基于神经网络的城市内湖水华预警综合建模方法研究
|
摘要
针对城市内湖水华产生过程存在复杂性、时变性、不确定性等特点,运用内集-外集、粗糙集约简和RBF神经网络模型,通过水华藻生物量阈值界定、风险概率计算、预警等级划分、预警因子识别和神经网络预测模型的研究,提出一种城市内湖水华预警综合建模方法.以天津清净湖为例,利用p H值、水温等12项水质指标监测数据,确定清净湖水华的叶绿素a浓度阈值为70.98?g/L,依据水华风险概率划分5个水华预警等级,并确定水温、溶解氧、高锰酸盐指数和TDS为水华预警因子.利用RBF神经网络技术构建清净湖水华预警模型,验证结果显示,模型预测精度达85.7%,表明该方法能较好地用于城市内湖水华预警模型构建.
Formation process of water bloom was complicated, time-varied and uncertain. So far water bloom prediction of urban lake was still difficult. An integrated modeling approachby using interior-outer-set, rough sets reduction algorithm and RBF neural network model was proposed for early-warning of water bloom risk. Interior-outer-set model was employed to define the threshold of chlorophyll a for predictingwater bloom risk, and a method was put forward for calculating the risk probability of water bloom.Rough sets reduction algorithm was used to identify the keydriving factors ofwater bloom. An early-warning model of water bloom risk was developed based on RBF neural network model. Feasibility of themodeling approach was proved though the application in Qingjing Lake. The results indicated thatthe threshold value of chlorophyll a was 70.98?g/L; water bloom risk was divided into five grades based on the risk probability of water bloom; fourwater quality indexes including water temperature, dissolved oxygen, permanganate index and total dissolved solids were identified as the indicators of water bloom. Result of model validation showed that the RBF neural network model's accurate rate exceeded 85%, and could be applied to early-warning of water bloom risk in Qingjing Lake.
Formation process of water bloom was complicated, time-varied and uncertain. So far water bloom prediction of urban lake was still difficult. An integrated modeling approachby using interior-outer-set, rough sets reduction algorithm and RBF neural network model was proposed for early-warning of water bloom risk. Interior-outer-set model was employed to define the threshold of chlorophyll a for predictingwater bloom risk, and a method was put forward for calculating the risk probability of water bloom.Rough sets reduction algorithm was used to identify the keydriving factors ofwater bloom. An early-warning model of water bloom risk was developed based on RBF neural network model. Feasibility of themodeling approach was proved though the application in Qingjing Lake. The results indicated thatthe threshold value of chlorophyll a was 70.98?g/L; water bloom risk was divided into five grades based on the risk probability of water bloom; fourwater quality indexes including water temperature, dissolved oxygen, permanganate index and total dissolved solids were identified as the indicators of water bloom. Result of model validation showed that the RBF neural network model's accurate rate exceeded 85%, and could be applied to early-warning of water bloom risk in Qingjing Lake.
引文
[1]孔繁翔,马荣华,高俊峰,等.太湖蓝藻水华的预防、预测和预警的理论与实践[J].湖泊科学,2009,21(3):314-328.
[2]王华,杨树平,房晟忠,等.滇池浮游植物群落特征及与环境因子的典范对应分析[J].中国环境科学,2016,36(2):544-552.
[3]王雪蕾,王新新,朱利,等.巢湖流域氮磷面源污染与水华空间分布遥感解析[J].中国环境科学,2015,35(5):1511-1519.
[4]王小艺,唐丽娜,刘载文,等.城市湖库蓝藻水华形成机理[J].化工学报,2012,63(5):1492-1497.
[5]Coad P,Cathers B,Ball J E,et al.Proactive management of estuarine algal blooms using an automated monitoring buoy coupled with an artificial neural network[J].Environmental Modeling&Software,2014,61:393-409.
[6]陈云峰,殷福才,陆根法.水华爆发的突变模型-以巢湖为例[J].生态学报,2006,26(3):878-883.
[7]JΦrgensen S E.Structural dynamic model[J].Ecological Modeling,1986,31:1-9.
[8]Kirchner W B,Dillon P J.Comment on an empirical method of estimating the retention of phosphorus in lakes[J].Water Researches,1975,2(1):182-183.
[9]Wool T A,Ambrose R B,Martin J L,et a1.Water Quality Analysis Simulation Program(WASP)Version6.0,DRAFF:User’s Manual[M].Georgia:U S Environmental Protection Agency-Region,Atlanta.2001:22-28.
[10]张质明,王晓燕,李明涛.基于全局敏感性分析方法的WASP模型不确定性分析[J].中国环境科学,2014,34(5):1336-1346.
[11]Vivian P,Roberto J C.Qual2E model for the Corumbata′?River[J].Ecological Modelling,2006,198:269-275.
[12]Mehmet Y,Erdal K,Ridvan B.Simulation of river streams:Comparison of a new technique with QUAL2E[J].Mathematical and Computer Modelling,2007,46:292-305.
[13]常旭,王黎,李芬,等.Mike 11模型在浑河流域水质预测中的应用[J].水电能源科学,2013,31(6):58-62.
[14]Cracknell A P,Newcombe S K,Black A F,et al.The ABDMAP(algal bloom detection,monitoring and prediction)concerted action[J].International Journal of Remote Sensing,2001,22(2/3):205-247.
[15]郑剑锋,李付宽,孙力平.滨海地区混盐水体富营养化主因子识别与分析-以天津市清净湖为例[J].环境科学学报,2016,36(3):785-791.
[16]Chen Q,Mynett A E.Predicting phaeocystisglobosa bloom in Dutch coastal waters by decision trees and non-linear piecewise regression[J].Ecological Modeling,2004,176:277-290.
