 824-831.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 李 娜,许有鹏, 陈 爽. 苏州城市化进程对降雨特征影响分析[J]. 长江流域资源与环境, 2006, 15(3): 335 -339 .
[2] 张 政, 付融冰| 杨海真, 顾国维. 水量衡算条件下人工湿地对有机物的去除[J]. 长江流域资源与环境, 2007, 16(3): 363 .
[3] 孙维侠, 赵永存, 黄 标, 廖菁菁, 王志刚, 王洪杰. 长三角典型地区土壤环境中Se的空间变异特征及其与人类健康的关系[J]. 长江流域资源与环境, 2008, 17(1): 113 .
[4] 许素芳,周寅康. 开发区土地利用的可持续性评价及实践研究——以芜湖经济技术开发区为例[J]. 长江流域资源与环境, 2006, 15(4): 453 -457 .
[5] 郝汉舟, 靳孟贵, 曹李靖, 谢先军. 模糊数学在水质综合评价中的应用[J]. 长江流域资源与环境, 2006, 15(Sup1): 83 -87 .
[6] 刘耀彬, 李仁东. 现阶段湖北省经济发展的地域差异分析[J]. 长江流域资源与环境, 2004, 13(1): 12 -17 .
[7] 陈永柏,. 三峡工程对长江流域可持续发展的影响[J]. 长江流域资源与环境, 2004, 13(2): 109 -113 .
[8] 时连强,李九发,应 铭,左书华,徐海根. 长江口没冒沙演变过程及其对水库工程的响应[J]. 长江流域资源与环境, 2006, 15(4): 458 -464 .
[9] 翁君山,段 宁| 张 颖. 嘉兴双桥农场大气颗粒物的物理化学特征[J]. 长江流域资源与环境, 2008, 17(1): 129 .
[10] 王书国,段学军,姚士谋. 长江三角洲地区人口空间演变特征及动力机制[J]. 长江流域资源与环境, 2007, 16(4): 405 .