基于计算智能方法的河流水质管理数字模拟研究与应用
|
摘要
依靠数字模拟或概念模型等手段在宏观层面上改善河流水质，不仅可以节省大量人力物力，也可以实时对目标问题进行快速高效的分析解决。针对目前我国河流水质管理中存在的主要技术问题，本文在调研国内外研究现状的基础上，以松花江哈尔滨段为研究对象，利用计算智能方法等数值模拟手段开展了入河污染源识别模式、河流水质预测模型和入河排污削减模式的研究。
基于专家系统思想研究建立了入河污染源识别模式。结合河流常规水质监测，建立了基于污染超标初筛和多元数据挖掘技术的核心水质指标解析机制，可对常规监测矩阵解析出代表污染信息的污染因子及其荷载核心水质指标。根据专家知识构建了污染源类别判定树及其22类产生式规则，基于53则国家行业水污染排放标准，设计建立了针对工业点源污染因子的行业相似度和污染贡献指数。该模式可识别出对目标水域影响较大的点源污染行业并排序。对松花江哈尔滨段各类水域进行了行业污染源识别，影响非城市水域较大的点源污染行业主要有制药和铁矿采选工业；影响阿什河内复杂高污染水域的上游点源污染行业主要有制药、陶瓷、炼焦和造纸等工业，根据资料和污染源调查，验证识别结果合理。大顶子山工程竣工后，影响过城主干流水域的污染点源主要有制药工业、污水厂、铁矿采选和电镀工业等，相比竣工前，点源行业贡献指数降低，非点源污染因子数量增加且污染因子总数减少，表明工程的建立在一定程度上强化了水体的自净作用，产业结构政策调整或环保政策的下达实施也颇有成效。
基于双重Bootstrap方法和小波技术，本研究建立了适用于常规水质时间序列预测及其综合不确定性评价的人工神经网络模型（BWNN）。模型以Morlet基函数作为ANN激活函数，水质监测时滞作为模型输入。BWNN对朱顺屯氨氮和DO序列的预测结果满意，准确性指标NSE分别可达0.9678和0.8556，验证表明BWNN比ARIMA和其他传统ANN等模型的预测准确性和可靠性更高，对于季节性较好的氨氮序列，模型结构带来的不确定性所占比例更多；对非季节性或序列波动较大的DO序列，数据带来的不确定性所占比例更多；北方冰封河流枯水期的平均综合预测不确定性比其他水期要大10-20%。
以BWNN为基础，开展了水质时间序列预测方案优选研究。BWNN对缺失达8.3%的无插补序列预测结果仍为满意，对季节周期性较好的缺失序列，应首选时间指数平移滑动平均插补策略；对季节周期性不好的缺失序列，应首选空间多重插补策略，当同类空间区域数据不易获取时，局部平均插补可以作为优先备选策略。对有监测缺失的大顶子山断面的水质进行了预测，结果表明在未来的一段时间，COD、氨氮和TP的预测值均能达到IV类功能区标准，但预测区间上限在冬季仍有超标。
基于水环境容量控制思想和计算智能方法，设计建立了用于河流水质管理的入河排污削减模式。利用Bootstrap法和ANN建立了实用性良好的排污源强-河流水质关联模型，仅需各目标断面的实际水质监测数据和相关的排污口数据，生成的预测区间可保证削减管理的安全性，适用于多种情形。根据大中型河流和小型河流的特点，分别研究构建了单功能区排污口优化削减模式和多目标多功能区排污口联合优化削减模式，并基于智能优化技术设计了两种模式的优化算法。单功能区排污口优化削减模式可直接对排污口和目标断面水质监测数据进行反向模拟与优化，在流域尺度内具有较好的普适性；多目标多功能区排污口联合削减模式可有效产生满足系统水环境容量和削减成本目标的若干个非劣解，可根据实际问题从中选择可行解。研究区域氨氮削减实例表明，该模式可为流域水质管理提供技术支撑，并有效提高流域常规水环境管理工作的系统性。
Improving river water quality in management aspect by digital simulation modelsnot only can save resources const, but also effectively achieve the task goal. Tosolve the main technical problems of river water quality management, models foridentifying pollution sources, forecasting water quality and allocating the reductionof outlet loads, were studied based on computational intelligence (CI) methods,through investigating the current research situation at home and abroad, with theSonghua River-Harbin section as the study area.
The model for identification pollution sources to river water was establishedbased on expert system. Through the normal water quality monitoring matrix, aninterpreting mechanism was built by preliminary screening and multivariate datamining technique, by which major pollution factors and their loading water qualityindices could be obtained.Then a decision tree model was constructed based on the22classes of produced rules by experts. According to the53national industrialwater pollution discharge standards, a similarity matching model for identifying thepotential point sources of industrial pollution was established, which can calculatethe contributing rate of a certain industry on target area. The model was applied tothe Songhua River Harbin section and for outside city group, the main point sourcesordinally were medical and pharmacy、iron ores dressing. For high pollution group,the major five were pottery and porcelain production, chemical coking, traditionalChinese medicine pharmacy and pulp and paper industry depending on thecontributing rate. The validation results were reasonable. For mainstream groupafter Dadingzishan Dam Project (DDP), the main five were pharmacy, sewage plant,iron ores dressing and electroplating industries. Compared to that before DDP, thecontribution rates of point sources were decreased and the number of non-pointsources factors increases, suggesting the DDP strengthened the self cleaningcapacity of river water body and the environmental policy was also effective.
For predicting monthly water quality series and assessing the total uncertainty,a Bootstrap wavelet neural network model (BWNN) was developed based on re-Bootstrap method. The Morlet wavelet basis function (WBF) was employed asnonlinear activation function and the time-lag orders were set as the input variables. Performances of BWNN models were satisfactory and were better than ARIMA andother ANN models for NH4+-N and DO in Zhushuntun station, with respect NSE0.9678and0.8556. The uncertainty from data noise was smaller than that frommodel structure for seasonal NH4+-N series; conversely, the uncertainty from datanoise was larger for unseasonal DO series. Besides, total uncertainties in the low-flow period were10-20%bigger than other flow periods.
The optimal data missing-refilling scheme was studied for the above BWNN.Performances of BWNN were still satisfactory when the missing percentage was8.3%. Temporal method was satisfactory for filling seasonal series, whereas spatialimputation was fit for unseasonal series and the local average infilling could be aneffective alternative when the spatial data were unavailable. The case study ofDadingzishan station showed that the predictions of COD, NH4+-N and TP couldmeet the national water quality standard IV, but the upper band of predictionintervals violated the standard in some winter months.
Loads reducing allocation model of regional outlet discharge was establishedbased on water environment capacity control and the CI method. A linkage modelwas developed by bootstrap and ANN, which only needed water quality monitoringdata and discharge loads data. However, obtained prediction intervals couldguarantee the margin of safety in environmental management. Considering thecharacters of big and small rivers, reduction allocation models for single waterfunctional area (RMS) and multi-functional area (RMM) were developed,respectively. Then two intelligent optimizing algorithms were created for solvingeach model. The RMS could inversely simulate and optimize the allocation ofreduction rate of discharge loads and it had good applicability in watershed scale;the RMM could generate many noninferior solutions that could meet the balancebetween water environment capacity and reduction cost, then some solutions couldbe chosen as feasible ones for the practice. The results of NH4+-N case studyshowed that the two models could provide effective scientific supports forwatershed water quality management and would strengthen its systematicness.
