基于高频在线水质数据异常的突发污染预警
|
摘要
在高频水质自动监测背景下,建立了基于软测量和水质时间序列异常检测的水体突发污染预警预报技术.假定突发污染事故会引起典型自动监测水质参数变化,采用回归分析建立水质参数和在线高频监测水质参数间的线性关系进行软测量,采用人工神经网络预测短程水质变化,建立基于预测残差的异常判断最小阈值,最终通过有序监督聚类进行水质突变检测从而对突发污染事故进行预警.采用美国弗吉尼亚州的Potomac River流域在线监测数据进行算法验证和案例分析.分析受试者工作曲线(ROC)表明:该方法对2倍异常和3倍异常水平的检测准确率分别为62.7%和92.5%,且随着异常水平的增加准确率增加,通常突发污染事故中特定污染物浓度水平一般明显高于3倍,该方法具有较高的准确率.较其他突发污染水质预警技术,该技术有效缩短了平均检测时间,为流域污染预警预报和快速应急响应提供了新途径.
With the high frequency automatic monitoring of surface water quality, a technique for early warning of water pollution incidents was developed using the water quality soft measurement and abnormal detection of time series. This technique takes the assumption that water pollution incidents would cause the change of typical automatic monitoring water quality parameters, and then establishes the linear relationship between the water quality parameters and online high frequency monitoring water quality parameters. Using the artificial neural network, the change of water quality parameters in a short duration was predicted; using the time series of residual error, the threshold of abnormal change was determined. Finally, early warning of pollution incidents could be achieved through detecting abnormal change based on sequential leader clustering algorithm. To verify the technique, this study takes the online monitoring data obtained from the Potomac River in Virginia, USA as a case study. The analysis of the receiver operating characteristic curve(ROC) shows that the detection accuracies of double and triple abnormal levels can reach 62.7% and 92.5%, respectively. Because the concentration level of a water pollution incident is usually significantly higher than 3 times, this technique can provide a relative high accurate early warning. Compared with traditional abnormal detection methods, this technique can shorten the detection time. Along with increasing improvement of automatic monitoring facilities, this study provided a new avenue for early warning of, and prompt response to, pollution incidents.
With the high frequency automatic monitoring of surface water quality, a technique for early warning of water pollution incidents was developed using the water quality soft measurement and abnormal detection of time series. This technique takes the assumption that water pollution incidents would cause the change of typical automatic monitoring water quality parameters, and then establishes the linear relationship between the water quality parameters and online high frequency monitoring water quality parameters. Using the artificial neural network, the change of water quality parameters in a short duration was predicted; using the time series of residual error, the threshold of abnormal change was determined. Finally, early warning of pollution incidents could be achieved through detecting abnormal change based on sequential leader clustering algorithm. To verify the technique, this study takes the online monitoring data obtained from the Potomac River in Virginia, USA as a case study. The analysis of the receiver operating characteristic curve(ROC) shows that the detection accuracies of double and triple abnormal levels can reach 62.7% and 92.5%, respectively. Because the concentration level of a water pollution incident is usually significantly higher than 3 times, this technique can provide a relative high accurate early warning. Compared with traditional abnormal detection methods, this technique can shorten the detection time. Along with increasing improvement of automatic monitoring facilities, this study provided a new avenue for early warning of, and prompt response to, pollution incidents.
引文
[1]李尧远,曹蓉.我国应急管理研究十年(2004~2013):成绩、问题与未来取向[J].中国行政管理,2015,(1):83-87.
[2]XUE P,ZENG W.Trends of environmental accidents and impact factors in China[J].Frontiers of Environmental Science&Engineering in China,2011,5(2):266-276.
[3]刘仁涛,郭亮,姜继平,等.环境污染应急处置技术的CBR-MADM两步筛选法模型[J].中国环境科学,2015,35(3):943-52.
[4]赵艳民,秦延文,郑丙辉,等.突发性水污染事故应急健康风险评价[J].中国环境科学,2014,34(5):1328-1335.
[5]Camp J V,Abkowitz M D,Leboeuf E J.Inland waterway resource and spill management needs in Southeastern USA[J].Disaster Prevention And Management,2010,19(4):483-497.
[6]US EPA,2017.National hydrography dataset high-resolution flowline data[EB/OL].The National Map.https://www.data.gov/.
[7]汤鸿霄.环境科学与技术的扩展融合趋势[J].环境科学学报,2017,37(2):405-406.
[8]李维铮,孟桥.基于遥测数据动态特征的卫星异常检测方法[J].空间科学学报,2014,34(2):201-207.
[9]田嘉瑞.传感器网络数据流异常数据检测与修正[D].哈尔滨:哈尔滨工程大学,2008.
[10]Zou S,Liang Y,Poor H V,et al.Nonparametric Detection of Anomalous Data Streams[J].Computer Science,2016,1:1-26.
[11]黄树成,曲亚辉.数据流分类技术研究综述[J].计算机研究应用,2009,26(10):3604-3609.
