基于自组织神经网络和K-means的场地地下水污染特征分析与分区管控研究

黄燕鹏; 汪远昊; 王超; 刘伟江; 王宏; 吕广丰; 林斯杰; 胡清

doi:10.13205/j.hjgc.202206004

基于自组织神经网络和K-means的场地地下水污染特征分析与分区管控研究

doi: 10.13205/j.hjgc.202206004

黄燕鹏^1,2,
汪远昊³,
王超^2,3,
刘伟江⁴,
王宏^2,3,
吕广丰³,
林斯杰³,
胡清^2,3, ,

1. 哈尔滨工业大学环境学院, 哈尔滨 150090;
2. 南方科技大学环境科学与工程学院, 广东深圳 518055;
3. 南科大工程技术创新中心(北京), 北京 100083;
4. 生态环境部土壤与农业农村生态环境监管技术中心, 北京 100012

基金项目:

国家重点研发计划(2018YFC1801303,2019YFC1803900,2018YFC1800204)

详细信息

作者简介:
黄燕鹏(1993-),男,博士研究生,主要研究方向为土壤、地下水调查与修复,大数据在生态环境中的应用。11849581@mail.sustech.edu.cn

通讯作者:
胡清(1964-),女,博士,教授,主要研究方向包括大数据与环境,城市环境工程研究,绿色可持续污染场地修复等。huq@sustech.edu.cn

计量
- 文章访问数: 290
- HTML全文浏览量: 85
- PDF下载量: 16
- 被引次数: 0
出版历程
- 收稿日期: 2022-01-10
- 网络出版日期: 2022-09-01
- 刊出日期: 2022-09-01

CHARACTERISTICS ANALYSIS AND ZONING CONTROL OF GROUNDWATER POLLUTION BASED ON SELF-ORGANIZING MAPS AND K-MEANS

1. School of Environment, Harbin Institute of Technology, Harbin 150090, China;
2. School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen 518055, China;
3. Engineering Innovation Center of Southern University of Science and Technology, Beijing 100083, China;
4. Technical Center for Soil, Agriculture and Rural Ecology and Environment, Ministry of Ecology and Environment, Beijing 100012, China

摘要

摘要: 该研究基于自组织神经网络(SOM)和K-means方法,以华中地区某铬渣污染场地为研究对象,探讨了SOM+K-means方法应用于场地地下水污染分区管控的可能性。通过监测数据的描述性统计分析场地地下水污染特征,发现Cr (Ⅵ)、COD_Mn、SO₄^2-、TDS、NO₃^-、NH₃-N、Mn为研究区的主要污染物。基于SOM+K-means分析挖掘,并基于空间插值方法,将研究区地下水分为4类区域,并识别出每类区域需重点关注的污染指标。结果显示:类别Ⅰ需关注NO₃^-;类别Ⅱ需关注Cr (Ⅵ)、COD_Mn、NO₃、TDS、NH₃^--N;类别Ⅲ需关注SO₄^2-;类别Ⅳ需关注Mn。该方法可较好地应用于地下水污染分区管控,对场地地下水污染防治具有指导意义。
- 机器学习 /
- 自组织神经网络 /
- K-means /
- 地下水污染 /
- 分区管控
Abstract: Based on the self-organizing maps (SOM) and K-means method,this study took a contaminated site to explore the feasibility of applying SOM and K-means method to the zoning control of groundwater pollution.Through descriptive statistical analysis of monitoring data,the groundwater pollution characteristics of the site were obtained.It was found that Cr (Ⅵ),COD_Mn,SO₄^2-,TDS,NO₃^-,NH₃-N and Mn were the main pollutants in the study area.Derived from SOM,K-means analysis and spatial interpolation,groundwater in the study area was divided into four types of areas.The pollution factors of each cluster that need to be paid attention to were identified.The results showed that NO₃^- should be paid attention to for cluster Ⅰ;Cr (Ⅵ),COD_Mn,NO₃^-,TDS and NH₃-N for cluster Ⅱ;SO₄^2- for cluster Ⅲ,and Mn for cluster Ⅳ.This method can be applied to the zoning control of groundwater pollution,which had guiding significance for the prevention and control of groundwater pollution in contamination sites.
- machine learning /
- self-organizing map /
- K-means /
- groundwater pollution /
- pollution prevention and control

HTML全文

参考文献(46)