基于专家系统思想研究建立了入河污染源识别模式。结合河流常规水质监测，建立了基于污染超标初筛和多元数据挖掘技术的核心水质指标解析机制，可对常规监测矩阵解析出代表污染信息的污染因子及其荷载核心水质指标。根据专家知识构建了污染源类别判定树及其22类产生式规则，基于53则国家行业水污染排放标准，设计建立了针对工业点源污染因子的行业相似度和污染贡献指数。该模式可识别出对目标水域影响较大的点源污染行业并排序。对松花江哈尔滨段各类水域进行了行业污染源识别，影响非城市水域较大的点源污染行业主要有制药和铁矿采选工业；影响阿什河内复杂高污染水域的上游点源污染行业主要有制药、陶瓷、炼焦和造纸等工业，根据资料和污染源调查，验证识别结果合理。大顶子山工程竣工后，影响过城主干流水域的污染点源主要有制药工业、污水厂、铁矿采选和电镀工业等，相比竣工前，点源行业贡献指数降低，非点源污染因子数量增加且污染因子总数减少，表明工程的建立在一定程度上强化了水体的自净作用，产业结构政策调整或环保政策的下达实施也颇有成效。
基于双重Bootstrap方法和小波技术，本研究建立了适用于常规水质时间序列预测及其综合不确定性评价的人工神经网络模型（BWNN）。模型以Morlet基函数作为ANN激活函数，水质监测时滞作为模型输入。BWNN对朱顺屯氨氮和DO序列的预测结果满意，准确性指标NSE分别可达0.9678和0.8556，验证表明BWNN比ARIMA和其他传统ANN等模型的预测准确性和可靠性更高，对于季节性较好的氨氮序列，模型结构带来的不确定性所占比例更多；对非季节性或序列波动较大的DO序列，数据带来的不确定性所占比例更多；北方冰封河流枯水期的平均综合预测不确定性比其他水期要大10-20%。
以BWNN为基础，开展了水质时间序列预测方案优选研究。BWNN对缺失达8.3%的无插补序列预测结果仍为满意，对季节周期性较好的缺失序列，应首选时间指数平移滑动平均插补策略；对季节周期性不好的缺失序列，应首选空间多重插补策略，当同类空间区域数据不易获取时，局部平均插补可以作为优先备选策略。对有监测缺失的大顶子山断面的水质进行了预测，结果表明在未来的一段时间，COD、氨氮和TP的预测值均能达到IV类功能区标准，但预测区间上限在冬季仍有超标。
基于水环境容量控制思想和计算智能方法，设计建立了用于河流水质管理的入河排污削减模式。利用Bootstrap法和ANN建立了实用性良好的排污源强-河流水质关联模型，仅需各目标断面的实际水质监测数据和相关的排污口数据，生成的预测区间可保证削减管理的安全性，适用于多种情形。根据大中型河流和小型河流的特点，分别研究构建了单功能区排污口优化削减模式和多目标多功能区排污口联合优化削减模式，并基于智能优化技术设计了两种模式的优化算法。单功能区排污口优化削减模式可直接对排污口和目标断面水质监测数据进行反向模拟与优化，在流域尺度内具有较好的普适性；多目标多功能区排污口联合削减模式可有效产生满足系统水环境容量和削减成本目标的若干个非劣解，可根据实际问题从中选择可行解。研究区域氨氮削减实例表明，该模式可为流域水质管理提供技术支撑，并有效提高流域常规水环境管理工作的系统性。
Improving river water quality in management aspect by digital simulation modelsnot only can save resources const, but also effectively achieve the task goal. Tosolve the main technical problems of river water quality management, models foridentifying pollution sources, forecasting water quality and allocating the reductionof outlet loads, were studied based on computational intelligence (CI) methods,through investigating the current research situation at home and abroad, with theSonghua River-Harbin section as the study area.
The model for identification pollution sources to river water was establishedbased on expert system. Through the normal water quality monitoring matrix, aninterpreting mechanism was built by preliminary screening and multivariate datamining technique, by which major pollution factors and their loading water qualityindices could be obtained.Then a decision tree model was constructed based on the22classes of produced rules by experts. According to the53national industrialwater pollution discharge standards, a similarity matching model for identifying thepotential point sources of industrial pollution was established, which can calculatethe contributing rate of a certain industry on target area. The model was applied tothe Songhua River Harbin section and for outside city group, the main point sourcesordinally were medical and pharmacy、iron ores dressing. For high pollution group,the major five were pottery and porcelain production, chemical coking, traditionalChinese medicine pharmacy and pulp and paper industry depending on thecontributing rate. The validation results were reasonable. For mainstream groupafter Dadingzishan Dam Project (DDP), the main five were pharmacy, sewage plant,iron ores dressing and electroplating industries. Compared to that before DDP, thecontribution rates of point sources were decreased and the number of non-pointsources factors increases, suggesting the DDP strengthened the self cleaningcapacity of river water body and the environmental policy was also effective.
For predicting monthly water quality series and assessing the total uncertainty,a Bootstrap wavelet neural network model (BWNN) was developed based on re-Bootstrap method. The Morlet wavelet basis function (WBF) was employed asnonlinear activation function and the time-lag orders were set as the input variables. Performances of BWNN models were satisfactory and were better than ARIMA andother ANN models for NH4+-N and DO in Zhushuntun station, with respect NSE0.9678and0.8556. The uncertainty from data noise was smaller than that frommodel structure for seasonal NH4+-N series; conversely, the uncertainty from datanoise was larger for unseasonal DO series. Besides, total uncertainties in the low-flow period were10-20%bigger than other flow periods.
The optimal data missing-refilling scheme was studied for the above BWNN.Performances of BWNN were still satisfactory when the missing percentage was8.3%. Temporal method was satisfactory for filling seasonal series, whereas spatialimputation was fit for unseasonal series and the local average infilling could be aneffective alternative when the spatial data were unavailable. The case study ofDadingzishan station showed that the predictions of COD, NH4+-N and TP couldmeet the national water quality standard IV, but the upper band of predictionintervals violated the standard in some winter months.
Loads reducing allocation model of regional outlet discharge was establishedbased on water environment capacity control and the CI method. A linkage modelwas developed by bootstrap and ANN, which only needed water quality monitoringdata and discharge loads data. However, obtained prediction intervals couldguarantee the margin of safety in environmental management. Considering thecharacters of big and small rivers, reduction allocation models for single waterfunctional area (RMS) and multi-functional area (RMM) were developed,respectively. Then two intelligent optimizing algorithms were created for solvingeach model. The RMS could inversely simulate and optimize the allocation ofreduction rate of discharge loads and it had good applicability in watershed scale;the RMM could generate many noninferior solutions that could meet the balancebetween water environment capacity and reduction cost, then some solutions couldbe chosen as feasible ones for the practice. The results of NH4+-N case studyshowed that the two models could provide effective scientific supports forwatershed water quality management and would strengthen its systematicness.
引文
[1]中华人民共和国国家环保总局.中国水资源公报(2000~2006)[R].2000.
[2]中华人民共和国国务院.国家环境保护“十二五”规划[S].2011.
[3]刘韬.水资源水质水量联合评价综述[J].环境科学导刊，2012，31（2）：73-78.
[4] Santhi C，Arnold J G，Williams J R. Application of a watershed model toevaluate management effects on points and nonpoint source pollution[J].American Society of Agricultural Engineers.2001，44（6）：1559–1570.
[5] Chetan M， Indrajeet C， Jennie P. Development of a multiobjectiveoptimization tool for the selection and placement of best management practicesfor nonpoint source pollution control[J].Water Resources Research.2009，45：604-626.
[6] Zessner M，Lindtner S. Estimations of municipal point source pollution in thecontext of river basin management[J].Water science and technology.2005，52：175-182.
[7]冯天瑾，丁香乾.计算智能与科学配方[M].北京：科学出版社，2008：20-21.
[8] Simeonov V, Einax J, Tsakovski S, et al. Multivariate statistical assessment ofpolluted soils[J]. Central Eurpoean Journal of Chemistry，2005，3（1）：1-9.
[9]陈敏鹏，陈吉宁，赖斯芸.中国农业和农村污染的清单分析与空间特征识别[J].中国环境科学，2006，26（6）：751-755.
[10]牛文胜,孙振海.大气扩散模式的简要回顾[J].气象科技,2000,28（2）：1-4.
[11]逄勇，陆桂华.水环境容量计算及理论应用[M].北京：科学出版社，2010：100-121.
[12] Gorden G E. Receptor models[J]. Environmental Science and Technology，1988，22（10）：1132-1142.
[13] Mencio A，MasP J. Assessment by multivariate analysis ofgroundwater-surface water interactions in urbanized Mediterraneanstreams[J]. JournalofHydrology，2008，352（3-4）：355-366.