[12]陈玥.城市供水水质异常检测方法研究[D].杭州:浙江大学,2013.
[13]魏媛,冯天恒,黄平捷,等.管网水质多指标动态关联异常检测方法[J].浙江大学学报(工学版),2016,50(7):1402-1409.
[14]Christensen V G.Characterization of surface-water quality based on real-time monitoring and regression analysis,quivira national wildlife refuge,south-central kansas,december 1998 through June 2001[R].Center for Integrated Data Analytics Wisconsin Science Center,2001.
[15]Horsburgh J S,Jones A S,Stevens D K,et al.A sensor network for high frequency estimation of water quality constituent fluxes using surrogates[J].Environmental Modelling&Software,2010,25(9):1031-1044.
[16]姜继平,王鹏,刘洁,等.突发水污染预警应急响应研究与实践的方法学辨析[J].环境科学学报,2017,37(1):1-13.
[17]Liu J,Guo L,Jiang J P,et al.Evaluation and selection of emergency treatment technology based on dynamic fuzzy GRAmethod for chemical contingency spills[J].Journal of Hazardous Materials,2015,299:306-315.
[18]Helsel D R.Statistical methods in water resources/D.R.Helsel and R.M.Hirsch[M].Amsterdam,New York:Elsevier,1992.
[19]Parmar K S,Bhardwaj R.Water quality management using statistical analysis and time-series prediction model[J].Applied Water Science,2014,4(4):425-434.
[20]Mckenna S A,Hart D B,Murray R,et al.Testing and evaluation of water quality event detection algorithms[M].Handbook of Water and Wastewater Systems Protection,2011.
[21]PE A-AYALA A.Educational data mining:A survey and a data mining-based analysis of recent works[J].Expert Systems with Applications,2014,41(4):1432-1462.
[2]XUE P,ZENG W.Trends of environmental accidents and impact factors in China[J].Frontiers of Environmental Science&Engineering in China,2011,5(2):266-276.
[3]刘仁涛,郭亮,姜继平,等.环境污染应急处置技术的CBR-MADM两步筛选法模型[J].中国环境科学,2015,35(3):943-52.
[4]赵艳民,秦延文,郑丙辉,等.突发性水污染事故应急健康风险评价[J].中国环境科学,2014,34(5):1328-1335.
[5]Camp J V,Abkowitz M D,Leboeuf E J.Inland waterway resource and spill management needs in Southeastern USA[J].Disaster Prevention And Management,2010,19(4):483-497.
[6]US EPA,2017.National hydrography dataset high-resolution flowline data[EB/OL].The National Map.https://www.data.gov/.
[7]汤鸿霄.环境科学与技术的扩展融合趋势[J].环境科学学报,2017,37(2):405-406.
[8]李维铮,孟桥.基于遥测数据动态特征的卫星异常检测方法[J].空间科学学报,2014,34(2):201-207.
[9]田嘉瑞.传感器网络数据流异常数据检测与修正[D].哈尔滨:哈尔滨工程大学,2008.
[10]Zou S,Liang Y,Poor H V,et al.Nonparametric Detection of Anomalous Data Streams[J].Computer Science,2016,1:1-26.
[11]黄树成,曲亚辉.数据流分类技术研究综述[J].计算机研究应用,2009,26(10):3604-3609.
[12]陈玥.城市供水水质异常检测方法研究[D].杭州:浙江大学,2013.
[13]魏媛,冯天恒,黄平捷,等.管网水质多指标动态关联异常检测方法[J].浙江大学学报(工学版),2016,50(7):1402-1409.
[14]Christensen V G.Characterization of surface-water quality based on real-time monitoring and regression analysis,quivira national wildlife refuge,south-central kansas,december 1998 through June 2001[R].Center for Integrated Data Analytics Wisconsin Science Center,2001.
[15]Horsburgh J S,Jones A S,Stevens D K,et al.A sensor network for high frequency estimation of water quality constituent fluxes using surrogates[J].Environmental Modelling&Software,2010,25(9):1031-1044.
[16]姜继平,王鹏,刘洁,等.突发水污染预警应急响应研究与实践的方法学辨析[J].环境科学学报,2017,37(1):1-13.
[17]Liu J,Guo L,Jiang J P,et al.Evaluation and selection of emergency treatment technology based on dynamic fuzzy GRAmethod for chemical contingency spills[J].Journal of Hazardous Materials,2015,299:306-315.
[18]Helsel D R.Statistical methods in water resources/D.R.Helsel and R.M.Hirsch[M].Amsterdam,New York:Elsevier,1992.
[19]Parmar K S,Bhardwaj R.Water quality management using statistical analysis and time-series prediction model[J].Applied Water Science,2014,4(4):425-434.
[20]Mckenna S A,Hart D B,Murray R,et al.Testing and evaluation of water quality event detection algorithms[M].Handbook of Water and Wastewater Systems Protection,2011.
[21]PE A-AYALA A.Educational data mining:A survey and a data mining-based analysis of recent works[J].Expert Systems with Applications,2014,41(4):1432-1462.