[1]	GLEICK P H. Water resources[J]. Encyclopedia of Climate, Weather, 1996:817-823.
[2]	周仰效,李文鹏.地下水水质监测与评价[J].水文地质工程地质, 2008(1):1-11.
[3]	左锐,石榕涛,王膑,等.地下水型水源地水质安全预警技术体系研究[J].环境科学研究, 2018, 31(3):409-418.
[4]	任黎明,秦冰,桑军强,等.石化污染场地地下水修复治理挑战与对策[J].石油炼制与化工, 2021, 52(4):119-126.
[5]	中华人民共和国国家质量监督检验检疫总局,中国国家标准化管理委员会.地下水质量标准:GB/T 14848-2017[S]. 2017.
[6]	张佳文,张伟红,陈震,等.北京密怀顺地区地下水污染风险评价方法探究[J].环境科学学报, 2018, 38(7):2876-2883.
[7]	孙从军,韩振波,赵振,等.地下水数值模拟的研究与应用进展[J].环境工程, 2013, 31(5):9-13 ,17.
[8]	江成鑫,赵江,张洪文.复杂岩溶条件下锰矿尾矿库地下水溶质运移特征数值模拟研究[J].中国环境监测, 2021, 37(1):95-102.
[9]	BADEENEZHAD A, TABATABAEE H R, NIKBAKHT H A, et al. Estimation of the groundwater quality index and investigation of the affecting factors their changes in Shiraz drinking groundwater, Iran[J]. Groundwater for Sustainable Development, 2020, 11:100435.
[10]	SANTOS M R, ROISENBERG A, IWASHITA F, et al. Hydrogeochemical spatialization and controls of the Serra Geral Aquifer System in southern Brazil:a regional approach by self-organizing maps and k-means clustering[J]. Journal of Hydrology, 2020, 591:125602.
[11]	FRIEDEL M J. Estimation and scaling of hydrostratigraphic units:application of unsupervised machine learning and multivariate statistical techniques to hydrogeophysical data[J]. Hydrogeology Journal, 2016, 24(8):2103-2122.
[12]	MELIN P, CESAR M J, SANCHEZ D, et al. Analysis of spatial spread relationships of coronavirus (COVID-19) pandemic in the world using self organizing maps[J]. Chaos Solitons&Fractals, 2020, 138:109917.
[13]	HAN H, LIU J, SHU L, et al. Local and synoptic meteorological influences on daily variability in summertime surface ozone in eastern China[J]. Atmospheric Chemistry and Physics, 2020, 20(1):203-222.
[14]	DAI L J, WANG L Q, LI L F, et al. Multivariate geostatistical analysis and source identification of heavy metals in the sediment of Poyang Lake in China[J]. Science of the Total Environment, 2018, 621:1433-1444.
[15]	KALTEH A M, BERNDTSSON R. Interpolating monthly precipitation by self-organizing map (SOM) and multilayer perceptron (MLP)[J]. Hydrological Sciences Journal, 2007, 52(2):305-317.
[16]	NOURANI V, MOGADDAM A A, NADIRI A O. An ANN-based model for spatiotemporal groundwater level forecasting[J]. Hydrological Processes, 2008, 22(26):5054-5066.
[17]	IWASHITA F, FRIEDEL M J, FERREIRA F J F. A self-organizing map approach to characterize hydrogeology of the fractured Serra-Geral transboundary aquifer[J]. Hydrology Research, 2018, 49(3):794-814.
[18]	洪悦,郭承军.基于K-means和SOM的水下传感器数据采集方法[J].数据采集与处理, 2021, 36(2):280-288.
[19]	陈军林,彭润民,李帅值,等.利用自组织特征映射神经网络和K-means聚类算法挖掘区域化探数据中的地质信息[J].物探与化探, 2017, 41(5):919-927.
[20]	中华人民共和国环境保护总局.水质六价铬的测定二苯碳酰二肼分光光度法:GB/T 7467-1987[S].北京:1987.
[21]	中华人民共和国卫生部,中国国家标准化委员会.生活饮用水标准检验方法:GB/T 5750[S].北京:中国标准出版社, 2006.
[22]	American Public Health Association. 4500-NO₃-NITROGEN (NITRATE)[M]. Standard Methods For the Examination of Water and Wastewater, 2018.
[23]	中华人民共和国环境保护部.水质氨氮的测定水杨酸分光光度法:HJ 536-2009[S].北京:中国环境科学出版社, 2009.
[24]	国家环境保护总局.水和废水监测分析方法[M]. 4版.北京:中国环境科学出版社, 2002.
[25]	U.S.Environmental Protection Agency. Inductively coupled plasma-optical emission spectrometry:method 6010D[S]. 2008.
[26]	KOHONEN T. Self-organized formation of topologically correct feature maps[J]. Biological Cybernetics, 1982, 43(1):59-69.
[27]	MARINAI S, FAINI S, MARINO E, et al. Efficient word retrieval by means of SOM clustering and PCA[C]//International Workshop on Document Analysis Systems, Nelson, New Zealand, 2006.
[28]	ASTEL A, TSAKOVSKI S, BARBIERI P, et al. Comparison of self-organizing maps classification approach with cluster and principal components analysis for large environmental data sets[J]. Water Research, 2007, 41(19):4566-4578.
[29]	任婷玉,梁中耀,陈会丽,等.基于模式识别方法的湖泊水质污染特征聚类研究[J].北京大学学报(自然科学版), 2019, 55(2):335-341.
[30]	VESANTO J, ALHONIEMI E. Clustering of the self-organizing map[J]. IEEE Transactions on Neural Networks, 2000, 11(3):586-600.
[31]	JAMES G, WITTEN D, HASTIE T, et al. An introduction to statistical learning[M]. Springer, 2013.
[32]	FABBROCINO S, RAINIERI C, PADUANO P, et al. Cluster analysis for groundwater classification in multi-aquifer systems based on a novel correlation index[J]. Journal of Geochemical Exploration, 2019, 204:90-111.
[33]	DAVIES D L, BOULDIN D W. A cluster separation measure[J]. IEEE Transactions on pattern analysis and machine intelligence, 1979,2:224-227.
[34]	ZOUBI M D B A, RAWI M A. An efficient approach for computing silhouette coefficients[J]. Journal of Computer Science, 2008, 4(3):252.
[35]	SYAKUR M, KHOTIMAH B, ROCHMAN E, et al. Integration k-means clustering method and elbow method for identification of the best customer profile cluster[C]//The 2nd International Conference on Vocational Education and Electrical Engineering (ICVEE), Surabaya, Indonesia, 2017.
[36]	WANG J X, WANG Z Y, YANG C, et al. Optimization of the number of components in the mixed model using multi-criteria decision-making[J]. Applied Mathematical Modelling, 2012, 36(9):4227-4240.
[37]	TIBSHIRANI R, WALTHER G, HASTIE T. Estimating the number of clusters in a data set via the gap statistic[J]. Journal of the Royal Statistical Society:Series B (Statistical Methodology), 2001, 63(2):411-423.
[38]	栗泽苑,杨雷峰,华道柱,等. 2013-2018年中国近地面臭氧浓度空间分布特征及其与气象因子的关系[J].环境科学研究, 2021, 34(9):2094-2104.
[39]	GEHRING U, TAMBURIC L, SBIHI H, et al. Impact of noise and air pollution on pregnancy outcomes[J]. Epidemiology, 2014,25(3):351-358.
[40]	HUANG Y, LI T Q, WU C X, et al. An integrated approach to assess heavy metal source apportionment in peri-urban agricultural soils[J]. Journal of Hazardous Materials, 2015, 299:540-549.
[41]	袁建飞,邓国仕,徐芬,等.毕节市北部岩溶地下水水化学特征及影响因素的多元统计分析[J].中国地质, 2016, 43(4):1446-1456.
[42]	刘丽丽,邓一荣,廖高明,等.华南某污染场地土壤重金属污染健康风险评估与来源解析[J].环境污染与防治, 2021, 43(7):875-879.
[43]	任加国,龚克,马福俊,等.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.
[44]	胡冰殊,柳西亚,王宁,等.河南省东部平原浅层地下水水质特征分析[J].地下水, 2021, 43(2):33-36.
[45]	徐腾,南丰,蒋晓锋,等.制革场地土壤和地下水中铬污染来源及污染特征研究进展[J].土壤学报, 2020, 57(6):1341-1352.
[46]	李笑诺,陈卫平,吕斯丹.国内外污染场地风险管控技术体系与模式研究进展[J].土壤学报, 2022,59(1):38-53.

