基于水信息技术的渤海湾水生态环境特性及模拟研究
|
摘要
渤海湾是一个半封闭的淤泥质浅水海湾,与外海的水交换能力较弱。随着沿海经济的快速发展和近岸排污量的增加,水体富营养化和赤潮灾害频发等海洋水生态环境问题日趋明显。近岸海域水生态环境特性及模拟方法的研究,对认识海洋生态过程、保护近岸海洋生态系统和海洋管理有重要的意义。
由于水生态环境的高度复杂性、非线性和时空特异性,系统的内部作用机理及其动态变化过程还未被完全知晓,使得单纯用传统的基于机理或假设的确定性水生态动力学模型方法受到了限制。随着包括遥感在内的海洋生态环境数据信息量的飞快增加,越来越多的信息学技术被应用于水生态环境的研究中。本文利用现代水信息技术,系统地研究了近岸海域水生态环境的特性及建模方法。
本文首先分析了近岸海域水生态环境的特性及模拟研究中需要解决的问题:如何有效地提取出海量数据中潜在有用的信息和知识;如何准确地分析水生态环境的空间特性;如何有效地模拟水生态环境的高度复杂性和非线性关系;如何在动态演变中体现出空间异质性和局部相互作用的影响;如何有效地耦合水动力学模型和生态模型。
其次,利用数据挖掘方法和空间数据分析方法对渤海湾水生态环境特性进行了分析。聚类分析、关联分析和决策树分析提取出了渤海湾水生态环境中一些潜在的知识;空间自相关和空间自回归分析的研究表明渤海湾各生态环境指标具有高度的正空间自相关性,同时发掘了渤海湾赤潮前后的一些特性及异常现象。然后利用非确定性的软计算方法研究近岸海域水生态系统的高度复杂性和非线性关系,建立了基于混合软计算方法的生态模型Eco_HSC,研究表明该模型能较好地反映出各站位叶绿素a浓度实测值的变化趋势,并具有较强的泛化能力;利用元胞自动机(CA)的局部网格动力学优势,综合考虑了局部作用、空间差异和外在因子的影响,建立了基于CA-SVM的渤海湾遥感叶绿素浓度模型,研究表明该模型总体上能较好地反映出渤海湾空间上叶绿素浓度的时空变化特征。
最后,探讨了确定性方法与非确定性方法的结合。通过将水动力学模块的模拟结果引入到的CA-SVM生态模块中,建立了渤海湾的生态和水动力学耦合模型,研究表明该模型能很好地模拟渤海湾遥感叶绿素浓度的时空变化特征。
The Bohai Bay is a semi-enclosed sea bay with mild-slope mud beach and shallow water. The water exchange and self-purifying capacity of this sea bay are very weak. With the rapid development of economy and increasing pollutant emission along coastal area, marine ecological environment issues have become increasingly serious, such as serious eutrophication and frequently occured red tides. Research of coastal ecological environment characteristics and modelling methods has great significance for understanding of marine ecological processes, protecting coastal aquatic ecosystem and marine management.
Due to the high complexity, the non-linearity and time-space specificity of coastal ecological environment, the internal mechanism of the system and its dynamic processes have not been fully understood, which results in the difficulty of using the conventional deterministic ecohydraulics models. Meanwhile, with the rapid increase of the quantity of coastal ecological environment data including romete sensing data, more and more information technologies are applied to the research of aquatic ecological environment. This dissertation studied the characteristics and modelling methods of coastal ecological environment using new hydroinformatics technologies.
This dissertation firstly accounts for the problems of study on the characteristics and modelling methods for coastal ecological environment, including: 1) How to effectively extract some potential useful informations and knowledge from massive data, 2) How to availably reflect the spatial characteristics of aquatic ecological environment data, 3) How to availably simulate the high complexity and the non-linearity of coastal ecological environment, 4) How to availably reflect the effects of local action and spatial discrepancy during dynamic evolution, and 5) How to carry on the integration of deterministic hydrodynamic module with nondeterministic ecological module.
Secondly, the ecological environment romete sensing data of Bohai Bay have been analyzed using data mining methods and spatial statistical analysis. Some potential useful knowledge for the aquatic ecological environment of Bohai Bay was extracted using clustering analysis, association analysis and decision tree analysis. The results of spatial autocorrelation analysis and spatial autoregressive model showed that there was a signifieant spatial autocorrelation in ecological environment index during the red tide and detected some anomalous changes of spatio-temporal distribution in ecological environment index.