[14]Razmkhah H，Abrishamchi A，Torkian A. Evaluation of spatial andtemporalvariation in water quality by pattern recognition techniques:a case study onJajrood River (Tehran, Iran)[J]. Journal of Environment Management，2010，91（4）：852-860.
[15]Zhang Q，Li Z W，Zeng G M，et al. Assessment of surface water qualityusing multivariatestatistical techniques in red soil hilly region: a case study ofXiangjiangwatershed, China[J]. Environment Monitoring and Assessment，2009，152（8）：123-131.
[16]Zhou F，Guo H C，Liu Y，et al. Chemometrics data analysisof marine waterquality and source identification in Southern Hong Kong[J].Marine PollutionBulletin，2007，54（6）：745-756.
[17]王帅杰，朱坦.大气颗粒物源解析技术研究进展[J].环境污染治理技术与设备，2002，3（8）：8-12.
[18]黄国兰，萧航，陈春江等.化学质量平衡法在水体污染物源解析中的应用[J].环境科学，1999，20（6）：14-17.
[19]苏丹，唐大元，刘兰岚，等.水环境污染源解析研究进展[J].生态环境学报，2009，18（2）：749-755.
[20]田晶，沈振兴，张琨，等.夏季大气降水的化学组成和来源分析[J].西安交通大学学报，2011，45（5）：108-113.
[21]KikuchiT，Furuichi T，Hai H T，et al. Assessment of Heavy Metal Pollutionin River Water of Hanoi, Vietnam Using Multivariate Analyses[J]. Bulletin ofEnvironmental Contamination and Toxicology，2009，83（4）：575-582.
[22]Singh K P，Malik A，Mohan D，et al．Multivariate statistical techniques forthe evaluation of spatial and temporal variations in water quality of GomtiRiver (India)-a case study [J].Water Research，2004，38（18）：3980-3992.
[23]Zhou F，Huang G H，Guo H C, et al.Spatio-temporal patterns and sourceapportionment of coastal water pollution in eastern Hong Kong[J]. WaterResearch，2007，41（15）：3429-3439.
[24]Shrestha S，Kazama F. Assessment of surface water quality using multivariatestatistical techniques: a case study of the Fuji river basin, Japan[J].Environmental Modelling&Software，2007，22（4）：464-475.
[25]Varol M， Sen B. Assessment of surface water quality using multivariatestatistical techniques: a case study of Behrimaz Stream, Turkey[J].Environmental Monitoring and Assessment，2009，159（1-4）：543-553.
[26]Zhang Y， Guo F， Meng W， et al. Water quality assessmentand sourceidentification of Daliao river basin using multivariate statisticalmethods[J].Environment Monitoring Assessment，2009，152（8），105-121.
[27]Li S Y，Zhang Q F. Spatial characterization of dissolved trace elements andheavy metals in the upper Han River (China) using multivariate statisticaltechniques [J].Journal of Hazardous Materials，2010，176（1-3）：579-588.
[28]王翠榆，杨永辉，周丰，等.沁河流域水体污染物时空分异特征及潜在污染源识别[J].环境科学学报，2012，32（9）：2267-2278.
[29]徐华山，徐宗学，唐芳芳，等.漳卫南运河流域水质时空变化特征及其污染源识别[J].环境科学，2012，33（2）：359-368.
[30]蔡自兴，徐光祐.人工智能及其应用(第三版)[M].北京：清华大学出版社，2007：200-206.
[31]罗宏，张惠远.环境专家系统研究进展[J].上海环境科学，2003，22（12）：359-362.
[32]韩小铮，赵淑莉，裴健.基于CBR和RBR的环境污染事故应急辅助决策专家系统[J].中国安全生产科学技术，2011，7（10）：181-185.
[33]孙新升，康彩霞，周谆，等.基于产生式规则和归结原理的环境污染事故应急处理处置专家系统[J].中国科技信息，2010，16：18-20.
[34]马勇，彭永臻，王淑莹.A/O工艺硝化与反硝化反应专家系统的建立及应用[J].中国环境科学，2005，25（2）：252-256.
[35]白乃彬，杜敏，姚贵安，等.区域环境大气质量评价专家系统[J].中国环境科学，1994，14（2）：95-100.
[36]王桂莲，白乃彬.有机工业废水中常见污染物结构与活性关系专家系统研究[J].中国环境科学，1997，17（4）：304-308.
[37]韩小铮，董文福，毛应淮.重点污染行业环境统计准专家系统制作[J].中国环境监测，2012，26（6）：42-45.
[38]郭亮.跨界河流水污染应急决策支持系统关键技术研究[D].哈尔滨工业大学博士学位论文，2011：18-19.
[39]Wang C，Feng Y J，Sun Q F，et al. A multimedia fate model to evaluate thefate of PAHs in Songhua River, China[J]. Environment Pollution，2012，164（5）：81-88.
[40]Wang C，Feng Y J，Gao P，et al. Simulation and prediction of phenoliccompounds fate in Songhua River, China[J]. Science of the Total Environment，2012，431（8）:366-374.
[41]Kim M，Gerba C P，Choi C Y. Assessment of physically-based and data-driven models to predict microbial water quality in open channels[J]. Journal ofEnvironmental Sciences-China，2010，22（6）：851-857.
[42]Wang H B.Spatial distribution of water quality based on generalized regressionneural network[C].2006IEEE International Conference on InformationAcquisition，Conference Proceedings，2006：1086-1090.
[43]Aguilera P A，Frenich G A，Torres J A，et al. Application of the Kohonenneural network in coastal water management: Methodological development forthe assessment and prediction of water quality[J]. Water Research，2001，35（17）：4053-4062.
[44]Skowronska K T，Skowronski Z G，BiziukM K. Application of a fuzzy neuralnetwork for river water quality prediction[J]. Chemia Analityczna，2006，51（3）：365-375.
[45]MuttilN， Lee J H W. Genetic programming for analysis and real-timeprediction of coastal algal blooms[J]. Ecological Modelling，2005，189（3-4）：363-376.
[46]Goethals P L M. Applications of artificial neural networks predictingmacroinvertebrates in freshwaters[J]. Aquatic Ecology,2007,41（3）：491-508.
[47]Holger R M，Ashu J，Graeme C D，et al. Methods used for the developmentof neural networks for the prediction ofwater resource variables in riversystems: Current status and future directions[J]. Environmental Modelling&Software,2010，25：891-909.
[48]宋国浩.人工神经网络在水质模拟与水质评价中的研究应用[D].重庆大学硕士学位论文，2008：35-50.
[49]郭劲松，李胜海，龙腾锐.水质模型及其应用研究进展[J].重庆建筑大学学报，2002，4（2）：109-115.
[50]卢金锁，黄廷林.基于神经网络技术的水质预测[J].数学的实践与认识，2007，9（37）：43-49.
[51]李莹，邹经湘，张宇羽，等.自适应神经网络在水质预测建模中的应用[J].系统工程，2001，19（1）：89-93.
[52]袁健，树锦.改进多元回归法与神经网络应用于水质预测[J].水资源保护，2008，24（3）：46-48.
[53]王艳琼，白秀琴.基于BP神经网络模型的水质预测及评价[J].武汉工业学院学报，2007，26（1）：64-66.
[54]Sharma S K，Tiwari K N. Bootstrap based artificial neural network (BANN)analysis for hierarchical prediction of monthly runoff in Upper Damodar ValleyCatchment[J]. Journal of Hydrology，2009，374（3-4）：209-222.
[55]Kuo J T，Hsieh M H，Lung W S，et al. Using artificial neural network forreservoir eutrophication prediction[J]. Ecological Modeling，2007，200（1-2）：171-177.
[56]郭亮，王鹏，赵英.基于BP神经网络的松花江四方台水质预测[J].哈尔滨工业大学学报，2009，41（6）：1569-1573.
[57]Jia J S，Zhao J Z，Deng H B，et al. Ecological footprint simulation andprediction by ARIMA model—A case study in Henan Province of China[J].Ecological Indice，2010，10（2）：538-544.
[58]Abaurrea J，Asín J，Cebrián A C，et al. Trend analysis of water quality seriesbased on regression models with correlated errors[J]. Journal of Hydrology，2011，400（3-4）：341-352.
