基于神经网络的藻类水华建模与预测研究
|
摘要
本文的研究工作主要着眼于利用神经网络模型对藻类水华进行建模和预测。一方面期望通过结合敏感分析方法来促进我们对于环境因素对藻类水华影响的认识,另一方面期望能够获得具有良好性能的藻类水华预测模型。
论文第一章首先介绍水体富营养化和藻类水华问题,以及藻类水华建模研究的主要目的。然后对藻类水华建模(藻类生物量建模)的研究文献进行综述,并介绍了神经网络方法在这一领域的应用。最后,在文献综述的基础上提出了本文的主要研究方法和研究内容。
第二章是BP神经网络在滇池藻类水华建模的实证研究。滇池是一个水体浑浊的浅水湖泊,位于中国的西南地区。自1985年以来,滇池已经遭受过多次严重的水华,引起水华发生的藻类中最主要的是微囊藻(Microcystis spp.)。在水华极端严重的情形下,滇池中藻类生物量曾超过每升30亿个。为了预测滇池中微囊藻(Microcystis spp.)的生物量变化以及探索微囊藻(Microcystis spp.)生物量的动力学特性,作者开发了一个基于BP神经网络的模型。将模型预测的藻类生物量和实际观测值进行相关分析,相关系数R2(correlation coefficient)达到0.911。基于训练后得到的神经网络,我们进行了敏感分析。敏感分析的主要目的是研究不同环境因素的变化对微囊藻(Microcystis spp.)生物量变化的影响。敏感分析的结果表明一个较小的pH增量,可以引起微囊藻(Microcystis spp.)生物量的显著减少。并且,针对原始数据的进一步研究表明:微囊藻(Microcystis spp.)生物量对pH值升高的反应依赖于藻类生物量本身以及pH值的高低。当滇池中微囊藻(Microcystis spp.)生物量和pH值处于中等或较低水平时,pH值的增加更倾向于引起微囊藻(Microcystis spp.)生物量的增加;反之,当滇池中微囊藻(Microcystis spp.)生物量和pH值处于较高水平时,pH值的增加则倾向于引起微囊藻(Microcystis spp.)生物量的减少。总之,滇池中微囊藻生物量对pH变化的独特反应特性可由极高的藻类生物量和较高的pH值水平的来进行解释。本章还对其它环境变量的变化对藻类生物量的影响进行了阐述。所有环境变量中,水温一个标准差的增量对微囊藻(Microcystis spp.)生物量的正面影响最强。化学需氧量(chemical oxygen demand,COD)和总磷(total phosphorus,TP)也和微囊藻(Microcystis spp.)生物量具有较强的正相关性。而总氮(total nitrogen,TN)、五日生物需氧量(biological oxygen demand in five days,BOD5)和溶解氧(dissolved oxygen,DO)与微囊藻(Microcystis spp.)生物量之间只有较弱的相关性。此外,透明度(transparency,Tr)和微囊藻(Microcystis spp.)生物量之间具有中等程度的正相关。
第三章将径向基函数(Radial basis function,RBF)神经网络应用于澳大利亚Darling河的水华建模研究。结果表明,训练后RBF神经网络能够准确预测Darling河中引起水华的两种主要藻种,Nostocales spp(.后文简写为Nostocales)和Anabaena spp.(后文简写为Anabaena),的生物量。同时,我们还进行了敏感分析研究,以阐明Nostocales和Anabaena的生物量动力学特征。敏感分析的结果表明,总动氮(total kinetic nitrogen)对这两类藻的生长都有非常强的正面影响。其次,水电导率与这两类藻的藻生物量之间具有非常强的负相关关系。第三,河水流量也确认为水华形成的一个非常突出的原因。在本章中,我们还通过散点图技术较为形象地展现了较高的河水流量可以显著减少两种藻的藻生物量这一事实。最后,研究结果表明其它变量,如透明度、水颜色和pH值,对Darling河水华的形成没有前面所述因素那么重要。
第四章通过分析澳大利亚Darling河Nostocales藻(Nostocales spp.)的历史数据,首先阐明Nostocales藻(Nostocales spp.)生物量时间序列的非平稳特性。进而说明淡水生态系统倾向于呈现出非平稳特性,而不是平稳特性。而非平稳特性则意味着只有系统“近期的过去”才能够预测系统“近期的未来”。然而,在所有过去的藻生态预测和建模的研究工作中,研究者都没有认真对待和关注系统的非平稳特性。在本章的研究中,作者构造了一种结合时间窗口技术的径向基函数神经网络方法来进行非平稳藻生态时间序列的建模与预测研究,并具体用来预测Darling河Nostocales藻(Nostocales spp.)生物量时间序列。结果表明,结合时间窗口技术的径向基函数神经网络模型能够有效地预测Nostocales藻(Nostocales spp.)水华的发生及其强度。此外,基于多个结合不同尺寸时间窗口的径向基函数神经网络模型,我们特别构造了一个智能组合器将多个径向基函数模型的预测结果进行智能选择,并得到了比单个径向基函数模型更好的预测结果。
第五章对全文进行总结,并对未来的研究进行了展望。
This paper focuses on the modeling and forecasting algal blooms using neural networks. While we want to further our knowledge with neural network models incorporated with sensitivity analysis, we also want to realize some forecasting models with good performance.
Chapter 1 introduced first the eutrophication, algal blooms problem, and the purpose of modeling algal blooms. Then the previous researches were summarized, and the applications of neural networks in this field were introduced. In the end of the chapter, the main research methods and research efforts in this paper were outlined.
The empirical research of modeling algal blooms in Lake Dianchi by BP neural network was outlined in Chapter 2. Lake Dianchi is a shallow and turbid lake, located in Southwest China. Since 1985, Lake Dianchi has experienced severe cyanabacterial blooms (dominated by Microcystis spp.). In extreme cases, the algal cell densities have exceeded three billion cells per liter. To predict and elucidate the population dynamics of Microcystis spp. in Lake Dianchi, a neural network based model was developed. The correlation coefficient (R2) between the predicted algal concentrations by the model and the observed values was 0.911. Sensitivity analysis was performed to clarify the algal dynamics to the changes of environmental factors. The results of sensitivity analysis based on the trained neural network model suggested that small increases in pH could cause significant reduction of algal abundance. And further researches revealed that the response of Microcystis spp. biomass to pH increase depended on the algal biomass itself and the pH level. With moderate or low level of algal biomass and pH in Lake Dianchi, pH increase was likely to lead to an increase of Microcystis spp. biomass. Otherwise, when pH and algal biomass were high, pH increase was likely to reduce the Microcystis spp. biomass. It is concluded that the extremely high concentration of algal population and high pH could explain the distinctive response of Microcystis spp. population to +1 SD (standard deviation) pH increase in Lake Dianchi. Further, another hypothesis presented in the paper was that the higher abundance of algal population and the higher pH, an increase of pH would be more likely to have a negative (or strong negative) influence on algal growth in an extremely high eutrophicated water such as Lake Dianchi. And the paper also elucidated the algal dynamics to changes of other environmental factors. One SD (standard deviation) increase of water temperature (WT) had strongest positive relationship with Microcystis spp. biomass. Chemical oxygen demand (COD) and total phosphorus (TP) had strong positive effect on Microcystis spp. abundance while total nitrogen (TN), biological oxygen demand in five days (BOD5), and dissolved oxygen had only weak relationship with Microcystis spp. concentration. And transparency (Tr) had moderate positive relationship with Microcystis spp. concentration.
In Chapter 3, radial basis function (RBF) neural network were applied for modelling the abundance of cyanobacteria. The trained RBF neural network could predict with high accuracy the population of the two bloom forming algal taxa, Nostocales spp. and Anabaena spp., in River Darling, Australia. To elucidate the dynamics of algal population for both Nostocales spp. and Anabaena spp. Sensitivity analysis was performed. Some hypothesis could be obtained from the results of sensitivity analysis. First, total kinetic nitrogen had a very strong influence on the abundance of the two algal taxa. Second, electrical conductivity had a very strong negative relation with the population of the two algal species. In other words, more dissolved salts or ions in the water, the algal population are more likely to decrease. Third, flow was identified as one predominant factor on algal blooms after scatter plot clarified the fact that high flow could reduce significantly the algal biomass for both Nostocales spp. and Anabaena spp. in River Darling. Other variables such as turbidity, colour, and pH were less important in determining the abundance and succession of the algal blooms.
Chapter 4 demonstrated first the nonstationarity of algal population behaviors by analyzing the historical populations of Nostocales spp. in the River Darling, Australia. Freshwater ecosystems were more likely to be nonstationary, instead of stationary. And nonstionarity implies that only the near past behaviors could forecast the near future for the system. However, nonstionarity was not considered seriously in previous research efforts for modeling and predicting algal population behaviors. Therefore the moving window technique was incorporated with radial basis function neural network (RBFNN) approach to deal with nonstationarity when modeling and forecasting the population behaviors of Nostocales spp. in the River Darling. The results showed that the RBFNN model could predict the timing and magnitude of algal blooms of Nostocales spp. with high accuracy. Moreover, a combined model based on individual RBFNN models was implemented, which showed superiority over the individual RBFNN models. Hence, the combined model was recommended for the modeling and forecasting the phytoplankton populations, especially for the forecasting.