Thirdly, the high complexity and the non-linearity of coastal ecological environment were studied using nondeterministic soft computing, and an ecological model based on hybrid soft computing (Eco_HSC) was established. The results show that the Eco_HSC model can be preferably used to simulate and predict chlorophyll-a concentrations of each site in the Bohai Bay, and it has good generalization ability. Considering the effects of local action, spatial discrepancy and external factors, an integrated cellular automata and support vector machine model (CA-SVM) was developed to simulate the remote sensing chlorophyll-a concentrations in the Bohai Bay. The results show that the CA-SVM model can catch the spatio-temporal variation of chlorophyll-a concentrations.
Finally, this dissertation tries to carry on discussion and research in the integration of deterministic method and nondeterministic method. An integrated ecohyrdraulics model has been developed by coupling the simulation results of hydrodynamic module with CA-SVM module. The results indicate that the intergrated model has better performace than CA-SVM, and can be applied to simulate the spatio-temporal variation of chlorophyll-a concentrations in the Bohai Bay.
由于水生态环境的高度复杂性、非线性和时空特异性,系统的内部作用机理及其动态变化过程还未被完全知晓,使得单纯用传统的基于机理或假设的确定性水生态动力学模型方法受到了限制。随着包括遥感在内的海洋生态环境数据信息量的飞快增加,越来越多的信息学技术被应用于水生态环境的研究中。本文利用现代水信息技术,系统地研究了近岸海域水生态环境的特性及建模方法。
本文首先分析了近岸海域水生态环境的特性及模拟研究中需要解决的问题:如何有效地提取出海量数据中潜在有用的信息和知识;如何准确地分析水生态环境的空间特性;如何有效地模拟水生态环境的高度复杂性和非线性关系;如何在动态演变中体现出空间异质性和局部相互作用的影响;如何有效地耦合水动力学模型和生态模型。
其次,利用数据挖掘方法和空间数据分析方法对渤海湾水生态环境特性进行了分析。聚类分析、关联分析和决策树分析提取出了渤海湾水生态环境中一些潜在的知识;空间自相关和空间自回归分析的研究表明渤海湾各生态环境指标具有高度的正空间自相关性,同时发掘了渤海湾赤潮前后的一些特性及异常现象。然后利用非确定性的软计算方法研究近岸海域水生态系统的高度复杂性和非线性关系,建立了基于混合软计算方法的生态模型Eco_HSC,研究表明该模型能较好地反映出各站位叶绿素a浓度实测值的变化趋势,并具有较强的泛化能力;利用元胞自动机(CA)的局部网格动力学优势,综合考虑了局部作用、空间差异和外在因子的影响,建立了基于CA-SVM的渤海湾遥感叶绿素浓度模型,研究表明该模型总体上能较好地反映出渤海湾空间上叶绿素浓度的时空变化特征。
最后,探讨了确定性方法与非确定性方法的结合。通过将水动力学模块的模拟结果引入到的CA-SVM生态模块中,建立了渤海湾的生态和水动力学耦合模型,研究表明该模型能很好地模拟渤海湾遥感叶绿素浓度的时空变化特征。
The Bohai Bay is a semi-enclosed sea bay with mild-slope mud beach and shallow water. The water exchange and self-purifying capacity of this sea bay are very weak. With the rapid development of economy and increasing pollutant emission along coastal area, marine ecological environment issues have become increasingly serious, such as serious eutrophication and frequently occured red tides. Research of coastal ecological environment characteristics and modelling methods has great significance for understanding of marine ecological processes, protecting coastal aquatic ecosystem and marine management.
Due to the high complexity, the non-linearity and time-space specificity of coastal ecological environment, the internal mechanism of the system and its dynamic processes have not been fully understood, which results in the difficulty of using the conventional deterministic ecohydraulics models. Meanwhile, with the rapid increase of the quantity of coastal ecological environment data including romete sensing data, more and more information technologies are applied to the research of aquatic ecological environment. This dissertation studied the characteristics and modelling methods of coastal ecological environment using new hydroinformatics technologies.
This dissertation firstly accounts for the problems of study on the characteristics and modelling methods for coastal ecological environment, including: 1) How to effectively extract some potential useful informations and knowledge from massive data, 2) How to availably reflect the spatial characteristics of aquatic ecological environment data, 3) How to availably simulate the high complexity and the non-linearity of coastal ecological environment, 4) How to availably reflect the effects of local action and spatial discrepancy during dynamic evolution, and 5) How to carry on the integration of deterministic hydrodynamic module with nondeterministic ecological module.