[59]Tan G，Yan J，Gao C，et al. Prediction of water quality time series databased on least squares support vector machine[J].Procedia Engineering，2012，31:1194-1199.
[60]Wu J，Lu J，Wang J. Application of chaos and fractal models to water qualitytime series prediction[J]. Environment Modelling&Software，2009，24（5）：632-636.
[61]Kumar K，Jain V K. Autoregressive integrated moving averages (ARIMA)modelling of a traffic noise time series[J]. Applied Acoustics，1999，58（3）：283-294.
[62]王绪鹏，秦保平.季节ARIMA模型在于桥水库溶解氧预测中的应用[J].水资源与水工程学报，2010，21（2）：39-41.
[63]Díaz-Robles L A，Ortega J C，Fu J S，et al. A hybrid ARIMA and artificialneural networks model to forecast particulate matter in urban areas: The case ofTemuco, Chile[J]. Atmosphere Environment，2008，42（35）：8331-8340.
[64]Faruk D. A hybrid neural network and ARIMA model for water quality timeseries prediction[J]. Engineering Applications of Artificial Intelligence，2010，23（4）：586-594.
[65]Zealand C M，Burn D H，Simonovic SP. Short term streamflow forecastingusing artificial neural networks[J]. Journal of Hydrology，214（1-4）：32-48.
[66]Taormina R，Chaua K-w，Sethib R. Artificial neural network simulation ofhourly groundwater levels in a coastal aquifer system of the Venice lagoon[J].Engineering Applications of Artificial Intelligence，2012，25（8）：1670-1676.
[67]Zou P，Yang J，Fub J，et al. Artificial neural network and time series modelsfor predicting soil salt and water content[J]. Agricultural Water Management，2010，97（12）：2009-2019.
[68]Cannas B， Fanni A， See L， et al. Data preprocessing for river flowforecasting using neural networks: wavelet transforms and data partitioning[J].Physis and Chemistry of the Earth，2006，31（18）：1164-1171.
[69]Wu C L, Chau K W, Fan C. Prediction of rainfall time series using modularartificial neural networks coupled with data-preprocessing techniques[J].Journal of Hydrology，2010，389（1-2）：146-147.
[70]Adamowski J，Chan H F. A wavelet neural network conjunction model forgroundwater level forecasting[J]. Journal of Hydrology，2011，407（1-4）：28-40.
[71]PartalT，Cigizoglu H K. Prediction of daily precipitation using wavelet–neuralnetworks[J]. Hydrological Sciences Journal，2009，54（2）：234-246.
[72]Rajaee T. Wavelet and ANN combination model for prediction of dailysuspended sediment load in rivers[J]. Scienceof the Total Environment，2011，409（15）：2917-2928.
[73]Shekarrizfard M， Karimi-Jashni A， Hadad K. Wavelet transform-basedartificial neural networks (WT-ANN) in PM10pollution level estimation,basedon circular variables[J]. Environment Scienceand Pollution Research，2012，19（8）：256-268.
[74]Tiwari M K，Chatterjee C. Development of an accurate and reliable hourlyflood forecasting model using wavelet–bootstrap–ANN(WBANN)hybridapproach[J]. Jorunal of Hydrology，2010,394:458-470
[75]Zhang Q，Benveniste A. Wavelet networks[J]. IEEE Transactions on NeuralNetworks，1992，3（6）：889–898.
[76]Inouss G，Peng H，Wu J. Nonlinear time series modeling and predictionusing functional weights wavelet neural network-based state-dependent ARmodel[J]. Neurocomputing，2012，86（1）：59-74.
[77]Wang Y，Wang H，Lei X，et al. Flood simulation using parallel geneticalgorithm integrated wavelet neural networks[J]. Neurocomputing，74（17）：2734-2744.
[78]Cao J，Lin X. Study of hourly and daily solar irradiation forecast usingdiagonal recurrent wavelet neural networks[J]. Energy Converse Management，2008，49（6）：1396-1406.
[79]Beck M B. Water quality modeling: a review of the analysis of uncertainty[J].Water resources research，1987，23（8）：1393-1442.
[80]Arhami M，Kamali N，Rajabi M M，et al. Predicting hourly air pollutantlevels using artificial neural networks coupled with uncertainty analysisbyMonte Carlo simulations[J]. Environment Science and Polluttion Research，2013： doi:10.1007/s11356-012-1451-6.
[81]Heskes T. Practical confidence and prediction interval[J]. Advances in NeuralInformation Processing System，1997，9：176-182.
[82]Mazloumi E，Rose G，Currie G，et al. Prediction intervals to account foruncertainties in neural network predictions: Methodology and application inbus travel time prediction[J]. Engineering Applications of Artificial Intelligence，2011，24（7）：534-542.
[83]Khosravi A，Nahavandi S，Creighton D. A prediction interval-basedapproachto determine optimal structures of neural network metamodels[J].EngineeringApplications of Artificial Intelligence，2010，37（3）：2377-2387.
[84]Hinsbergen V，Lint V，Zuylen V. Bayesian committee ofneural networks topredict travel times with confidence intervals[J]. Transportation Research PartC，2009，17（5）：498-509.
[85]Khosravi A， Nahavandi S， Creighton D. Construction of optimalpredictionintervals for load forecasting problems[J]. IEEE Transactions onPower Systems，2010，25（3）：1496-1503.
[86]Dybowski R，Roberts S J. Confidence intervals and prediction intervalsforfeed-forward neural networks(Eds.)[M]. London：Cambridge University Press，2001：298-327.
[87]Efron B. Bootstrap methods: another look at the jackknife[J]. Annals ofStatistics，1979，7：1-26.
[88]Twomey J M，Smith A E. Bias and variance of validationmethods for functionapproximation neural networks underconditions of sparse data[J]. IEEETransaction on Systems, Man,and Cybernetics-Part C: Applications andReviews，1998，28（3）：417-430.
[89]Jia Y B，Culver T B. Bootstrapped artificial neural networks for synthetic flowgeneration with a small data sample[J]. Journal of Hydrology，2006，331（3-4）：580-590.
[90]Tiwari M K， Chatterjee C. Uncertainty assessment and ensemble floodforecasting using bootstrap based artificial neural networks (BANNs)[J].Journal of Hydrology，2010，382（1-4）：20-33.
[91] Tiwari M K，Chatterjee C. A new wavelet-bootstrap-ANN hybrid model fordaily discharge forecasting[J]. Journal of Hydroinformatics，2011，13（3）：500-519.
[92]周孝德，郭瑾珑，程文，等.水环境容量计算方法研究[J].西安理工大学学报，1999，15（3）：1-6.
[93] Chapra S C. Engineering water quality models and TMDLs[J]. Journal ofWater Resources Planning and Manangement，2003，129（4）：247-256.
[94] Haith D A. Systems analysis, TMDLs and watershed apporach[J]. Journal ofWater Resources Planning and Manangement，2003，129（4）：257-260.
[95] Li S Y， Morioka T. Optimal allocation of waste loads in a river withprobabilistic tributary flow under transverse mixing[J]. Water EnvironmentResearch，1999，71（2）：156-162.
[96] Mahjouri N， Mohammad B M.Waste Load Allocation in RiversusingFallback Bargaining[J]. Water Resources Management，2013，（1）：DOI10.1007/s11269-013-0279-2.
[97]戴正德，王蕾，马生伟，等.杞麓湖水污染总量控制和工程治理的效益分析[J].云南大学学报（自然科学版），2000，22（1）：18-19.
[98]林国强.南流江玉林城区段污染物总量控制及方案[J].广西水利水电，2002，（1）：54-56.
[99]程声通.环境信息系统[M].北京：化学工业出版社，2006，34-50.
[100]鲍琨，逄勇，孙翰.基于控制断面水质达标的水环境容量计算方法研究—以殷村港为例[J].资源科学，2011，33（2）：249-252.
[101]徐祖信，卢士强，林卫青.潮汐河网水环境容量的计算分析[J].上海环境科学，2003，22（4）：254-257.