The last chapter concluded the paper and made some comments on further researches.
论文第一章首先介绍水体富营养化和藻类水华问题,以及藻类水华建模研究的主要目的。然后对藻类水华建模(藻类生物量建模)的研究文献进行综述,并介绍了神经网络方法在这一领域的应用。最后,在文献综述的基础上提出了本文的主要研究方法和研究内容。
第二章是BP神经网络在滇池藻类水华建模的实证研究。滇池是一个水体浑浊的浅水湖泊,位于中国的西南地区。自1985年以来,滇池已经遭受过多次严重的水华,引起水华发生的藻类中最主要的是微囊藻(Microcystis spp.)。在水华极端严重的情形下,滇池中藻类生物量曾超过每升30亿个。为了预测滇池中微囊藻(Microcystis spp.)的生物量变化以及探索微囊藻(Microcystis spp.)生物量的动力学特性,作者开发了一个基于BP神经网络的模型。将模型预测的藻类生物量和实际观测值进行相关分析,相关系数R2(correlation coefficient)达到0.911。基于训练后得到的神经网络,我们进行了敏感分析。敏感分析的主要目的是研究不同环境因素的变化对微囊藻(Microcystis spp.)生物量变化的影响。敏感分析的结果表明一个较小的pH增量,可以引起微囊藻(Microcystis spp.)生物量的显著减少。并且,针对原始数据的进一步研究表明:微囊藻(Microcystis spp.)生物量对pH值升高的反应依赖于藻类生物量本身以及pH值的高低。当滇池中微囊藻(Microcystis spp.)生物量和pH值处于中等或较低水平时,pH值的增加更倾向于引起微囊藻(Microcystis spp.)生物量的增加;反之,当滇池中微囊藻(Microcystis spp.)生物量和pH值处于较高水平时,pH值的增加则倾向于引起微囊藻(Microcystis spp.)生物量的减少。总之,滇池中微囊藻生物量对pH变化的独特反应特性可由极高的藻类生物量和较高的pH值水平的来进行解释。本章还对其它环境变量的变化对藻类生物量的影响进行了阐述。所有环境变量中,水温一个标准差的增量对微囊藻(Microcystis spp.)生物量的正面影响最强。化学需氧量(chemical oxygen demand,COD)和总磷(total phosphorus,TP)也和微囊藻(Microcystis spp.)生物量具有较强的正相关性。而总氮(total nitrogen,TN)、五日生物需氧量(biological oxygen demand in five days,BOD5)和溶解氧(dissolved oxygen,DO)与微囊藻(Microcystis spp.)生物量之间只有较弱的相关性。此外,透明度(transparency,Tr)和微囊藻(Microcystis spp.)生物量之间具有中等程度的正相关。
第三章将径向基函数(Radial basis function,RBF)神经网络应用于澳大利亚Darling河的水华建模研究。结果表明,训练后RBF神经网络能够准确预测Darling河中引起水华的两种主要藻种,Nostocales spp(.后文简写为Nostocales)和Anabaena spp.(后文简写为Anabaena),的生物量。同时,我们还进行了敏感分析研究,以阐明Nostocales和Anabaena的生物量动力学特征。敏感分析的结果表明,总动氮(total kinetic nitrogen)对这两类藻的生长都有非常强的正面影响。其次,水电导率与这两类藻的藻生物量之间具有非常强的负相关关系。第三,河水流量也确认为水华形成的一个非常突出的原因。在本章中,我们还通过散点图技术较为形象地展现了较高的河水流量可以显著减少两种藻的藻生物量这一事实。最后,研究结果表明其它变量,如透明度、水颜色和pH值,对Darling河水华的形成没有前面所述因素那么重要。
第四章通过分析澳大利亚Darling河Nostocales藻(Nostocales spp.)的历史数据,首先阐明Nostocales藻(Nostocales spp.)生物量时间序列的非平稳特性。进而说明淡水生态系统倾向于呈现出非平稳特性,而不是平稳特性。而非平稳特性则意味着只有系统“近期的过去”才能够预测系统“近期的未来”。然而,在所有过去的藻生态预测和建模的研究工作中,研究者都没有认真对待和关注系统的非平稳特性。在本章的研究中,作者构造了一种结合时间窗口技术的径向基函数神经网络方法来进行非平稳藻生态时间序列的建模与预测研究,并具体用来预测Darling河Nostocales藻(Nostocales spp.)生物量时间序列。结果表明,结合时间窗口技术的径向基函数神经网络模型能够有效地预测Nostocales藻(Nostocales spp.)水华的发生及其强度。此外,基于多个结合不同尺寸时间窗口的径向基函数神经网络模型,我们特别构造了一个智能组合器将多个径向基函数模型的预测结果进行智能选择,并得到了比单个径向基函数模型更好的预测结果。
第五章对全文进行总结,并对未来的研究进行了展望。
This paper focuses on the modeling and forecasting algal blooms using neural networks. While we want to further our knowledge with neural network models incorporated with sensitivity analysis, we also want to realize some forecasting models with good performance.
Chapter 1 introduced first the eutrophication, algal blooms problem, and the purpose of modeling algal blooms. Then the previous researches were summarized, and the applications of neural networks in this field were introduced. In the end of the chapter, the main research methods and research efforts in this paper were outlined.
The empirical research of modeling algal blooms in Lake Dianchi by BP neural network was outlined in Chapter 2. Lake Dianchi is a shallow and turbid lake, located in Southwest China. Since 1985, Lake Dianchi has experienced severe cyanabacterial blooms (dominated by Microcystis spp.). In extreme cases, the algal cell densities have exceeded three billion cells per liter. To predict and elucidate the population dynamics of Microcystis spp. in Lake Dianchi, a neural network based model was developed. The correlation coefficient (R2) between the predicted algal concentrations by the model and the observed values was 0.911. Sensitivity analysis was performed to clarify the algal dynamics to the changes of environmental factors. The results of sensitivity analysis based on the trained neural network model suggested that small increases in pH could cause significant reduction of algal abundance. And further researches revealed that the response of Microcystis spp. biomass to pH increase depended on the algal biomass itself and the pH level. With moderate or low level of algal biomass and pH in Lake Dianchi, pH increase was likely to lead to an increase of Microcystis spp. biomass. Otherwise, when pH and algal biomass were high, pH increase was likely to reduce the Microcystis spp. biomass. It is concluded that the extremely high concentration of algal population and high pH could explain the distinctive response of Microcystis spp. population to +1 SD (standard deviation) pH increase in Lake Dianchi. Further, another hypothesis presented in the paper was that the higher abundance of algal population and the higher pH, an increase of pH would be more likely to have a negative (or strong negative) influence on algal growth in an extremely high eutrophicated water such as Lake Dianchi. And the paper also elucidated the algal dynamics to changes of other environmental factors. One SD (standard deviation) increase of water temperature (WT) had strongest positive relationship with Microcystis spp. biomass. Chemical oxygen demand (COD) and total phosphorus (TP) had strong positive effect on Microcystis spp. abundance while total nitrogen (TN), biological oxygen demand in five days (BOD5), and dissolved oxygen had only weak relationship with Microcystis spp. concentration. And transparency (Tr) had moderate positive relationship with Microcystis spp. concentration.
In Chapter 3, radial basis function (RBF) neural network were applied for modelling the abundance of cyanobacteria. The trained RBF neural network could predict with high accuracy the population of the two bloom forming algal taxa, Nostocales spp. and Anabaena spp., in River Darling, Australia. To elucidate the dynamics of algal population for both Nostocales spp. and Anabaena spp. Sensitivity analysis was performed. Some hypothesis could be obtained from the results of sensitivity analysis. First, total kinetic nitrogen had a very strong influence on the abundance of the two algal taxa. Second, electrical conductivity had a very strong negative relation with the population of the two algal species. In other words, more dissolved salts or ions in the water, the algal population are more likely to decrease. Third, flow was identified as one predominant factor on algal blooms after scatter plot clarified the fact that high flow could reduce significantly the algal biomass for both Nostocales spp. and Anabaena spp. in River Darling. Other variables such as turbidity, colour, and pH were less important in determining the abundance and succession of the algal blooms.
Chapter 4 demonstrated first the nonstationarity of algal population behaviors by analyzing the historical populations of Nostocales spp. in the River Darling, Australia. Freshwater ecosystems were more likely to be nonstationary, instead of stationary. And nonstionarity implies that only the near past behaviors could forecast the near future for the system. However, nonstionarity was not considered seriously in previous research efforts for modeling and predicting algal population behaviors. Therefore the moving window technique was incorporated with radial basis function neural network (RBFNN) approach to deal with nonstationarity when modeling and forecasting the population behaviors of Nostocales spp. in the River Darling. The results showed that the RBFNN model could predict the timing and magnitude of algal blooms of Nostocales spp. with high accuracy. Moreover, a combined model based on individual RBFNN models was implemented, which showed superiority over the individual RBFNN models. Hence, the combined model was recommended for the modeling and forecasting the phytoplankton populations, especially for the forecasting.