Secondly, the ecological environment romete sensing data of Bohai Bay have been analyzed using data mining methods and spatial statistical analysis. Some potential useful knowledge for the aquatic ecological environment of Bohai Bay was extracted using clustering analysis, association analysis and decision tree analysis. The results of spatial autocorrelation analysis and spatial autoregressive model showed that there was a signifieant spatial autocorrelation in ecological environment index during the red tide and detected some anomalous changes of spatio-temporal distribution in ecological environment index.
Thirdly, the high complexity and the non-linearity of coastal ecological environment were studied using nondeterministic soft computing, and an ecological model based on hybrid soft computing (Eco_HSC) was established. The results show that the Eco_HSC model can be preferably used to simulate and predict chlorophyll-a concentrations of each site in the Bohai Bay, and it has good generalization ability. Considering the effects of local action, spatial discrepancy and external factors, an integrated cellular automata and support vector machine model (CA-SVM) was developed to simulate the remote sensing chlorophyll-a concentrations in the Bohai Bay. The results show that the CA-SVM model can catch the spatio-temporal variation of chlorophyll-a concentrations.
Finally, this dissertation tries to carry on discussion and research in the integration of deterministic method and nondeterministic method. An integrated ecohyrdraulics model has been developed by coupling the simulation results of hydrodynamic module with CA-SVM module. The results indicate that the intergrated model has better performace than CA-SVM, and can be applied to simulate the spatio-temporal variation of chlorophyll-a concentrations in the Bohai Bay.
引文
[1]国家海洋局. 2009年中国海洋环境质量公报[R].北京:国家海洋局, 2010.
[2]聂红涛,陶建华.渤海湾海岸带开发对近海水环境影响分析[J].海洋工程, 2008, 26(3): 44-50.
[3] Sun T, Tao J. Experimental and numerical study of wave-induced long-shore currents on a mild slope beach[J]. China Ocean Engineering, 2005, 19(3): 469-484.
[4]国家海洋局. 2008年中国海洋环境质量公报[R].北京:国家海洋局, 2009.
[5]赵海萍.渤海湾浮游细菌及水层生态水动力学模拟[D].天津:天津大学, 2006.
[6]阚文静,张秋丰,石海明,等.近年来渤海湾营养盐变化趋势研究[J].海洋环境科学, 2010, 29(2): 238-241.
[7]王勇,焦念志.营养盐对浮游植物生长的上行效应的研究方法[J].海洋科学, 2000, 24(11): 16-18.
[8]齐雨藻,楚建华,黄奕华.诱发海洋褐胞藻赤潮的环境因素分析[J].海洋通报, 1993, 12(2): 30-34.
[9] Handan C, Nilsun D, Arzu K, et al. Use of principal component scores in multiple linear regression models for prediction of chlorophyll-a in reservoirs[J]. Ecological Modelling, 2005, 181: 581-589.
[10]桑艳丽.统计分析在渤海湾浮游动物数据处理中的应用[D].济南:山东大学, 2009.
[11]许勇,张鹰,刘吉堂,等.基于支持向量机分类的海州湾赤潮判别[J].海洋湖沼通报, 2009, 3: 60-65.
[12] Chau K, Muttil N. Data mining and multivariate statistical analysis for ecological system in coastal waters[J]. Journal of Hydroinformatics, 2007, 9(4): 305-317.
[13]夏静.长江口浮游植物变化及影响因子初步研究[D].上海:上海师范大学, 2005.
[14]齐雨藻,洪英,吕颂辉,等.中国赤潮生物新纪录种海洋褐胞藻[J].暨南大学学报(自然科学报), 1991, 12(3): 92-95.
[15]徐祖信,廖振良.水质数学模型研究的发展阶段与空间层次闭[J].上海环境科学, 2003, 22(2): 79-85.
[16]穆迪.渤海湾生态水质动力学模型研究[D].天津:天津大学, 2006.
[17]张素香,李瑞杰,罗锋,等.海洋生态动力学模型的研究进展[J].海洋湖沼通报, 2006, 4: 121-127.
[18] Moll A. Regional distribution of primary production in the North Sea simulation by a three dimentional model[J]. Journal of Marine Systems, 1998, 16(1-2): 151-170.