[102]宿俊英，刘树坤，何少苓，等.太湖水环境容量的研究[J].水利学报，1992，（11）：22-26.
[103]黄真理，李玉梁，李锦绣，等.三峡水库水环境容量计算[J].水利学报，2004，（3）：7-14.
[104]邵雪.松花江哈尔滨段水质变化趋势分析与控制对策研究[D].哈尔滨工业大学硕士学位论文，2011：54-75.
[105] Deng X，Zhao Y，Wu F，et al. Analysis of the trade-off between economicgrowth and the reduction of nitrogen and phosphorus emissions in the PoyangLake Watershed, China[J]. Ecological Modeling，2011，222（8）：330-336.
[106] Xie Y L， Li Y P， Huang GH， et al. An inexact chance-constrainedprogramming model for water quality management in Binhai New Area ofTianjin,China[J]. Science of the Total Environment，2011，409（11）：1757-1773.
[107] Khan S，Faisal M N. An analytic network process model for municipal solidwaste disposal options[J]. Waste Management，2008，28（11）：1500-1508.
[108]刘首文，冯尚友.遗传算法及其在水污染控制系统规划中的应用[J].武汉水利电力大学学报，1996，29（4）：95-99.
[109]黄国如，胡和平，田富强，等.基于遗传算法的水污染控制系统规划[J].清华大学学报（自然科学版），2002，（4）：551-554.
[110] SunD Z，Yang W. Genetic algorithm solution of a gray nonlinear waterenvironment management model developed for the liming river in Daqing,China[J]. Journal of Environmental Engineering-Asce，2007，133（3）：287-293.
[111] Momtahen S， Dariane A B. Direct search approaches using geneticalgorithms for optimization of water reservoir operating policies[J]. Journal ofWater Resources Planning and Management-Asce,2007，133（3）：202-209.
[112] Chaves P，Kojiri T. Stochastic fuzzy neural network: Case study of optimalreservoir operation[J]. Journal of Water Resources Planning and Management-Asce，2007，133（6）：509-518.
[113] Kuo J T，Wang Y Y，Lung W S. A hybrid neural-genetic algorithm forreservoir water quality management[J]. Water Research，2006，40（7）：1367-1376.
[114] Wang C G，Jamieson D G. An objective approach to regional wastewatertreatment planning[J]. Water Resources Research，2002，38（3）：111-121.
[115] Gaing Z L. A particle swarm optimization approach for optimum design ofPID controller in AVR system[C]. IEEE Transactionson Energy Conversion，2004，19：384-391.
[116]杨瑞连，曾光明，李晓东.混沌粒子群算法在水污染控制系统规划中的应用[J].环境工程学报，2010，4（12）：2679-2682.
[117]宋丽华，张桂华，刘玉莲.哈尔滨市汛期特征与年变化[J].黑龙江气象，1999：7-9.
[118]赫晓彦，万亚超.哈尔滨市四方台护岸工程区水文地质条件初探[J].水利科技与经济，2011，17（11）42-43.
[119]李亚男.大顶子山工程建成后松花江哈尔滨段水质分析与污染控制[D].哈尔滨工业大学硕士学位论文，2012：22-53.
[120]张波.大顶子山航电枢纽工程建库后上游水质总量控制研究[J].环境科学与管理，2005，30（6）：58-62.
[121]洪毅，王义安，于广年.大顶子山航电枢纽河段现状条件下河床演变规律[J].水道港口，2005，26（4）：233-236.
[122]陈家厚，孙子孟，白羽军，等.大顶子山航电枢纽工程蓄水后对松花江哈尔滨江段着生藻类的影响[J].环境科学与管理，2010，35（5）：46-50.
[123] Pires J C M，Gon alves B，Azevedo F G，et al. Optimization of artificialneural network models through genetic algorithms for surface ozoneconcentration forecasting[J]. Environment Science and Pollution Research，2012，19（7）：3228-3234.
[124] Lee C M，Ko CN. Time series prediction using RBF neural networks with anonlinear time-varying evolution PSO algorithm[J]. Neurocomputing，2009，73（13）：449-460.
[125] Ko C N，Chang Y P，Wu C J. A PSO method with nonlinear time-varyingevolution for optimal design of harmonic filters[J]. IEEE Transactions onPower Systems，2009，24：437-444.
[126]中华人民共和国环境保护部.国家“十二五”重点流域水污染防治规划（2011-2015年）[R].2011.
[127] AlbertoW D， DelPilar D M， Valeria A M， et al. Pattern recognitiontechniques for the evaluationof spatial and temporal variations in waterquality. A case study: SuquiaRiver basin (Cordoba-Argentina)[J]. WaterResearch，35（5）：2881-2894.
[128]国家环境保护部.[2013-06-01].http://kjs.mep.gov.cn/hjbhbz/bzwb/shjbh/swrwpfbz/
[129] Liu C W， Lin K H， Kuo Y M. Application of factor analysis intheassessment of groundwater quality in a blackfoot disease area inTaiwan[J].Science of the Total Environment，2003，313（12）：77-89.
[130]国家环境保护部.[2013-06-01].http://datacenter.mep.gov.cn/report/getCountGraph.do?type=runQianWater
[131] Nash J E，Shutcliff J V. River flow forcasting through conceptual modelsPart I—a discussion of principles[J]. Journal of Hydrology，1970，10：282-290.
[132] Lung W S. Trends in BOD/DO modeling for wasteload allocations[J]. Journalof Environment Engineering-ASCE，1998，124，1004-1007.
[133] Yang W， Nan J， Sun D Z. An online water quality monitoring andmanagement system developed for the Liming River basin in Daqing,China[J]. Journal of Environment Management，2008，88（2）：318-325.
[134]杨军，赵宇，丁文兴.抽样调查中缺失数据的插补方法[J].数理统计与管理，2008，27（5）：821-831.
[135] Lint J W C，Hoogendoorn S P，Zuylen HJ V. Accurate freeway travel timeprediction with state-space neural networks under missing data[J].Transportation Research Part C，2005，13（2）：347-369.
[136] Schenker N，Borrud L G，BurtV L，et al. Multiple Imputation of MissingDual-Energy X-ray Absorptiometry Data in the National Health and NutritionExamination Survey[J].Statistics in Medicine，2011，30（4）：260-276.
[137]刘忠熳.松花江哈尔滨市江段地表水环境容量测算及总量控制研究[D].吉林大学硕士学位论文，2006：53-63.
[138]李静文.松花江哈尔滨段底泥中营养盐释放规律与数字模拟[D].哈尔滨工业大学硕士学位论文，2012：26-32.
[139] Wang H，Appan A，Gulliver J S. Modeling of phosphorus dynamics inaquatic sediments：I—model development[J]. Water Research，2003（37）：3928-3938.
[140] Chen C F，Ma H W，Reckhow K. Assessment of water quality managementwith a sytematic qualitative uncertainty analysis[J]. Science of the TotalEnvironment，374（20）：13-25.
[141] Reckhow K. On the need for uncertainty assessment in TMDL modeling andimplementation[J]. Journal of Water Resource Plan Management ASCE，2003，124（4）：245-246.
[142] GB3838-2002,地表水环境质量标准[S].
[143]钱荣孙.进一步强化水环境容量控制管理[N].中国建设报，2008.
[2]中华人民共和国国务院.国家环境保护“十二五”规划[S].2011.
[3]刘韬.水资源水质水量联合评价综述[J].环境科学导刊，2012，31（2）：73-78.
[4] Santhi C，Arnold J G，Williams J R. Application of a watershed model toevaluate management effects on points and nonpoint source pollution[J].American Society of Agricultural Engineers.2001，44（6）：1559–1570.
[5] Chetan M， Indrajeet C， Jennie P. Development of a multiobjectiveoptimization tool for the selection and placement of best management practicesfor nonpoint source pollution control[J].Water Resources Research.2009，45：604-626.
[6] Zessner M，Lindtner S. Estimations of municipal point source pollution in thecontext of river basin management[J].Water science and technology.2005，52：175-182.
[7]冯天瑾，丁香乾.计算智能与科学配方[M].北京：科学出版社，2008：20-21.