The last chapter concluded the paper and made some comments on further researches.
引文
[1]刘健康译,联合国环境规划署国际环境技术中心.湖泊与水库富营养化防治的理论与实践.北京:科学出版社,2003.
[2]郑建军,钟成华,邓春光.试论水华的定义.水资源保护,2006,22(5): 45-48.
[3] Gamini H. Freshwater algal blooms and their control: Comparison of the European and Australian experience. Journal of Environmental Management, 1997, 51: 217-227.
[4]杨士建.骆马湖富营养化发生机制与防治途径初探.水资源保护,2004,3:26-28.
[5]方如康.环境学词典.北京:科学出版社,2003:125.
[6]王苏民,窦鸿身.中国湖泊志.北京:科学出版社,1998:120.
[7]中国科学院南京地理与湖泊研究所.科研人员提出蓝藻水华形成机理研究新思路[EB/OL].[2004-05-04].http://www.cas.ac.cn/html/dir/2004/05/04/3177.htm.
[8]张维昊,徐小清,丘昌强.水环境中微囊藻毒素研究进展.环境科学研究, 2001, 14(2): 57-61.
[9] Liu Y., Han M., Liang Z., and Lin Y. Influence of light intensity, temperature and nutrients on the growth of Microcystis in water of Dianchi Lake. Res. Environ. Sci., 1995, 8: 7-11.
[10]赵影,王志强,杨志平,谢春平,范琼,王勇.巢湖取水口浮游藻类污染调查.环境与健康杂志,2002,19(4):316-318.
[11]刘建康,谢平.揭开武汉东湖蓝藻水华消失之谜.长江流域资源与环境, 1999, 8(3): 312-319.
[12]张哲海.玄武湖蓝藻水华应急治理成效分析.污染防治技术, 2006, 19(5): 56-59.
[13] [奚万艳,吴鑫,叶文瑾,杨虹.太湖梅梁湾水域蓝藻水华前与水华末期细菌群落结构的变化.应用与环境生物学报,2007,13(1): 97-103.
[14]刘家寿,陈文祥,黄永川,胡传林,彭建华,朱爱民,吴晓辉,常秀岭.浮桥河水库的营养状况与水质调控措施.长江流域资源与环境, 2001, 10(4): 360-364.
[15]方云英,杨肖娥,濮培民,常会庆,丁学锋.宁波力洋水库富营养化现状及生态治理对策.水土保持学报, 2004, 18(6): 183-186.
[16]金春华,陆开宏,王扬才,吴科锋,吕振平,孙游云.浙江省3座饮用水水库的蓝藻控制对策及效果.水利渔业, 2005, 25(3): 50-55.
[17]苏玉萍,陈娜蓉,林婉珍,梁晓丹.福建省山仔水库浮游植物特征与水体富营养状况分析.亚热带资源与环境学报, 2006, 1(2): 48-54.
[18]张娟,梁前进,周云龙,包智泓,李启军.官厅水库水体中微囊藻毒素及其与微囊藻细胞密度相关性研究.安全与环境学报, 2006, 6(5):53-56.
[19]刘昂俊,余华章,赵孟绪,韩博平.汤溪水库富营养化特征与水质管理对策.生态科学, 2006, 25(3): 193-197.
[20]卢大远,刘培刚,范天俞,彭辉,张政科.汉江下游突发“水华”的调查研究.环境科学研究, 2000, 13(2):28-31.
[21]周广杰,况琪军,胡征宇,蔡庆华.三峡库区四条支流藻类多样性评价及“水华”防治.中国环境科学, 2006,26(3):337-341.
[22]孙军,刘东艳,杨世民,郭健,钱树本.渤海中部和渤海海峡及邻近海域浮游植物群落结构的初步研究.海洋与湖沼, 2002, 33(5): 461-471.
[23]孙丕喜,王波,张朝晖,王宗灵,夏滨.莱州湾海水中营养盐分布与富营养化的关系.海洋科学进展, 2006, 24(3): 329-335.
[24]杜佳垠.大连黄海沿岸海域针胞藻类有毒有害赤潮生物.河北渔业,2005,1: 25-26.
[25]崔毅,陈碧鹃,陈聚法.黄渤海海水养殖自身污染的评估.应用生态学报, 2005, 16(1): 180-185.
[26]李肖娜,周伟华,刘素美,张经.东海赤潮高发区沉积物中叶绿素的分析.应用生态学报, 2003, 14(7):1102-1106.
[27]田荣湘.东亚季风与东海赤潮.浙江大学学报(理学版), 2005, 32(3): 355-360.
[28]潘雪峰,张鹰,张东,刘吉堂.海州湾圆筛藻与环境因子的关系研究.环境监测管理与技术, 2007, 19(1): 15-18.
[29]曾祥波,黄邦钦,陈纪新,洪华生.台湾海峡小型浮游动物的摄食对夏季藻华演替的影响.海洋学报, 2006, 28(5): 107-116.
[30]杨清良,林更铭.厦门海域浮游植物夏季赤潮期间分布变异的多元分析.生态学报, 2007, 27(2): 465-476.
[31]刘晓南,王为,吴志峰.广东沿海赤潮发生频率差异与城市发展的关系.地理学报, 2004, 59(6): 911-917.
[32]冷科明,江天久.深圳海域近20年赤潮发生的特征分析.生态科学, 2004, 23(2): 166-170.
[33]翁焕新,孙向卫,陈静峰,陈建芳,陈立红,陈祥华,秦亚超.珠江口沉积铁-磷的富集对赤潮频发的潜在作用.中国科学D辑-地球科学, 2006, 36(12): 1122-1130.
[34]刘沛然,黄先玉,柯栋.赤潮成因及预报方法.海洋预报, 1999, 16(4): 46-51.
[35]王洪礼,冯剑丰.赤潮生态动力学.天津:天津大学出版社,2006: 4-6.
[36] Takamura N., Qtsuki A., Aizaki M., and Nojiri Y. Phytoplankton species shift accompanied by transition from nitrogen to phosphorus dependence of primary production in Lake Kasumigaura, Japan. Arch. Hydrobiol.,1992, 124: 129-148.
[37] Jeong K.S., Kim D.K., Whigham P., and Joo G.J. Modeling Microcystis aeruginosa bloom dynamics in the Nakdong River by means of evolutionary computation and statistical approach. Ecological Modelling, 2003, 161: 67-78.
[38] Maier H.R., Dandy G.C. Modelling cyanobacterial (blue-green algae) in the River Murray using artificial neural networks. Mathematics and computers in Simulation, 1997, 43: 377-386.
[39] Maier H.R., Dandy G. C. Neural Network Based Modelling of Environmental Variables: A Systematic Approach. Mathematical and computer modeling, 2001, 33: 669-682.
[40] Fahnenstiel G.L., Lang G.A., Nalepa T.F., and Johengen T.H. Effects of zebra mussel (Dreissena polymorpha) colonization on water quality parameters in Saginaw Bay, Lake Huron. J. Great Lake Res., 1995, 21: 435-448.
[41] Jennifer L. Graham. Environmental factors influencing Microcystin distributionand concentration in Midwestern lakes. Ph.D. thesis. University of Missouri- Columbia, USA, 2004.
[42] Scott Neil Higgins. Modeling the growth dynamics of Cladophora in eastern Lake Erie. Ph.D. thesis. University of Waterloo, Canada, 2005.
[43] Whitehead P. & Hornberger G. Modelling algal behaviour in the River Thames. Wat. Res., 1984, 18: 945-953.
[44] Smith V.H., Willen B. and Karlsson B. Predicting the summer peak biomass of four species of blue-green algae in Swedish lakes. Water Resour. Bull., 1987, 23(3): 397-402.
[45] Reisenhofer E., Picciotto A. and Donfang L. A factor analysis approach to the study of the eutrophication of a shallow, temperature lake (San Daniele, North Eastern Italy). Analytic Chimica Acta, 1995, 306: 99-106.
[46] Perona E., Bonilla I. and Mateo P. Spatial and temporal changes in water quality in a Spanish river. Sci. Total Environ., 1999, 241: 75-90.
[47] Pingree R.D., Pugh P.R., Holligan P.M., Forster, G.R. Summer phytoplankton blooms and red tides along tidal fronts in the approaches to the English Channel. Nature, 1975, 258: 672– 677.
[48] Anne-Marie B., Michel R. and Noriyuld I. Tide versus eutrophication, impacts on ostracods populations structure of Mikawa Bay (Japan). REVUE DE MICROPALIONTOLOGIE, 1997, 40(1): 3-13.
[49] Voravit C.and Piamsak M. Water pollution and habitat degradation in the Gulf of Thailand. Marine Pollution Bulletin, 2003, 47: 43-51.