[19] Skogen M, Moll A. Interannual variability of the North Sea primary production: comparison from two model studies[J]. Continental Shelf Research. 2000, 20: 129-151.
[20]吴增茂,俞光耀,张志南,等.胶州湾北部水层生态动力学模型与模拟II:胶州湾北部水层生态动力学的模拟研究[J].青岛海洋大学学报, 1999, 29(3): 429-435.
[21] Cui M, Zhang H. Coupled physical ecological modeling of the central part of Jiaozhou bay II: coupled with an ecological model[J]. Chinese Journal of Oceanology Liminology, 2001, 19(1): 21-28.
[22]魏皓,赵亮,冯士筰.渤海浮游植物生物量与初级生产力变化的三维模拟[J].海洋学报, 2003, 25(2): 66-72.
[23]魏皓,赵亮,冯士筰.渤海碳循环与浮游植物动力学过程研究[J].海洋学报, 2003, 25(2): 151-156.
[24]李清雪.海湾浮游生物及氮营养盐生态水动力学模拟[D].天津:天津大学, 2007.
[25]宋文筠.渤海湾浮游生态系统动力学模型[D].天津:天津大学, 2002.
[26]向先全,陶建华.水信息学及其在水环境中的应用研究综述[J].生态环境学报, 2009, 18(4): 1587-1593.
[27]李树平.水信息学概述[J].给水排水, 2002, 28(4): 90-94.
[28] Michael B. Introducing hydroinformatics[J]. Journal of Hydroinformatics, 1999, 1(1): 3-l9.
[29] Appignanesi R, Garatt C. Postmodernism for Beginners[M]. Cambridge: Cambridge University Press, 1995.
[30]王泽良,陶建华.海湾水质模型的信息化研究[J].海洋通报, 1999, 18(4): 55-63.
[31] Los F, Villars M, Van M. A 3-dimensional primary production model (BLOOM/GEM) and its applications to the (southern) North Sea (coupled physical chemical ecological model)[J]. Journal of Marine Systems, 2008, 74(1-2): 259-294.
[32] Xu J, Hood R. Modeling biogeochemical cycles in Chesapeake Bay with a coupled physical-biological model[J]. Estuarine, Coastal and Shelf Science, 2006, 69(1-2): 19-46.
[33] Yamane N, Nakatsuji K, Muraoka K. Field data collection and modeling for verification of an ecosystem model in Osaka Bay[J]. Estuarine and Coastal Modeling, 1997, 4: 196-210.
[34] Murray A, Parslow J. Modelling of nutrient impacts in Port Phillip Bay - a semi-enclosed marine Australian ecosystem[J]. Marine and Freshwater Research, 1999, 50(6): 597-611.
[35]李德仁,王树良,史文中,等.论空间数据挖掘和知识发现[J].武汉大学学报(信息科学), 2001, 26(6): 491-499.
[36]梁秀菊.浅析统计学与数据挖掘[J].经济与社会发展, 2008, 6(8): 38-42.
[37]张小娟.数据挖掘技术在水资源领域的应用研究[D].北京:中国水利水电科学研究院, 2007.
[38]夏登文,石绥祥,于戈,等.海洋数据仓库及数据挖掘技术方法研究[J].海洋通报, 2005, 24(3): 60-65.
[39]宁勇.数据挖掘在海洋环境在线监测及赤潮灾害智能预警系统中的应用[D].济南:山东大学, 2008.
[40]罗文静.数据挖掘中可视化技术研究与实现[D].成都:电子科技大学, 2007.
[41]魏红宇,张峰,李四海.海洋数据挖掘技术应用研究[J].海洋通报, 2008, 27(6): 82-87.
[42] Bridges S, Hodges J, Wooley B, et al. Knowledge discovery in an oceanographic database[J]. Applied Intelligence, 1999, 11(2): 135-148.
[43]马超飞,刘建强.遥感图像多维量化关联规则挖掘[J].遥感技术与应用, 2003, 18(4): 243-247.
[44] Kitamoto A. Spatio-temporal data mining for typhoon image collection[J]. Journal of Intelligent Information Systems, 2002, 19(1): 25-41.
[45]冯剑丰,王洪礼,孙景.渤海赤潮预测的研究现状及展望[J].气象水文海洋仪器, 2004, 1: 10-13.
[46]武孔春.概念驱动的加工与数据驱动的加工——科学信息是怎样进化的[J].自然杂志, 2002, 24(3): 178-181.