[8] Simeonov V, Einax J, Tsakovski S, et al. Multivariate statistical assessment ofpolluted soils[J]. Central Eurpoean Journal of Chemistry，2005，3（1）：1-9.
[9]陈敏鹏，陈吉宁，赖斯芸.中国农业和农村污染的清单分析与空间特征识别[J].中国环境科学，2006，26（6）：751-755.
[10]牛文胜,孙振海.大气扩散模式的简要回顾[J].气象科技,2000,28（2）：1-4.
[11]逄勇，陆桂华.水环境容量计算及理论应用[M].北京：科学出版社，2010：100-121.
[12] Gorden G E. Receptor models[J]. Environmental Science and Technology，1988，22（10）：1132-1142.
[13] Mencio A，MasP J. Assessment by multivariate analysis ofgroundwater-surface water interactions in urbanized Mediterraneanstreams[J]. JournalofHydrology，2008，352（3-4）：355-366.
[14]Razmkhah H，Abrishamchi A，Torkian A. Evaluation of spatial andtemporalvariation in water quality by pattern recognition techniques:a case study onJajrood River (Tehran, Iran)[J]. Journal of Environment Management，2010，91（4）：852-860.
[15]Zhang Q，Li Z W，Zeng G M，et al. Assessment of surface water qualityusing multivariatestatistical techniques in red soil hilly region: a case study ofXiangjiangwatershed, China[J]. Environment Monitoring and Assessment，2009，152（8）：123-131.
[16]Zhou F，Guo H C，Liu Y，et al. Chemometrics data analysisof marine waterquality and source identification in Southern Hong Kong[J].Marine PollutionBulletin，2007，54（6）：745-756.
[17]王帅杰，朱坦.大气颗粒物源解析技术研究进展[J].环境污染治理技术与设备，2002，3（8）：8-12.
[18]黄国兰，萧航，陈春江等.化学质量平衡法在水体污染物源解析中的应用[J].环境科学，1999，20（6）：14-17.
[19]苏丹，唐大元，刘兰岚，等.水环境污染源解析研究进展[J].生态环境学报，2009，18（2）：749-755.
[20]田晶，沈振兴，张琨，等.夏季大气降水的化学组成和来源分析[J].西安交通大学学报，2011，45（5）：108-113.
[21]KikuchiT，Furuichi T，Hai H T，et al. Assessment of Heavy Metal Pollutionin River Water of Hanoi, Vietnam Using Multivariate Analyses[J]. Bulletin ofEnvironmental Contamination and Toxicology，2009，83（4）：575-582.
[22]Singh K P，Malik A，Mohan D，et al．Multivariate statistical techniques forthe evaluation of spatial and temporal variations in water quality of GomtiRiver (India)-a case study [J].Water Research，2004，38（18）：3980-3992.
[23]Zhou F，Huang G H，Guo H C, et al.Spatio-temporal patterns and sourceapportionment of coastal water pollution in eastern Hong Kong[J]. WaterResearch，2007，41（15）：3429-3439.
[24]Shrestha S，Kazama F. Assessment of surface water quality using multivariatestatistical techniques: a case study of the Fuji river basin, Japan[J].Environmental Modelling&Software，2007，22（4）：464-475.
[25]Varol M， Sen B. Assessment of surface water quality using multivariatestatistical techniques: a case study of Behrimaz Stream, Turkey[J].Environmental Monitoring and Assessment，2009，159（1-4）：543-553.
[26]Zhang Y， Guo F， Meng W， et al. Water quality assessmentand sourceidentification of Daliao river basin using multivariate statisticalmethods[J].Environment Monitoring Assessment，2009，152（8），105-121.
[27]Li S Y，Zhang Q F. Spatial characterization of dissolved trace elements andheavy metals in the upper Han River (China) using multivariate statisticaltechniques [J].Journal of Hazardous Materials，2010，176（1-3）：579-588.
[28]王翠榆，杨永辉，周丰，等.沁河流域水体污染物时空分异特征及潜在污染源识别[J].环境科学学报，2012，32（9）：2267-2278.
[29]徐华山，徐宗学，唐芳芳，等.漳卫南运河流域水质时空变化特征及其污染源识别[J].环境科学，2012，33（2）：359-368.
[30]蔡自兴，徐光祐.人工智能及其应用(第三版)[M].北京：清华大学出版社，2007：200-206.
[31]罗宏，张惠远.环境专家系统研究进展[J].上海环境科学，2003，22（12）：359-362.
[32]韩小铮，赵淑莉，裴健.基于CBR和RBR的环境污染事故应急辅助决策专家系统[J].中国安全生产科学技术，2011，7（10）：181-185.
[33]孙新升，康彩霞，周谆，等.基于产生式规则和归结原理的环境污染事故应急处理处置专家系统[J].中国科技信息，2010，16：18-20.
[34]马勇，彭永臻，王淑莹.A/O工艺硝化与反硝化反应专家系统的建立及应用[J].中国环境科学，2005，25（2）：252-256.
[35]白乃彬，杜敏，姚贵安，等.区域环境大气质量评价专家系统[J].中国环境科学，1994，14（2）：95-100.
[36]王桂莲，白乃彬.有机工业废水中常见污染物结构与活性关系专家系统研究[J].中国环境科学，1997，17（4）：304-308.
[37]韩小铮，董文福，毛应淮.重点污染行业环境统计准专家系统制作[J].中国环境监测，2012，26（6）：42-45.
[38]郭亮.跨界河流水污染应急决策支持系统关键技术研究[D].哈尔滨工业大学博士学位论文，2011：18-19.
[39]Wang C，Feng Y J，Sun Q F，et al. A multimedia fate model to evaluate thefate of PAHs in Songhua River, China[J]. Environment Pollution，2012，164（5）：81-88.
[40]Wang C，Feng Y J，Gao P，et al. Simulation and prediction of phenoliccompounds fate in Songhua River, China[J]. Science of the Total Environment，2012，431（8）:366-374.
[41]Kim M，Gerba C P，Choi C Y. Assessment of physically-based and data-driven models to predict microbial water quality in open channels[J]. Journal ofEnvironmental Sciences-China，2010，22（6）：851-857.
[42]Wang H B.Spatial distribution of water quality based on generalized regressionneural network[C].2006IEEE International Conference on InformationAcquisition，Conference Proceedings，2006：1086-1090.
[43]Aguilera P A，Frenich G A，Torres J A，et al. Application of the Kohonenneural network in coastal water management: Methodological development forthe assessment and prediction of water quality[J]. Water Research，2001，35（17）：4053-4062.
[44]Skowronska K T，Skowronski Z G，BiziukM K. Application of a fuzzy neuralnetwork for river water quality prediction[J]. Chemia Analityczna，2006，51（3）：365-375.
[45]MuttilN， Lee J H W. Genetic programming for analysis and real-timeprediction of coastal algal blooms[J]. Ecological Modelling，2005，189（3-4）：363-376.
[46]Goethals P L M. Applications of artificial neural networks predictingmacroinvertebrates in freshwaters[J]. Aquatic Ecology,2007,41（3）：491-508.
[47]Holger R M，Ashu J，Graeme C D，et al. Methods used for the developmentof neural networks for the prediction ofwater resource variables in riversystems: Current status and future directions[J]. Environmental Modelling&Software,2010，25：891-909.
[48]宋国浩.人工神经网络在水质模拟与水质评价中的研究应用[D].重庆大学硕士学位论文，2008：35-50.
[49]郭劲松，李胜海，龙腾锐.水质模型及其应用研究进展[J].重庆建筑大学学报，2002，4（2）：109-115.
[50]卢金锁，黄廷林.基于神经网络技术的水质预测[J].数学的实践与认识，2007，9（37）：43-49.
[51]李莹，邹经湘，张宇羽，等.自适应神经网络在水质预测建模中的应用[J].系统工程，2001，19（1）：89-93.
[52]袁健，树锦.改进多元回归法与神经网络应用于水质预测[J].水资源保护，2008，24（3）：46-48.
[53]王艳琼，白秀琴.基于BP神经网络模型的水质预测及评价[J].武汉工业学院学报，2007，26（1）：64-66.