[50] Casas B., Varela M., Canle M., Gonza N. and Bodea A. Seasonal Variations of Nutrients, Seston and Phytoplankton, and Upwelling Intensity off La Coru?a (NW Spain). Estuarine, Coastal and Shelf Science, 1997, 44: 767–778.
[51] Raine R. and McMahon T. Physical dynamics on the continental shelf off southwestern Ireland and their influence on coastal phytoplankton blooms. Continental Shelf Research, 1998, 18: 883-914.
[52] Riyad S. M., Fuad A. A., Mohammad Y. R. et al.Patterns of summer vertical and horizontal currents in coastal waters of the northern Gulf of Aqaba, Red Sea. Estuarine, Coastal and Shelf Science, 2006, 69: 567-579.
[53] Rosalba A. and Ochoa J.L. Hydrology of winter–spring“red tides”in Bahía de Mazatlán, Sinaloa, México. Harmful Algae, 2004, 3:163-171.
[54] Werbos, P.J. Beyond regression: new tools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard University, 1974.
[55] Werbos, P.J. Generalization of backpropagation with application to a recurrent gas market model. Neural Networks, 1988, 1: 339-356.
[56] Rumelhart, D.E., Hinton, G.E., Williams, R.J. Learning representations by backpropagation errors. Nature, 1986, 323(6188):533-536.
[57] Weigend, A.S., Huberman, B.A., Rumelhart, D.E. Predicting the future: A connectionist approach. International Journal of Neural Systems, 1990, 1: 193-209.
[58] Weigend, A.S., Rumelhart, D.E., Huberman, B.A. Generalization by weight-elimination with application to forecasting. Advances in Neural Information Processing Systems, 1991, 3:875-882.
[59] Cottrell, M., Girard, B., Girard, Y., Mangeas, M., Muller, C. Neural modeling for time series: a statistical stepwise method for weight elimination. IEEE Transactions on Neural Networks, 1995, 6(6): 1355-1364.
[60] Tang, Z., Almeida, C., Fishwick, P.A. Time series forecasting using neural networks vs Box-Jenkins methodology. Simulation, 1991, 57(5): 303-310.
[61] Sharda, R., Patil, R.B. Connectionist approach to time series prediction: An empirical test. Journal of Intelligent Manaufacturing, 1992, 3: 317-323.
[62] Celik A.E. and Karatepe Y. Evaluating and forecasting banking crises through neural network models: An application for Turkish banking sector. Expert Systems with Applications, 2007, 33(4):809-815.
[63] Engin M., Demira? S., Engin E.Z. et al. The classification of human tremor signals using artificial neural network. Expert Systems with Applications, 2007, 33(3):754-761.
[64] Grznar J., Prasad S. and Tata J. Neural networks and organizational systems: Modeling non-linear relationships. European Journal of Operational Research, 2007, 181(2): 939-955.
[65] Ráduly B., Gernaey K.V., Capodaglio A.G. et al. Artificial neural networks for rapid WWTP performance evaluation: Methodology and case study. Environmental Modelling & Software, 2007, 22(8): 1208-1216.
[66] Zou H., Xia G., Yang F. and Yang H. A neural network model based on the multi-stage optimization approach for short-term food price forecasting in China. Expert Systems with Applications, 2007, 33(2): 347-356.
[67] Hagan M.T., Demuth H.B. and Beale M.H. Neural Network Design. Boston, MA: PWS Publishing, 1996.
[68] Tzafestas S.G., Dalianis P.J., Anthopoulos G. On the overtraining phenomenon of backpropagation neural networks. Mathematics and Computers in Simulation, 1996, 40: 507-521.
[69] Amari S.-i., Murata N.K.-R., Finke M., Yang H.H. Asymptotic statistical theory of overtraining and cross-validation. IEEE trans. on Neural Networks, 1997, 8(5): 985-996.
[70] Rivals I. and Personnaz L. On cross validation for model selection. Neural computation, 1999, 11: 863-870.
[71] Girosi F., Jones M. and Poggio T. Regularization theory and neural networks architectures. Neural computation, 1995,7: 219-269.
[72] Chen D.D. and Hagan M.T. Optimal use of regularization and cross validation in neural network modeling. Proceedings of the 1999 International Joint Conference on Neural Networks, 1999, 2: 1275-1280.
[73] Haykin Simon. Neural networks: a comprehensive foundation. New Jersey: Prentice Hall, Inc., 1999.
[74] White H. Connectionist nonparametric regression: multilayer feedforwardnetworks can learn arbitrary mappings. Neural networks, 1990, 3: 535-549.
[75] Fontova M. V., Oliveira A.R.L. and Lyra C. Warm start by Hopfield neural networks for interior point methods. Computers & Operations Research, 2007, 34(9): 2553-2561.
[76] Sun T.H., Chen M., Lo S. et al. Face recognition using 2D and disparity eigenface Expert Systems with Applications, 2007, 33(2):265-273.
[77] Al-Assaf Y. and Kadi H.E. Fatigue life prediction of composite materials using polynomial classifiers and recurrent neural networks. Composite Structures, 2007, 77(4): 561-569.
[78] Ren T.J. and Chen T.C. Robust speed-controlled induction motor drive based on recurrent neural network. Electric Power Systems Research, 2006, 76(12): 1064-1074.
[79] Mandal S. and Prabaharan N. Ocean wave forecasting using recurrent neural networks. Ocean Engineering, 2006, 33(10): 1401-1410.
[80] Lin C.M., Huang J.J., Gen M. and Tzeng G.H. Recurrent neural network for dynamic portfolio selection. Applied Mathematics and Computation, 2006, 175(2): 1139-1146.
[81] Broomhead D.S., Lowe D. Multi-variable functional interpolation and adaptive networks. Complex Syst., 1988, 2: 321–55.
[82] Yao X.J., Zhang X.Y., Zhang R.S. et al. Prediction of enthalpy of alkanes by the use of radial basis function neural networks. Computers and Chemistry, 2001, 25: 475–482.
[83] Dibike Y. B. and Solomatlne D. P. River Flow Forecasting Using Artificial Neural Networks. Phys. Chem. Earth(B), 2001, 26(1):1-7.
[84] Rivas V.M., Merelo J.J., Castillo P.A. et al. Evolving RBF neural networks for time-series forecasting with EvRBF. Information Sciences, 2004, 165: 207-220.
[85] Morelli M.J., Montagna G., Nicrosini O. et al. Pricing financial derivatives with neural networks. Physica A, 2004, 338: 160-165.
[86] Zhang Aishe and Zhang Ling. RBF neural networks for the prediction of building interference effects. Computers & Structures, 2004, 82: 2333-2339.
[87] Santos A.P., Costa N.A. and Coelho L.S. Computational intelligence approaches and linear models in case studies of forecasting exchange rates. Expert Systems with Applications, 2007, 33(4): 816-823.
[88] Bierman V.J. Mathematical model of the selective enhancement of blue-green algae by nutrient enrichment. In Recknagel F., ANNA-artificial neural network model for predicting species abundance and succession of blue-green algae, Hydrobiologia, 1976, 349(1997):47-57.
[89] Okada M. & Aiba S. Simulation of water blooms in a eutrophic lake: Modeling the vertical migration in a population of Microcystis aeruginosa. Wat. Res., 1983, 20: 485-490.
[90] Reynolds F.M. The ecology of freshwater phytoplankton. Cambridge: Cambridge University Press, 1984: 384.
[91] Sakamoto M. Primary production by phytoplankton community in some Japanese lakes and its dependence on lake depth. Arch. Hydrobiol., 1966, 62: 1-28.
[92] Dillon P.J. & Rigler F.H. The phosphorus-chlorophyll relationship in lakes. Limnol. Oceanogr., 1975, 19: 767-773.
[93] Recknagel F., Petzoldt T., Jaeke O., Krusche F. Hybrid expert system DELAQUA– a toolkit for water quality control of lakes and reservoirs. Ecol. Modelling, 1994, 71: 17-36.
[94] Quchia. Simalation of red tide by means of multiple regression and fourier analysis. Bull. Jap. Soc. Sci. Fish, 1986, 52(2):203-207.
[95]洪君超,黄秀清,蒋晓山等.嵊山水域中肋骨条藻赤潮发生过程主导因子分析.海洋学报.1993, 15(6):135-141.
[96]黄良民,钱宏林,李锦蓉.大鹏湾赤潮多发区的叶绿素a分布与环境关系初探.海洋与湖沼,1994,25(2):197-205.
[97]林永水,邱德全,周近明.小等刺硅鞭藻赤潮的成因.中国赤潮研究及SCOR-IOC赤潮工作组中国委员会第二次会议论文选.青岛:青岛出版社,1996:48-53.
[98] [98]赵明桥,李攻科,张展霞.应用多元回归法研究赤潮特征有机物与赤潮关系.中山大学学报(自然科学版),2003,42(1): 35-39.
[99]谢中华.运用混合回归模型预报赤潮.海洋技术,2004,23(1): 27-30.
[100] Altrock C. Fuzzy logic and neuro fuzzy applications explained. New Jersey: Prentice Hall, 1995.