[47]周涛.软计算与人工智能[J].福建电脑, 2006, 1: 55-56.
[48] Zadeh L. Fuzzy logic, neural networks and soft computing[J]. Communications of the ACM, 1994, 37(3): 77-84.
[49]张颖,刘艳秋.软计算方法[M].北京:科学出版社, 2002.
[50]王攀,万君康,冯珊.创建计算智能的新方法软计算的若干问题研究[J].武汉理工大学学报, 2004, 28(4): 618-621.
[51]温显斌,张桦,张颖,等.软计算及其应用[M].北京:科学出版社, 2009.
[52] Hugh W, Friedrich R. Towards a genetic artificial neural network model for dynamic prediction of algal abundance in freshwater lakes[J]. Ecological Modelling, 2001, 146: 69-84.
[53]杨建强,罗先香,丁德文,等.赤潮预测的人工神经网络方法初步研究[J].海洋科学进展, 2003, 21(3): 318-324.
[54] Salski A. Fuzzy clustering of fuzzy ecological data[J]. Ecological Informatics, 2007, 2(3): 262-269.
[55] Chen Q, Mynett A. Integration of data mining techniques with heuristic knowledge in a fuzzy logic modelling of eutrophication in Taihu Lake[J]. Ecological Modelling, 2003, 162: 55-67.
[56]沈菲,曲阳,李会民,等.浮游植物密度的人工神经网络预测研究[J].海洋技术, 2005, 24(1): 44-47.
[57]李祚泳,张欣莉,丁晶.水质污染损害指数评价的普适公式[J].水科学进展, 2001, 12(2): 160-164.
[58]李祚泳,彭荔红,吕玉嫦.基于遗传算法的普适卡森指数公式[J].中国环境科学, 2001, 21(2): 144-147.
[59]冯剑丰,王洪礼,李胜朋.基于支持向量机的浮游植物密度预测研究[J].海洋环境科学, 2007, 26(5): 438-441.
[60]王长江.渤海赤潮生态环境评价与非线性预测系统[D].天津:天津大学, 2005.
[61]窦君鸿.基于支持向量机的生态环境预警及环境指标预测方法研究[D].北京:中国农业人学, 2004.
[62] GAO S, Wu Z, Xie H. The development and applications of Kalman filters in meterrological data assimilation[J]. Advance in Earth Sciences, 2000, 15(5): 571-575.
[63] Friedrichs M. Assimilation of JGOFS EqPac and SeaWiFS data into a marine ecosystem model of the central equatorial Pacific Ocean[J]. Deep Sea Research II, 2002, 49: 289-319.
[64] Garcia G, Hoepffner N, Ouberdous M. Assimilation of SeaWiFS data in a coupled physical-biological model of the Adriatic sea[J]. Journal of Marine Systems, 2003, 40: 233-252.
[65] Allen J, Eknes M, Evensen G. An ensemble Kalman filter with a complex marine ecosystem model: hindcasting phytoplankton in the Cretan Sea[J]. Annales Geophysicae, 2002, 20: 1-13.
[66] Eknes M, Evensen G. An ensemble Kalman filter with a 1-D marine ecosystem model[J]. Journal of Marine Systems, 2002, 36: 75-100.
[67] Natvik L, Evensen G. Assimilation of ocean colour data into a biochemical model of the North Atlantic I: data assimilation experiments[J]. Journal of Marine Systems, 2003, 40: 127-153.
[68] Hurtt G, Armstrong R. A pelagic ecosystem model calibrated with BATS data[J]. Deep Sea Research II, 1996, 43: 653-683.
[69]万振文,袁业立,乔方立.海洋赤潮生态模型参数优化研究[J].海洋与湖沼, 2000, 31(2): 205-209.
[70]马寨璞,井爱芹.海洋科学中的数据同化方法意义、结构与发展现状[J].海岸工程, 2005, 24(4): 83-99.
[71] Roverso D. Intelligent system integration: guiding principles, examples and lessons learned[J]. Progress in Nuclear Energy, 2005, 46(3-4): 190-205.
[72]万显烈.利用离散点插值扩展法评价大连湾水质状况[J].辽宁城乡环境科技, 2004, 18(6): 41-42.
[73]穆迪,袁德奎,陶建华.地理信息系统在渤海湾水体富营养化研究中的应用[J].海洋技术, 2006, 25(1): 73-77.
[74]王桥,吴纪桃.空间决策支持系统中的模型标准化问题研究[J].测绘学报, 1999, 2(28): 172-176.