[54]Sharma S K，Tiwari K N. Bootstrap based artificial neural network (BANN)analysis for hierarchical prediction of monthly runoff in Upper Damodar ValleyCatchment[J]. Journal of Hydrology，2009，374（3-4）：209-222.
[55]Kuo J T，Hsieh M H，Lung W S，et al. Using artificial neural network forreservoir eutrophication prediction[J]. Ecological Modeling，2007，200（1-2）：171-177.
[56]郭亮，王鹏，赵英.基于BP神经网络的松花江四方台水质预测[J].哈尔滨工业大学学报，2009，41（6）：1569-1573.
[57]Jia J S，Zhao J Z，Deng H B，et al. Ecological footprint simulation andprediction by ARIMA model—A case study in Henan Province of China[J].Ecological Indice，2010，10（2）：538-544.
[58]Abaurrea J，Asín J，Cebrián A C，et al. Trend analysis of water quality seriesbased on regression models with correlated errors[J]. Journal of Hydrology，2011，400（3-4）：341-352.
[59]Tan G，Yan J，Gao C，et al. Prediction of water quality time series databased on least squares support vector machine[J].Procedia Engineering，2012，31:1194-1199.
[60]Wu J，Lu J，Wang J. Application of chaos and fractal models to water qualitytime series prediction[J]. Environment Modelling&Software，2009，24（5）：632-636.
[61]Kumar K，Jain V K. Autoregressive integrated moving averages (ARIMA)modelling of a traffic noise time series[J]. Applied Acoustics，1999，58（3）：283-294.
[62]王绪鹏，秦保平.季节ARIMA模型在于桥水库溶解氧预测中的应用[J].水资源与水工程学报，2010，21（2）：39-41.
[63]Díaz-Robles L A，Ortega J C，Fu J S，et al. A hybrid ARIMA and artificialneural networks model to forecast particulate matter in urban areas: The case ofTemuco, Chile[J]. Atmosphere Environment，2008，42（35）：8331-8340.
[64]Faruk D. A hybrid neural network and ARIMA model for water quality timeseries prediction[J]. Engineering Applications of Artificial Intelligence，2010，23（4）：586-594.
[65]Zealand C M，Burn D H，Simonovic SP. Short term streamflow forecastingusing artificial neural networks[J]. Journal of Hydrology，214（1-4）：32-48.
[66]Taormina R，Chaua K-w，Sethib R. Artificial neural network simulation ofhourly groundwater levels in a coastal aquifer system of the Venice lagoon[J].Engineering Applications of Artificial Intelligence，2012，25（8）：1670-1676.
[67]Zou P，Yang J，Fub J，et al. Artificial neural network and time series modelsfor predicting soil salt and water content[J]. Agricultural Water Management，2010，97（12）：2009-2019.
[68]Cannas B， Fanni A， See L， et al. Data preprocessing for river flowforecasting using neural networks: wavelet transforms and data partitioning[J].Physis and Chemistry of the Earth，2006，31（18）：1164-1171.
[69]Wu C L, Chau K W, Fan C. Prediction of rainfall time series using modularartificial neural networks coupled with data-preprocessing techniques[J].Journal of Hydrology，2010，389（1-2）：146-147.
[70]Adamowski J，Chan H F. A wavelet neural network conjunction model forgroundwater level forecasting[J]. Journal of Hydrology，2011，407（1-4）：28-40.
[71]PartalT，Cigizoglu H K. Prediction of daily precipitation using wavelet–neuralnetworks[J]. Hydrological Sciences Journal，2009，54（2）：234-246.
[72]Rajaee T. Wavelet and ANN combination model for prediction of dailysuspended sediment load in rivers[J]. Scienceof the Total Environment，2011，409（15）：2917-2928.
[73]Shekarrizfard M， Karimi-Jashni A， Hadad K. Wavelet transform-basedartificial neural networks (WT-ANN) in PM10pollution level estimation,basedon circular variables[J]. Environment Scienceand Pollution Research，2012，19（8）：256-268.
[74]Tiwari M K，Chatterjee C. Development of an accurate and reliable hourlyflood forecasting model using wavelet–bootstrap–ANN(WBANN)hybridapproach[J]. Jorunal of Hydrology，2010,394:458-470
[75]Zhang Q，Benveniste A. Wavelet networks[J]. IEEE Transactions on NeuralNetworks，1992，3（6）：889–898.
[76]Inouss G，Peng H，Wu J. Nonlinear time series modeling and predictionusing functional weights wavelet neural network-based state-dependent ARmodel[J]. Neurocomputing，2012，86（1）：59-74.
[77]Wang Y，Wang H，Lei X，et al. Flood simulation using parallel geneticalgorithm integrated wavelet neural networks[J]. Neurocomputing，74（17）：2734-2744.
[78]Cao J，Lin X. Study of hourly and daily solar irradiation forecast usingdiagonal recurrent wavelet neural networks[J]. Energy Converse Management，2008，49（6）：1396-1406.
[79]Beck M B. Water quality modeling: a review of the analysis of uncertainty[J].Water resources research，1987，23（8）：1393-1442.
[80]Arhami M，Kamali N，Rajabi M M，et al. Predicting hourly air pollutantlevels using artificial neural networks coupled with uncertainty analysisbyMonte Carlo simulations[J]. Environment Science and Polluttion Research，2013： doi:10.1007/s11356-012-1451-6.
[81]Heskes T. Practical confidence and prediction interval[J]. Advances in NeuralInformation Processing System，1997，9：176-182.
[82]Mazloumi E，Rose G，Currie G，et al. Prediction intervals to account foruncertainties in neural network predictions: Methodology and application inbus travel time prediction[J]. Engineering Applications of Artificial Intelligence，2011，24（7）：534-542.
[83]Khosravi A，Nahavandi S，Creighton D. A prediction interval-basedapproachto determine optimal structures of neural network metamodels[J].EngineeringApplications of Artificial Intelligence，2010，37（3）：2377-2387.
[84]Hinsbergen V，Lint V，Zuylen V. Bayesian committee ofneural networks topredict travel times with confidence intervals[J]. Transportation Research PartC，2009，17（5）：498-509.
[85]Khosravi A， Nahavandi S， Creighton D. Construction of optimalpredictionintervals for load forecasting problems[J]. IEEE Transactions onPower Systems，2010，25（3）：1496-1503.
[86]Dybowski R，Roberts S J. Confidence intervals and prediction intervalsforfeed-forward neural networks(Eds.)[M]. London：Cambridge University Press，2001：298-327.
[87]Efron B. Bootstrap methods: another look at the jackknife[J]. Annals ofStatistics，1979，7：1-26.
[88]Twomey J M，Smith A E. Bias and variance of validationmethods for functionapproximation neural networks underconditions of sparse data[J]. IEEETransaction on Systems, Man,and Cybernetics-Part C: Applications andReviews，1998，28（3）：417-430.
[89]Jia Y B，Culver T B. Bootstrapped artificial neural networks for synthetic flowgeneration with a small data sample[J]. Journal of Hydrology，2006，331（3-4）：580-590.
[90]Tiwari M K， Chatterjee C. Uncertainty assessment and ensemble floodforecasting using bootstrap based artificial neural networks (BANNs)[J].Journal of Hydrology，2010，382（1-4）：20-33.
[91] Tiwari M K，Chatterjee C. A new wavelet-bootstrap-ANN hybrid model fordaily discharge forecasting[J]. Journal of Hydroinformatics，2011，13（3）：500-519.
[92]周孝德，郭瑾珑，程文，等.水环境容量计算方法研究[J].西安理工大学学报，1999，15（3）：1-6.
[93] Chapra S C. Engineering water quality models and TMDLs[J]. Journal ofWater Resources Planning and Manangement，2003，129（4）：247-256.
[94] Haith D A. Systems analysis, TMDLs and watershed apporach[J]. Journal ofWater Resources Planning and Manangement，2003，129（4）：257-260.
[95] Li S Y， Morioka T. Optimal allocation of waste loads in a river withprobabilistic tributary flow under transverse mixing[J]. Water EnvironmentResearch，1999，71（2）：156-162.