[101] Czogala J. Fuzzy and neuro-fuzzy intelligent systems. New York: Physica - Verlag, 2000.
[102] Chen Q.W. and Mynett A.E. Integration of data mining techniques and heuristic knowledge in fuzzy logic modeling of algal biomass in the north sea. Second international workshop on coastal eutrophication (proceedings), Nov. 2002. Chongqin: China.
[103] Soyupak S. and Chen D.G. Fuzzy logic model to estimate seasonal pseudo steady state chlorophyll-a concentration in reseroviors. Environmental Modeling Assessment, 2004, 9(1): 51-59.
[104] Marsili L.S. Fuzzy prediction of the algal blooms in the Orbetello Lagoon. Environmental Modeling and Software, 2004, 19(9): 799-808.
[105] French M. and Recknagel F.. Modelling of algal blooms in freshwaters using artificial neural networks. In: Zanetti P.(Editor), Computer Techniques in Environmental Studies V. Vol. II: Environmental Systems. Southampton, Boston: Computational Mechanics Publications, 1994: 87-94.
[106] Recknagel F., 1997. ANNA– Artificial neural network model for predicting species abundance and succession of blue-green algae. Hydrobiologia, 349: 47-57.
[107] Recknagel F., French M., Harkonen P., Yabunaka K.I. Artificial neural network approach for modelling prediction of algal blooms. Ecol. Modelling, 1997, 96: 11-28.
[108] Yabunaka K.I., Hosomi M. and Murakami A. Novel application of a back-propagation artificial neural network model formulated to predict algal bloom.Wat. Sci. Tech., 1997, 36(5): 89-97.
[109] Wei B., Sugiura N. and Maekawa T. Use of artificial neural network in the prediction of algal blooms. Water Resource, 2001,35(8): 2022–2028.
[110] Maier H.R., Dandy G.C., Burch M.D. Use of artificial neural networks for modeling cyanobacterial Anabaena app. in the River Murray, South Australia. Ecological Modelling, 1998, 105: 257-272.
[111] Hou G.X., Song L.R., Liu J.T. et al. Modeling of cyanobacterial blooms in hypereutrophic Lake Dianchi, China. Journal of Freshwater Ecology, 2004, 19(4): 623-629.
[112] Walter M., Recknagel F., Carpenter C., Bormans M. Predicting eutrophication effects in the Burrenjuck Reservoir (Australia) by means of the deterministic model SALMO and the recurrent neural network model ANNA. Ecological Modelling, 2001, 146: 97-113.
[113] Jeong K.S., Joo G.J., Kim H.W., Ha K., Recknagel F. Prediction and elucidation of phytoplankton dynamics in the Nakdong River (Korea) by means of a recurrent neural network. Ecological Modelling, 2001, 146: 115-129.
[114] Jeong K.S., Recknagel F., Joo G.J. Prediction and elucidation of population dynamics of the blue-green algae Microcystis aeruginosa and the diatom Stephanodiscus hantzschii in the Nakdong River-Reservior systems (South Korea) by a recurrent artificial neural network. In: Recknagel F., Ecological Informatics(2nd Edition). NY: Springer-Verlag, 2005: 255-273.
[115] Rechnagel F., Welk A., Kim B. and Takamura N. Artificial neural network approach to unravel and forecast algal population dynamics of two lakes different in morphometry and eutrophication. In: Recknagel F., Ecological Informatics(2nd Edition). NY: Springer-Verlag, 2005: 325-345.
[116]孙蓉桦,张微. GRNN和遗传算法在赤潮预报中的应用操作.科技通报, 2005, 21(4):485-490.
[117]吴京洪,杨秀环,唐宝英,张展霞,李锦蓉.人工神经网络预报浮游植物生长趋势的研究.中山大学学报(自然科学版), 2000, 39(6): 54-59.
[118]蔡如钰.基于人工神经网络的夜光藻密度预测模型.中国环境监测,2001,17(3): 52-55.
[119]王洪礼,沈菲,冯剑丰,孙景.基于人工神经网络的浮游植物密度预测模型研究.气象水文海洋仪器,2004, 3(4): 26-29.
[120]杨建强,罗先香,丁德文,秦洁.赤潮预测的人工神经网络方法初步研究.海洋科学进展,2003,21(3): 318-324.
[121]王洪礼,葛根,李悦雷.基于模糊神经网络(FNN)的赤潮预警预测研究.海洋通报,2006, 25(4): 36-41.
[122] ZHANG Rong, YAN Hong, DU Liping. Research on Prediction of Red Tide Based on Fuzzy Neural Network. Marine Science Bulletin, 2006, 8(1): 83-92.
[123]马玉梅,高静宇,王清华.基于人工神经网络的赤潮预测模型.海洋预报,2007,24(1): 38-44.
[124]杨建强,高振会,孙培艳,石强,李钦亮.自组织神经网络在有害赤潮预警研究中的应用.海洋环境科学, 2003, 22(1): 6-9.
[125] Zar J.H. Biostatistical Analysis, 2nd edition. NJ: Prentice-Hall, 1984: 718.
[126] Jin X. and Tu Q. Methods for Research of Eutrophicated Lakes, 2nd edition. Beijing: Meteorological Press, 1990.
[127] Ma X.X., He X.J., Zhao D.Q., and Wang X.Y. Influence of B-P networks hidden layer on water quality evaluation result. International Journal Hydroelectric Energy, 2002, 20: 16-18.
[128] Xiong L.H., Guo S.L., Wang Y. Study and application of artificial neural network in real time flood forecasting. International Journal Hydroelectric Energy, 2002, 20: 28-31.
[129] Xu S.G. and Wang J. Fuzzy optimal decision for structure of feedforward neural networks and its application in runoff forecast. International Journal of Hydroelectric Energy, 2002, 20: 35-37.
[130] MathWorks Inc. Neural Network Toolbox: User’s Guide (Matlab 7.0). MA: TheNatick, 2004.
[131] Goh A.T.C. Back-propagation neural networks for modeling complex systems. Artif. Intel. Eng. 1995, 9: 143-151.
[132] Lek S., Delacoste M., Baran P., Dimopoulos I., Lauga J., and Aulagner S. Application of neural networks to modeling non-linear relationships in ecology. Ecological Modelling,1996, 90: 39-52.
[133] Siginer I. Some artificial neural network applications to greenhouse environmental control. Comput. Electron. Agric.,1997, 18: 167-186.
[134] Dimopoulos Y., Chronopoulos J., Chronopoulou S.A., and Lek S. Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city. Ecological Modelling, 1999, 120: 157-165.
[135] Stumm W. and Morgan J.J. Aquatic Chemistry. New York: Wiley, 1970.
[136] Shapiro J. Current beliefs regarding dominance of by blue-greens: the case for the importance of CO2 and pH. Verh. Int. Verein. Limnol., 1990, 24: 38-54.
[137] Sommer U., Gliwica Z.M., Lampert W., and Duncan A. The PEG-model of seasonal succession of planktonic events in fresh waters, Arch. Hydrobiol., 1986, 106: 443-471.
[138] Kromkamp J. and Walsby A.E. A computer model of buoyancy and vertical migration in cyanobacteria, J. Plankton Res., 1990, 12: 161-183.
[139] Reynolds C.S. The River Handbook: Hydrological and Ecological Principles, Vol. 1. Oxford: Blackwell Scientific Publication, 1992: 526.
[140] Park J, Sandberg I.W. Universal approximation using radial basis functions network, Neural Computing, 1991, 3: 246–257.
[141] Bianchini M., Frasconi P. and Gori M. Learning without local minima in radial basis function networks. IEEE Trans. Neural Networks, 1995, 6:749–56.
[142] Moody J. and Darken C. Faster learning in networks of locally tuned processing units, Neural Computing, 1989, 1, 281–294.
[143] Sheta A.F. and Jong K. Time-series forecasting using GA-tuned radial basisfunctions, Information Sciences, 2001, 133(3–4): 221–228.
[144] Chen, S., Cowan C.F.N., and Grant P. M. Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks, IEEE Transactions on Neural Networks, 1991, 2(2): 302-309.
[145] Suttle C.A. and Harrison P.J. Ammonium and phosphate uptake rates, N:P supply ratios, and evidence for N and P limitation in some oligotrophic lakes. Limnol. Oceanogr., 1988, 33(2): 186-202.
[146] Moss B. Ecology of Fresh Waters: Man and Medium, Past to Future, 3rd Edition. Oxford: Blackwell Science, 1998: 557.
[147] Shapiro J. Blue-green algae: why they become dominant. Science, 1973, 179: 382-384.
[148] Harris G.P. Plankton Ecology– Stucture, Function, and Fluctuation. NY: Chapman and Hall, 1986: 384.
[149] Bowerman B.L. and Connell R. Forecasting and Time Series, 3rd Edition. Peking: China Machine Press, 2003.
[150] Morantz B.H. Weighted window method for time series forecasting with an artificial neural network, Ph.D. Dissertation, Robinson College of Business, Georgia State University, 2002.