[17]曾勇,杨志峰,刘静玲.城市湖泊水华预警模型研究-以北京“六海”为例[J].水科学进展,2007,18(1):79-85.
[18]Wei B,Sugiura N,Maekawa T.Use of artificial neural net-work in the prediction of algal blooms[J].Water Research,2001,35(8):2022-2028.
[19]蔡煜东,汪列,姚林声,等.水质富营养化程度的人工神经网络决策模型[J].中国环境科学,1995,15(2):123-127.
[20]卢小燕,徐福留,詹巍,等.湖泊富营养化模型的研究现状与发展趋势[J].水科学进展,2003,14(6):792-798.
[21]国家环境保护总局水和废水监测分析方法编委会.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.
[22]Huang C F.Demonstration of benefit of information distribution for probability estimation[J].Signal Processing,2000,80(6):1037-1048.
[23]黄崇福.内集-外集模型的计算机仿真检验[J].自然灾害学报,2002,11(3):62-70.
[24]Pawlak Z,Skowron A.Rudiments of rough sets[J].Information Sciences,2007,177(1):3-27.
[25]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[26]张家瑞,曾勇,赵彦伟.白洋淀湿地水华暴发阈值分析[J].生态学杂志,2011,30(8):1744-1750.
[27]赵军,王国胤,吴中福,等.基于粗集理论的数据离散化方法[J].小型微型计算机系统,2004,25(1):60-64.
[28]李元萍,李元良.粗糙集约简算法的研究与实现[J].矿业研究与开发,2008,28(4):48-50.
[2]王华,杨树平,房晟忠,等.滇池浮游植物群落特征及与环境因子的典范对应分析[J].中国环境科学,2016,36(2):544-552.
[3]王雪蕾,王新新,朱利,等.巢湖流域氮磷面源污染与水华空间分布遥感解析[J].中国环境科学,2015,35(5):1511-1519.
[4]王小艺,唐丽娜,刘载文,等.城市湖库蓝藻水华形成机理[J].化工学报,2012,63(5):1492-1497.
[5]Coad P,Cathers B,Ball J E,et al.Proactive management of estuarine algal blooms using an automated monitoring buoy coupled with an artificial neural network[J].Environmental Modeling&Software,2014,61:393-409.
[6]陈云峰,殷福才,陆根法.水华爆发的突变模型-以巢湖为例[J].生态学报,2006,26(3):878-883.
[7]JΦrgensen S E.Structural dynamic model[J].Ecological Modeling,1986,31:1-9.
[8]Kirchner W B,Dillon P J.Comment on an empirical method of estimating the retention of phosphorus in lakes[J].Water Researches,1975,2(1):182-183.
[9]Wool T A,Ambrose R B,Martin J L,et a1.Water Quality Analysis Simulation Program(WASP)Version6.0,DRAFF:User’s Manual[M].Georgia:U S Environmental Protection Agency-Region,Atlanta.2001:22-28.
[10]张质明,王晓燕,李明涛.基于全局敏感性分析方法的WASP模型不确定性分析[J].中国环境科学,2014,34(5):1336-1346.
[11]Vivian P,Roberto J C.Qual2E model for the Corumbata′?River[J].Ecological Modelling,2006,198:269-275.
[12]Mehmet Y,Erdal K,Ridvan B.Simulation of river streams:Comparison of a new technique with QUAL2E[J].Mathematical and Computer Modelling,2007,46:292-305.
[13]常旭,王黎,李芬,等.Mike 11模型在浑河流域水质预测中的应用[J].水电能源科学,2013,31(6):58-62.
[14]Cracknell A P,Newcombe S K,Black A F,et al.The ABDMAP(algal bloom detection,monitoring and prediction)concerted action[J].International Journal of Remote Sensing,2001,22(2/3):205-247.
[15]郑剑锋,李付宽,孙力平.滨海地区混盐水体富营养化主因子识别与分析-以天津市清净湖为例[J].环境科学学报,2016,36(3):785-791.
[16]Chen Q,Mynett A E.Predicting phaeocystisglobosa bloom in Dutch coastal waters by decision trees and non-linear piecewise regression[J].Ecological Modeling,2004,176:277-290.
[17]曾勇,杨志峰,刘静玲.城市湖泊水华预警模型研究-以北京“六海”为例[J].水科学进展,2007,18(1):79-85.
[18]Wei B,Sugiura N,Maekawa T.Use of artificial neural net-work in the prediction of algal blooms[J].Water Research,2001,35(8):2022-2028.
[19]蔡煜东,汪列,姚林声,等.水质富营养化程度的人工神经网络决策模型[J].中国环境科学,1995,15(2):123-127.
[20]卢小燕,徐福留,詹巍,等.湖泊富营养化模型的研究现状与发展趋势[J].水科学进展,2003,14(6):792-798.
[21]国家环境保护总局水和废水监测分析方法编委会.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.
[22]Huang C F.Demonstration of benefit of information distribution for probability estimation[J].Signal Processing,2000,80(6):1037-1048.
[23]黄崇福.内集-外集模型的计算机仿真检验[J].自然灾害学报,2002,11(3):62-70.
[24]Pawlak Z,Skowron A.Rudiments of rough sets[J].Information Sciences,2007,177(1):3-27.
[25]葛哲学,孙志强.神经网络理论与MATLAB R2007实现[M].北京:电子工业出版社,2007.
[26]张家瑞,曾勇,赵彦伟.白洋淀湿地水华暴发阈值分析[J].生态学杂志,2011,30(8):1744-1750.
[27]赵军,王国胤,吴中福,等.基于粗集理论的数据离散化方法[J].小型微型计算机系统,2004,25(1):60-64.
[28]李元萍,李元良.粗糙集约简算法的研究与实现[J].矿业研究与开发,2008,28(4):48-50.