[96] Mahjouri N， Mohammad B M.Waste Load Allocation in RiversusingFallback Bargaining[J]. Water Resources Management，2013，（1）：DOI10.1007/s11269-013-0279-2.
[97]戴正德，王蕾，马生伟，等.杞麓湖水污染总量控制和工程治理的效益分析[J].云南大学学报（自然科学版），2000，22（1）：18-19.
[98]林国强.南流江玉林城区段污染物总量控制及方案[J].广西水利水电，2002，（1）：54-56.
[99]程声通.环境信息系统[M].北京：化学工业出版社，2006，34-50.
[100]鲍琨，逄勇，孙翰.基于控制断面水质达标的水环境容量计算方法研究—以殷村港为例[J].资源科学，2011，33（2）：249-252.
[101]徐祖信，卢士强，林卫青.潮汐河网水环境容量的计算分析[J].上海环境科学，2003，22（4）：254-257.
[102]宿俊英，刘树坤，何少苓，等.太湖水环境容量的研究[J].水利学报，1992，（11）：22-26.
[103]黄真理，李玉梁，李锦绣，等.三峡水库水环境容量计算[J].水利学报，2004，（3）：7-14.
[104]邵雪.松花江哈尔滨段水质变化趋势分析与控制对策研究[D].哈尔滨工业大学硕士学位论文，2011：54-75.
[105] Deng X，Zhao Y，Wu F，et al. Analysis of the trade-off between economicgrowth and the reduction of nitrogen and phosphorus emissions in the PoyangLake Watershed, China[J]. Ecological Modeling，2011，222（8）：330-336.
[106] Xie Y L， Li Y P， Huang GH， et al. An inexact chance-constrainedprogramming model for water quality management in Binhai New Area ofTianjin,China[J]. Science of the Total Environment，2011，409（11）：1757-1773.
[107] Khan S，Faisal M N. An analytic network process model for municipal solidwaste disposal options[J]. Waste Management，2008，28（11）：1500-1508.
[108]刘首文，冯尚友.遗传算法及其在水污染控制系统规划中的应用[J].武汉水利电力大学学报，1996，29（4）：95-99.
[109]黄国如，胡和平，田富强，等.基于遗传算法的水污染控制系统规划[J].清华大学学报（自然科学版），2002，（4）：551-554.
[110] SunD Z，Yang W. Genetic algorithm solution of a gray nonlinear waterenvironment management model developed for the liming river in Daqing,China[J]. Journal of Environmental Engineering-Asce，2007，133（3）：287-293.
[111] Momtahen S， Dariane A B. Direct search approaches using geneticalgorithms for optimization of water reservoir operating policies[J]. Journal ofWater Resources Planning and Management-Asce,2007，133（3）：202-209.
[112] Chaves P，Kojiri T. Stochastic fuzzy neural network: Case study of optimalreservoir operation[J]. Journal of Water Resources Planning and Management-Asce，2007，133（6）：509-518.
[113] Kuo J T，Wang Y Y，Lung W S. A hybrid neural-genetic algorithm forreservoir water quality management[J]. Water Research，2006，40（7）：1367-1376.
[114] Wang C G，Jamieson D G. An objective approach to regional wastewatertreatment planning[J]. Water Resources Research，2002，38（3）：111-121.
[115] Gaing Z L. A particle swarm optimization approach for optimum design ofPID controller in AVR system[C]. IEEE Transactionson Energy Conversion，2004，19：384-391.
[116]杨瑞连，曾光明，李晓东.混沌粒子群算法在水污染控制系统规划中的应用[J].环境工程学报，2010，4（12）：2679-2682.
[117]宋丽华，张桂华，刘玉莲.哈尔滨市汛期特征与年变化[J].黑龙江气象，1999：7-9.
[118]赫晓彦，万亚超.哈尔滨市四方台护岸工程区水文地质条件初探[J].水利科技与经济，2011，17（11）42-43.
[119]李亚男.大顶子山工程建成后松花江哈尔滨段水质分析与污染控制[D].哈尔滨工业大学硕士学位论文，2012：22-53.
[120]张波.大顶子山航电枢纽工程建库后上游水质总量控制研究[J].环境科学与管理，2005，30（6）：58-62.
[121]洪毅，王义安，于广年.大顶子山航电枢纽河段现状条件下河床演变规律[J].水道港口，2005，26（4）：233-236.
[122]陈家厚，孙子孟，白羽军，等.大顶子山航电枢纽工程蓄水后对松花江哈尔滨江段着生藻类的影响[J].环境科学与管理，2010，35（5）：46-50.
[123] Pires J C M，Gon alves B，Azevedo F G，et al. Optimization of artificialneural network models through genetic algorithms for surface ozoneconcentration forecasting[J]. Environment Science and Pollution Research，2012，19（7）：3228-3234.
[124] Lee C M，Ko CN. Time series prediction using RBF neural networks with anonlinear time-varying evolution PSO algorithm[J]. Neurocomputing，2009，73（13）：449-460.
[125] Ko C N，Chang Y P，Wu C J. A PSO method with nonlinear time-varyingevolution for optimal design of harmonic filters[J]. IEEE Transactions onPower Systems，2009，24：437-444.
[126]中华人民共和国环境保护部.国家“十二五”重点流域水污染防治规划（2011-2015年）[R].2011.
[127] AlbertoW D， DelPilar D M， Valeria A M， et al. Pattern recognitiontechniques for the evaluationof spatial and temporal variations in waterquality. A case study: SuquiaRiver basin (Cordoba-Argentina)[J]. WaterResearch，35（5）：2881-2894.
[128]国家环境保护部.[2013-06-01].http://kjs.mep.gov.cn/hjbhbz/bzwb/shjbh/swrwpfbz/
[129] Liu C W， Lin K H， Kuo Y M. Application of factor analysis intheassessment of groundwater quality in a blackfoot disease area inTaiwan[J].Science of the Total Environment，2003，313（12）：77-89.
[130]国家环境保护部.[2013-06-01].http://datacenter.mep.gov.cn/report/getCountGraph.do?type=runQianWater
[131] Nash J E，Shutcliff J V. River flow forcasting through conceptual modelsPart I—a discussion of principles[J]. Journal of Hydrology，1970，10：282-290.
[132] Lung W S. Trends in BOD/DO modeling for wasteload allocations[J]. Journalof Environment Engineering-ASCE，1998，124，1004-1007.
[133] Yang W， Nan J， Sun D Z. An online water quality monitoring andmanagement system developed for the Liming River basin in Daqing,China[J]. Journal of Environment Management，2008，88（2）：318-325.
[134]杨军，赵宇，丁文兴.抽样调查中缺失数据的插补方法[J].数理统计与管理，2008，27（5）：821-831.
[135] Lint J W C，Hoogendoorn S P，Zuylen HJ V. Accurate freeway travel timeprediction with state-space neural networks under missing data[J].Transportation Research Part C，2005，13（2）：347-369.
[136] Schenker N，Borrud L G，BurtV L，et al. Multiple Imputation of MissingDual-Energy X-ray Absorptiometry Data in the National Health and NutritionExamination Survey[J].Statistics in Medicine，2011，30（4）：260-276.
[137]刘忠熳.松花江哈尔滨市江段地表水环境容量测算及总量控制研究[D].吉林大学硕士学位论文，2006：53-63.
[138]李静文.松花江哈尔滨段底泥中营养盐释放规律与数字模拟[D].哈尔滨工业大学硕士学位论文，2012：26-32.
[139] Wang H，Appan A，Gulliver J S. Modeling of phosphorus dynamics inaquatic sediments：I—model development[J]. Water Research，2003（37）：3928-3938.
[140] Chen C F，Ma H W，Reckhow K. Assessment of water quality managementwith a sytematic qualitative uncertainty analysis[J]. Science of the TotalEnvironment，374（20）：13-25.
[141] Reckhow K. On the need for uncertainty assessment in TMDL modeling andimplementation[J]. Journal of Water Resource Plan Management ASCE，2003，124（4）：245-246.
[142] GB3838-2002,地表水环境质量标准[S].
[143]钱荣孙.进一步强化水环境容量控制管理[N].中国建设报，2008.