[151] Poggio T. and Girosi F. Networks for approximation and learning. Proceeding of IEEE, 1990, 78.
[2]郑建军,钟成华,邓春光.试论水华的定义.水资源保护,2006,22(5): 45-48.
[3] Gamini H. Freshwater algal blooms and their control: Comparison of the European and Australian experience. Journal of Environmental Management, 1997, 51: 217-227.
[4]杨士建.骆马湖富营养化发生机制与防治途径初探.水资源保护,2004,3:26-28.
[5]方如康.环境学词典.北京:科学出版社,2003:125.
[6]王苏民,窦鸿身.中国湖泊志.北京:科学出版社,1998:120.
[7]中国科学院南京地理与湖泊研究所.科研人员提出蓝藻水华形成机理研究新思路[EB/OL].[2004-05-04].http://www.cas.ac.cn/html/dir/2004/05/04/3177.htm.
[8]张维昊,徐小清,丘昌强.水环境中微囊藻毒素研究进展.环境科学研究, 2001, 14(2): 57-61.
[9] Liu Y., Han M., Liang Z., and Lin Y. Influence of light intensity, temperature and nutrients on the growth of Microcystis in water of Dianchi Lake. Res. Environ. Sci., 1995, 8: 7-11.
[10]赵影,王志强,杨志平,谢春平,范琼,王勇.巢湖取水口浮游藻类污染调查.环境与健康杂志,2002,19(4):316-318.
[11]刘建康,谢平.揭开武汉东湖蓝藻水华消失之谜.长江流域资源与环境, 1999, 8(3): 312-319.
[12]张哲海.玄武湖蓝藻水华应急治理成效分析.污染防治技术, 2006, 19(5): 56-59.
[13] [奚万艳,吴鑫,叶文瑾,杨虹.太湖梅梁湾水域蓝藻水华前与水华末期细菌群落结构的变化.应用与环境生物学报,2007,13(1): 97-103.
[14]刘家寿,陈文祥,黄永川,胡传林,彭建华,朱爱民,吴晓辉,常秀岭.浮桥河水库的营养状况与水质调控措施.长江流域资源与环境, 2001, 10(4): 360-364.
[15]方云英,杨肖娥,濮培民,常会庆,丁学锋.宁波力洋水库富营养化现状及生态治理对策.水土保持学报, 2004, 18(6): 183-186.
[16]金春华,陆开宏,王扬才,吴科锋,吕振平,孙游云.浙江省3座饮用水水库的蓝藻控制对策及效果.水利渔业, 2005, 25(3): 50-55.
[17]苏玉萍,陈娜蓉,林婉珍,梁晓丹.福建省山仔水库浮游植物特征与水体富营养状况分析.亚热带资源与环境学报, 2006, 1(2): 48-54.
[18]张娟,梁前进,周云龙,包智泓,李启军.官厅水库水体中微囊藻毒素及其与微囊藻细胞密度相关性研究.安全与环境学报, 2006, 6(5):53-56.
[19]刘昂俊,余华章,赵孟绪,韩博平.汤溪水库富营养化特征与水质管理对策.生态科学, 2006, 25(3): 193-197.
[20]卢大远,刘培刚,范天俞,彭辉,张政科.汉江下游突发“水华”的调查研究.环境科学研究, 2000, 13(2):28-31.
[21]周广杰,况琪军,胡征宇,蔡庆华.三峡库区四条支流藻类多样性评价及“水华”防治.中国环境科学, 2006,26(3):337-341.
[22]孙军,刘东艳,杨世民,郭健,钱树本.渤海中部和渤海海峡及邻近海域浮游植物群落结构的初步研究.海洋与湖沼, 2002, 33(5): 461-471.
[23]孙丕喜,王波,张朝晖,王宗灵,夏滨.莱州湾海水中营养盐分布与富营养化的关系.海洋科学进展, 2006, 24(3): 329-335.
[24]杜佳垠.大连黄海沿岸海域针胞藻类有毒有害赤潮生物.河北渔业,2005,1: 25-26.
[25]崔毅,陈碧鹃,陈聚法.黄渤海海水养殖自身污染的评估.应用生态学报, 2005, 16(1): 180-185.
[26]李肖娜,周伟华,刘素美,张经.东海赤潮高发区沉积物中叶绿素的分析.应用生态学报, 2003, 14(7):1102-1106.
[27]田荣湘.东亚季风与东海赤潮.浙江大学学报(理学版), 2005, 32(3): 355-360.
[28]潘雪峰,张鹰,张东,刘吉堂.海州湾圆筛藻与环境因子的关系研究.环境监测管理与技术, 2007, 19(1): 15-18.
[29]曾祥波,黄邦钦,陈纪新,洪华生.台湾海峡小型浮游动物的摄食对夏季藻华演替的影响.海洋学报, 2006, 28(5): 107-116.
[30]杨清良,林更铭.厦门海域浮游植物夏季赤潮期间分布变异的多元分析.生态学报, 2007, 27(2): 465-476.
[31]刘晓南,王为,吴志峰.广东沿海赤潮发生频率差异与城市发展的关系.地理学报, 2004, 59(6): 911-917.
[32]冷科明,江天久.深圳海域近20年赤潮发生的特征分析.生态科学, 2004, 23(2): 166-170.
[33]翁焕新,孙向卫,陈静峰,陈建芳,陈立红,陈祥华,秦亚超.珠江口沉积铁-磷的富集对赤潮频发的潜在作用.中国科学D辑-地球科学, 2006, 36(12): 1122-1130.
[34]刘沛然,黄先玉,柯栋.赤潮成因及预报方法.海洋预报, 1999, 16(4): 46-51.
[35]王洪礼,冯剑丰.赤潮生态动力学.天津:天津大学出版社,2006: 4-6.
[36] Takamura N., Qtsuki A., Aizaki M., and Nojiri Y. Phytoplankton species shift accompanied by transition from nitrogen to phosphorus dependence of primary production in Lake Kasumigaura, Japan. Arch. Hydrobiol.,1992, 124: 129-148.
[37] Jeong K.S., Kim D.K., Whigham P., and Joo G.J. Modeling Microcystis aeruginosa bloom dynamics in the Nakdong River by means of evolutionary computation and statistical approach. Ecological Modelling, 2003, 161: 67-78.
[38] Maier H.R., Dandy G.C. Modelling cyanobacterial (blue-green algae) in the River Murray using artificial neural networks. Mathematics and computers in Simulation, 1997, 43: 377-386.
[39] Maier H.R., Dandy G. C. Neural Network Based Modelling of Environmental Variables: A Systematic Approach. Mathematical and computer modeling, 2001, 33: 669-682.
[40] Fahnenstiel G.L., Lang G.A., Nalepa T.F., and Johengen T.H. Effects of zebra mussel (Dreissena polymorpha) colonization on water quality parameters in Saginaw Bay, Lake Huron. J. Great Lake Res., 1995, 21: 435-448.
[41] Jennifer L. Graham. Environmental factors influencing Microcystin distributionand concentration in Midwestern lakes. Ph.D. thesis. University of Missouri- Columbia, USA, 2004.
[42] Scott Neil Higgins. Modeling the growth dynamics of Cladophora in eastern Lake Erie. Ph.D. thesis. University of Waterloo, Canada, 2005.
[43] Whitehead P. & Hornberger G. Modelling algal behaviour in the River Thames. Wat. Res., 1984, 18: 945-953.
[44] Smith V.H., Willen B. and Karlsson B. Predicting the summer peak biomass of four species of blue-green algae in Swedish lakes. Water Resour. Bull., 1987, 23(3): 397-402.
[45] Reisenhofer E., Picciotto A. and Donfang L. A factor analysis approach to the study of the eutrophication of a shallow, temperature lake (San Daniele, North Eastern Italy). Analytic Chimica Acta, 1995, 306: 99-106.
[46] Perona E., Bonilla I. and Mateo P. Spatial and temporal changes in water quality in a Spanish river. Sci. Total Environ., 1999, 241: 75-90.
[47] Pingree R.D., Pugh P.R., Holligan P.M., Forster, G.R. Summer phytoplankton blooms and red tides along tidal fronts in the approaches to the English Channel. Nature, 1975, 258: 672– 677.
[48] Anne-Marie B., Michel R. and Noriyuld I. Tide versus eutrophication, impacts on ostracods populations structure of Mikawa Bay (Japan). REVUE DE MICROPALIONTOLOGIE, 1997, 40(1): 3-13.
[49] Voravit C.and Piamsak M. Water pollution and habitat degradation in the Gulf of Thailand. Marine Pollution Bulletin, 2003, 47: 43-51.
[50] Casas B., Varela M., Canle M., Gonza N. and Bodea A. Seasonal Variations of Nutrients, Seston and Phytoplankton, and Upwelling Intensity off La Coru?a (NW Spain). Estuarine, Coastal and Shelf Science, 1997, 44: 767–778.