施引文献

资源附件(0)

访问统计

点击查看大图

计量

文章访问数: 290
HTML全文浏览量: 85
PDF下载量: 16
被引次数: 0

姓名
邮箱
手机号码
标题
留言内容
验证码

留言板

基于自组织神经网络和K-means的场地地下水污染特征分析与分区管控研究

doi: 10.13205/j.hjgc.202206004

作者简介:
黄燕鹏(1993-),男,博士研究生,主要研究方向为土壤、地下水调查与修复,大数据在生态环境中的应用。11849581@mail.sustech.edu.cn

通讯作者:
胡清(1964-),女,博士,教授,主要研究方向包括大数据与环境,城市环境工程研究,绿色可持续污染场地修复等。huq@sustech.edu.cn

计量

CHARACTERISTICS ANALYSIS AND ZONING CONTROL OF GROUNDWATER POLLUTION BASED ON SELF-ORGANIZING MAPS AND K-MEANS

计量

目录

期刊在线

作者中心

友情链接

留言板

基于自组织神经网络和K-means的场地地下水污染特征分析与分区管控研究

doi: 10.13205/j.hjgc.202206004

作者简介: 黄燕鹏(1993-),男,博士研究生,主要研究方向为土壤、地下水调查与修复,大数据在生态环境中的应用。11849581@mail.sustech.edu.cn

通讯作者: 胡清(1964-),女,博士,教授,主要研究方向包括大数据与环境,城市环境工程研究,绿色可持续污染场地修复等。huq@sustech.edu.cn

计量

出版历程

CHARACTERISTICS ANALYSIS AND ZONING CONTROL OF GROUNDWATER POLLUTION BASED ON SELF-ORGANIZING MAPS AND K-MEANS

计量

出版历程

目录

期刊在线

作者中心

友情链接

作者简介:
黄燕鹏(1993-),男,博士研究生,主要研究方向为土壤、地下水调查与修复,大数据在生态环境中的应用。11849581@mail.sustech.edu.cn

通讯作者:
胡清(1964-),女,博士,教授,主要研究方向包括大数据与环境,城市环境工程研究,绿色可持续污染场地修复等。huq@sustech.edu.cn