[51] Raine R. and McMahon T. Physical dynamics on the continental shelf off southwestern Ireland and their influence on coastal phytoplankton blooms. Continental Shelf Research, 1998, 18: 883-914.
[52] Riyad S. M., Fuad A. A., Mohammad Y. R. et al.Patterns of summer vertical and horizontal currents in coastal waters of the northern Gulf of Aqaba, Red Sea. Estuarine, Coastal and Shelf Science, 2006, 69: 567-579.
[53] Rosalba A. and Ochoa J.L. Hydrology of winter–spring“red tides”in Bahía de Mazatlán, Sinaloa, México. Harmful Algae, 2004, 3:163-171.
[54] Werbos, P.J. Beyond regression: new tools for prediction and analysis in the behavioral sciences. Ph.D. thesis, Harvard University, 1974.
[55] Werbos, P.J. Generalization of backpropagation with application to a recurrent gas market model. Neural Networks, 1988, 1: 339-356.
[56] Rumelhart, D.E., Hinton, G.E., Williams, R.J. Learning representations by backpropagation errors. Nature, 1986, 323(6188):533-536.
[57] Weigend, A.S., Huberman, B.A., Rumelhart, D.E. Predicting the future: A connectionist approach. International Journal of Neural Systems, 1990, 1: 193-209.
[58] Weigend, A.S., Rumelhart, D.E., Huberman, B.A. Generalization by weight-elimination with application to forecasting. Advances in Neural Information Processing Systems, 1991, 3:875-882.
[59] Cottrell, M., Girard, B., Girard, Y., Mangeas, M., Muller, C. Neural modeling for time series: a statistical stepwise method for weight elimination. IEEE Transactions on Neural Networks, 1995, 6(6): 1355-1364.
[60] Tang, Z., Almeida, C., Fishwick, P.A. Time series forecasting using neural networks vs Box-Jenkins methodology. Simulation, 1991, 57(5): 303-310.
[61] Sharda, R., Patil, R.B. Connectionist approach to time series prediction: An empirical test. Journal of Intelligent Manaufacturing, 1992, 3: 317-323.
[62] Celik A.E. and Karatepe Y. Evaluating and forecasting banking crises through neural network models: An application for Turkish banking sector. Expert Systems with Applications, 2007, 33(4):809-815.
[63] Engin M., Demira? S., Engin E.Z. et al. The classification of human tremor signals using artificial neural network. Expert Systems with Applications, 2007, 33(3):754-761.
[64] Grznar J., Prasad S. and Tata J. Neural networks and organizational systems: Modeling non-linear relationships. European Journal of Operational Research, 2007, 181(2): 939-955.
[65] Ráduly B., Gernaey K.V., Capodaglio A.G. et al. Artificial neural networks for rapid WWTP performance evaluation: Methodology and case study. Environmental Modelling & Software, 2007, 22(8): 1208-1216.
[66] Zou H., Xia G., Yang F. and Yang H. A neural network model based on the multi-stage optimization approach for short-term food price forecasting in China. Expert Systems with Applications, 2007, 33(2): 347-356.
[67] Hagan M.T., Demuth H.B. and Beale M.H. Neural Network Design. Boston, MA: PWS Publishing, 1996.
[68] Tzafestas S.G., Dalianis P.J., Anthopoulos G. On the overtraining phenomenon of backpropagation neural networks. Mathematics and Computers in Simulation, 1996, 40: 507-521.
[69] Amari S.-i., Murata N.K.-R., Finke M., Yang H.H. Asymptotic statistical theory of overtraining and cross-validation. IEEE trans. on Neural Networks, 1997, 8(5): 985-996.
[70] Rivals I. and Personnaz L. On cross validation for model selection. Neural computation, 1999, 11: 863-870.
[71] Girosi F., Jones M. and Poggio T. Regularization theory and neural networks architectures. Neural computation, 1995,7: 219-269.
[72] Chen D.D. and Hagan M.T. Optimal use of regularization and cross validation in neural network modeling. Proceedings of the 1999 International Joint Conference on Neural Networks, 1999, 2: 1275-1280.
[73] Haykin Simon. Neural networks: a comprehensive foundation. New Jersey: Prentice Hall, Inc., 1999.
[74] White H. Connectionist nonparametric regression: multilayer feedforwardnetworks can learn arbitrary mappings. Neural networks, 1990, 3: 535-549.
[75] Fontova M. V., Oliveira A.R.L. and Lyra C. Warm start by Hopfield neural networks for interior point methods. Computers & Operations Research, 2007, 34(9): 2553-2561.
[76] Sun T.H., Chen M., Lo S. et al. Face recognition using 2D and disparity eigenface Expert Systems with Applications, 2007, 33(2):265-273.
[77] Al-Assaf Y. and Kadi H.E. Fatigue life prediction of composite materials using polynomial classifiers and recurrent neural networks. Composite Structures, 2007, 77(4): 561-569.
[78] Ren T.J. and Chen T.C. Robust speed-controlled induction motor drive based on recurrent neural network. Electric Power Systems Research, 2006, 76(12): 1064-1074.
[79] Mandal S. and Prabaharan N. Ocean wave forecasting using recurrent neural networks. Ocean Engineering, 2006, 33(10): 1401-1410.
[80] Lin C.M., Huang J.J., Gen M. and Tzeng G.H. Recurrent neural network for dynamic portfolio selection. Applied Mathematics and Computation, 2006, 175(2): 1139-1146.
[81] Broomhead D.S., Lowe D. Multi-variable functional interpolation and adaptive networks. Complex Syst., 1988, 2: 321–55.
[82] Yao X.J., Zhang X.Y., Zhang R.S. et al. Prediction of enthalpy of alkanes by the use of radial basis function neural networks. Computers and Chemistry, 2001, 25: 475–482.
[83] Dibike Y. B. and Solomatlne D. P. River Flow Forecasting Using Artificial Neural Networks. Phys. Chem. Earth(B), 2001, 26(1):1-7.
[84] Rivas V.M., Merelo J.J., Castillo P.A. et al. Evolving RBF neural networks for time-series forecasting with EvRBF. Information Sciences, 2004, 165: 207-220.
[85] Morelli M.J., Montagna G., Nicrosini O. et al. Pricing financial derivatives with neural networks. Physica A, 2004, 338: 160-165.
[86] Zhang Aishe and Zhang Ling. RBF neural networks for the prediction of building interference effects. Computers & Structures, 2004, 82: 2333-2339.
[87] Santos A.P., Costa N.A. and Coelho L.S. Computational intelligence approaches and linear models in case studies of forecasting exchange rates. Expert Systems with Applications, 2007, 33(4): 816-823.
[88] Bierman V.J. Mathematical model of the selective enhancement of blue-green algae by nutrient enrichment. In Recknagel F., ANNA-artificial neural network model for predicting species abundance and succession of blue-green algae, Hydrobiologia, 1976, 349(1997):47-57.
[89] Okada M. & Aiba S. Simulation of water blooms in a eutrophic lake: Modeling the vertical migration in a population of Microcystis aeruginosa. Wat. Res., 1983, 20: 485-490.
[90] Reynolds F.M. The ecology of freshwater phytoplankton. Cambridge: Cambridge University Press, 1984: 384.
[91] Sakamoto M. Primary production by phytoplankton community in some Japanese lakes and its dependence on lake depth. Arch. Hydrobiol., 1966, 62: 1-28.
[92] Dillon P.J. & Rigler F.H. The phosphorus-chlorophyll relationship in lakes. Limnol. Oceanogr., 1975, 19: 767-773.
[93] Recknagel F., Petzoldt T., Jaeke O., Krusche F. Hybrid expert system DELAQUA– a toolkit for water quality control of lakes and reservoirs. Ecol. Modelling, 1994, 71: 17-36.
[94] Quchia. Simalation of red tide by means of multiple regression and fourier analysis. Bull. Jap. Soc. Sci. Fish, 1986, 52(2):203-207.
[95]洪君超,黄秀清,蒋晓山等.嵊山水域中肋骨条藻赤潮发生过程主导因子分析.海洋学报.1993, 15(6):135-141.
[96]黄良民,钱宏林,李锦蓉.大鹏湾赤潮多发区的叶绿素a分布与环境关系初探.海洋与湖沼,1994,25(2):197-205.
[97]林永水,邱德全,周近明.小等刺硅鞭藻赤潮的成因.中国赤潮研究及SCOR-IOC赤潮工作组中国委员会第二次会议论文选.青岛:青岛出版社,1996:48-53.
[98] [98]赵明桥,李攻科,张展霞.应用多元回归法研究赤潮特征有机物与赤潮关系.中山大学学报(自然科学版),2003,42(1): 35-39.
[99]谢中华.运用混合回归模型预报赤潮.海洋技术,2004,23(1): 27-30.
[100] Altrock C. Fuzzy logic and neuro fuzzy applications explained. New Jersey: Prentice Hall, 1995.
[101] Czogala J. Fuzzy and neuro-fuzzy intelligent systems. New York: Physica - Verlag, 2000.
[102] Chen Q.W. and Mynett A.E. Integration of data mining techniques and heuristic knowledge in fuzzy logic modeling of algal biomass in the north sea. Second international workshop on coastal eutrophication (proceedings), Nov. 2002. Chongqin: China.
[103] Soyupak S. and Chen D.G. Fuzzy logic model to estimate seasonal pseudo steady state chlorophyll-a concentration in reseroviors. Environmental Modeling Assessment, 2004, 9(1): 51-59.
[104] Marsili L.S. Fuzzy prediction of the algal blooms in the Orbetello Lagoon. Environmental Modeling and Software, 2004, 19(9): 799-808.
[105] French M. and Recknagel F.. Modelling of algal blooms in freshwaters using artificial neural networks. In: Zanetti P.(Editor), Computer Techniques in Environmental Studies V. Vol. II: Environmental Systems. Southampton, Boston: Computational Mechanics Publications, 1994: 87-94.
[106] Recknagel F., 1997. ANNA– Artificial neural network model for predicting species abundance and succession of blue-green algae. Hydrobiologia, 349: 47-57.
[107] Recknagel F., French M., Harkonen P., Yabunaka K.I. Artificial neural network approach for modelling prediction of algal blooms. Ecol. Modelling, 1997, 96: 11-28.
[108] Yabunaka K.I., Hosomi M. and Murakami A. Novel application of a back-propagation artificial neural network model formulated to predict algal bloom.Wat. Sci. Tech., 1997, 36(5): 89-97.
[109] Wei B., Sugiura N. and Maekawa T. Use of artificial neural network in the prediction of algal blooms. Water Resource, 2001,35(8): 2022–2028.
[110] Maier H.R., Dandy G.C., Burch M.D. Use of artificial neural networks for modeling cyanobacterial Anabaena app. in the River Murray, South Australia. Ecological Modelling, 1998, 105: 257-272.
[111] Hou G.X., Song L.R., Liu J.T. et al. Modeling of cyanobacterial blooms in hypereutrophic Lake Dianchi, China. Journal of Freshwater Ecology, 2004, 19(4): 623-629.
[112] Walter M., Recknagel F., Carpenter C., Bormans M. Predicting eutrophication effects in the Burrenjuck Reservoir (Australia) by means of the deterministic model SALMO and the recurrent neural network model ANNA. Ecological Modelling, 2001, 146: 97-113.
[113] Jeong K.S., Joo G.J., Kim H.W., Ha K., Recknagel F. Prediction and elucidation of phytoplankton dynamics in the Nakdong River (Korea) by means of a recurrent neural network. Ecological Modelling, 2001, 146: 115-129.
[114] Jeong K.S., Recknagel F., Joo G.J. Prediction and elucidation of population dynamics of the blue-green algae Microcystis aeruginosa and the diatom Stephanodiscus hantzschii in the Nakdong River-Reservior systems (South Korea) by a recurrent artificial neural network. In: Recknagel F., Ecological Informatics(2nd Edition). NY: Springer-Verlag, 2005: 255-273.
[115] Rechnagel F., Welk A., Kim B. and Takamura N. Artificial neural network approach to unravel and forecast algal population dynamics of two lakes different in morphometry and eutrophication. In: Recknagel F., Ecological Informatics(2nd Edition). NY: Springer-Verlag, 2005: 325-345.
[116]孙蓉桦,张微. GRNN和遗传算法在赤潮预报中的应用操作.科技通报, 2005, 21(4):485-490.
[117]吴京洪,杨秀环,唐宝英,张展霞,李锦蓉.人工神经网络预报浮游植物生长趋势的研究.中山大学学报(自然科学版), 2000, 39(6): 54-59.
[118]蔡如钰.基于人工神经网络的夜光藻密度预测模型.中国环境监测,2001,17(3): 52-55.
[119]王洪礼,沈菲,冯剑丰,孙景.基于人工神经网络的浮游植物密度预测模型研究.气象水文海洋仪器,2004, 3(4): 26-29.
[120]杨建强,罗先香,丁德文,秦洁.赤潮预测的人工神经网络方法初步研究.海洋科学进展,2003,21(3): 318-324.
[121]王洪礼,葛根,李悦雷.基于模糊神经网络(FNN)的赤潮预警预测研究.海洋通报,2006, 25(4): 36-41.
[122] ZHANG Rong, YAN Hong, DU Liping. Research on Prediction of Red Tide Based on Fuzzy Neural Network. Marine Science Bulletin, 2006, 8(1): 83-92.
[123]马玉梅,高静宇,王清华.基于人工神经网络的赤潮预测模型.海洋预报,2007,24(1): 38-44.
[124]杨建强,高振会,孙培艳,石强,李钦亮.自组织神经网络在有害赤潮预警研究中的应用.海洋环境科学, 2003, 22(1): 6-9.
[125] Zar J.H. Biostatistical Analysis, 2nd edition. NJ: Prentice-Hall, 1984: 718.
[126] Jin X. and Tu Q. Methods for Research of Eutrophicated Lakes, 2nd edition. Beijing: Meteorological Press, 1990.
[127] Ma X.X., He X.J., Zhao D.Q., and Wang X.Y. Influence of B-P networks hidden layer on water quality evaluation result. International Journal Hydroelectric Energy, 2002, 20: 16-18.
[128] Xiong L.H., Guo S.L., Wang Y. Study and application of artificial neural network in real time flood forecasting. International Journal Hydroelectric Energy, 2002, 20: 28-31.
[129] Xu S.G. and Wang J. Fuzzy optimal decision for structure of feedforward neural networks and its application in runoff forecast. International Journal of Hydroelectric Energy, 2002, 20: 35-37.
[130] MathWorks Inc. Neural Network Toolbox: User’s Guide (Matlab 7.0). MA: TheNatick, 2004.
[131] Goh A.T.C. Back-propagation neural networks for modeling complex systems. Artif. Intel. Eng. 1995, 9: 143-151.
[132] Lek S., Delacoste M., Baran P., Dimopoulos I., Lauga J., and Aulagner S. Application of neural networks to modeling non-linear relationships in ecology. Ecological Modelling,1996, 90: 39-52.
[133] Siginer I. Some artificial neural network applications to greenhouse environmental control. Comput. Electron. Agric.,1997, 18: 167-186.
[134] Dimopoulos Y., Chronopoulos J., Chronopoulou S.A., and Lek S. Neural network models to study relationships between lead concentration in grasses and permanent urban descriptors in Athens city. Ecological Modelling, 1999, 120: 157-165.
[135] Stumm W. and Morgan J.J. Aquatic Chemistry. New York: Wiley, 1970.
[136] Shapiro J. Current beliefs regarding dominance of by blue-greens: the case for the importance of CO2 and pH. Verh. Int. Verein. Limnol., 1990, 24: 38-54.
[137] Sommer U., Gliwica Z.M., Lampert W., and Duncan A. The PEG-model of seasonal succession of planktonic events in fresh waters, Arch. Hydrobiol., 1986, 106: 443-471.
[138] Kromkamp J. and Walsby A.E. A computer model of buoyancy and vertical migration in cyanobacteria, J. Plankton Res., 1990, 12: 161-183.
[139] Reynolds C.S. The River Handbook: Hydrological and Ecological Principles, Vol. 1. Oxford: Blackwell Scientific Publication, 1992: 526.
[140] Park J, Sandberg I.W. Universal approximation using radial basis functions network, Neural Computing, 1991, 3: 246–257.
[141] Bianchini M., Frasconi P. and Gori M. Learning without local minima in radial basis function networks. IEEE Trans. Neural Networks, 1995, 6:749–56.
[142] Moody J. and Darken C. Faster learning in networks of locally tuned processing units, Neural Computing, 1989, 1, 281–294.
[143] Sheta A.F. and Jong K. Time-series forecasting using GA-tuned radial basisfunctions, Information Sciences, 2001, 133(3–4): 221–228.
[144] Chen, S., Cowan C.F.N., and Grant P. M. Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks, IEEE Transactions on Neural Networks, 1991, 2(2): 302-309.
[145] Suttle C.A. and Harrison P.J. Ammonium and phosphate uptake rates, N:P supply ratios, and evidence for N and P limitation in some oligotrophic lakes. Limnol. Oceanogr., 1988, 33(2): 186-202.
[146] Moss B. Ecology of Fresh Waters: Man and Medium, Past to Future, 3rd Edition. Oxford: Blackwell Science, 1998: 557.
[147] Shapiro J. Blue-green algae: why they become dominant. Science, 1973, 179: 382-384.
[148] Harris G.P. Plankton Ecology– Stucture, Function, and Fluctuation. NY: Chapman and Hall, 1986: 384.
[149] Bowerman B.L. and Connell R. Forecasting and Time Series, 3rd Edition. Peking: China Machine Press, 2003.
[150] Morantz B.H. Weighted window method for time series forecasting with an artificial neural network, Ph.D. Dissertation, Robinson College of Business, Georgia State University, 2002.
[151] Poggio T. and Girosi F. Networks for approximation and learning. Proceeding of IEEE, 1990, 78.