[75]张宇羽.水质预测与评价管理决策支持系统[D].广州:广东工业大学, 2002.
[76]黄添强.基于空间数据挖掘的环境调控空间决策支持系统研究[D].福州:福州大学, 2002.
[77]唐崇杰,林继发.区域水环境管理决策支持系统的研究和开发以湛江市为例[J].资源环境与发展, 2007, 3: 30-34.
[78]曾维华.多源信息融合技术在内陆湖库水华预警中的研究进展与展望[J].长江流域资源与环境, 2009, 18(1): 72-78.
[79]吴小一.河流水环境数值模拟及可视化研究[D].重庆:重庆大学, 2006.
[80]顾正华,唐洪武,李云,等.水信息学与智能水力学[J].河海大学学报(自然科学版), 2003, 31(5): 518-521.
[81]杨世民,董树刚,李锋,等.渤海湾海域生态环境的研究Ⅰ:浮游植物种类组成和数量变化[J].海洋环境科学, 2007, 26(5): 442-445.
[82]杨世民,董树刚,窦明武,等.渤海湾海域生态环境的研究Ⅱ:水体富营养化的评价与分析[J].海洋环境科学, 2007, 26(6): 541-545.
[83]朱静.近岸海域水污染物输移规律及环境容量研究[D].南京:河海大学, 2007.
[84]王洪礼,冯剑丰,沈菲.渤海赤潮藻类生态动力学模型的非线性动力学研究[J].海洋技术, 2002, 21(3): 8-12.
[85]赵亮,魏皓,冯士筰.渤海氮磷营养盐的循环和收支[J].环境科学, 2002, 23(1): 78-81.
[86]何恩业,李海,任湘湘,等. BP人工神经网络在渤海湾叶绿素预测中的应用[J].海洋预报, 2008, 25(2): 1-10.
[87] Tao J, Wang Z. Refined water quality modeling of Bohai Bay[J]. Environmental and Coastal Hydraulics, 1997, 2: 3-8.
[88]王泽良,陶建华,季民,等.渤海湾中化学需氧量(COD)扩散、降解过程研究[J].海洋通报, 2004, 23(1): 27-31.
[89]王泽良,王日新,陶建华.渤海湾流场以及污染物分布的数值模拟研究[J].海洋与湖沼, 1999, 30(2): 224-230.
[90]邓华健.渤海湾沉积物-水界面营养盐交换通量的研究[D].天津:天津大学, 2004.
[91]张洁帆.渤海湾沉积物和水界面间营养盐的交换通量研究[D].天津:天津大学, 2007.
[92]高庆春.渤海湾赤潮监控区细菌对浮游生态系统影响的研究[D].天津:天津大学, 2007.
[93]安斐.渤海湾富营养化模糊评价与预测研究[D].天津:天津大学, 2007.
[94]向先全.基于模糊理论和神经网络方法的渤海湾富营养化模型研究[D].天津:天津大学, 2008.
[95]罗文静.数据挖掘中可视化技术研究与实现[D].成都:电子科技大学, 2007.
[96]朱绍文,王泉德,黄浩,等.关联规则挖掘技术及发展动向[J].计算机工程, 2000, 26(9): 4-6.
[97]郭崇慧,田凤占,靳晓明,等.数据挖掘教程[M].北京:清华大学出版社, 2005.
[98] Aggarwal C, Yu P. Mining large itemsets for association rules[J]. Data Engineering Bulletin, 1998, 21(l): 23-31.
[99]邵晶峰,于忠清.数据挖掘原理与算法[M].北京:中国水利水电出版社, 2003.
[100]廖芹,郝志峰,陈志宏.数据挖掘与数学建模[M].北京:国防工业出版社, 2010.
[101] Nikolay P. Patterns of seasonal and interannual variability of remotely sensed chlorophyll[J]. Earth and Environmental Science, 2005, 5: 143-157.
[102] Yoder O, Reilly J, Barnard A, et al. Variability in coastal zone color canner (CZCS) chlorophyll imagery of ocean margin waters off the US East Coast[J]. Continental Shelf Research, 2001, 21: 1191-1218.
[103] Iida T, Saitoh S. Temporal and spatial variability of chlorophyll concentrations in the Bering Sea using empirical orthogonal function (EOF) analysis of remote sensing data[J]. Deep Sea Research, 2007, 54: 2657-2671.
[104]万小芳.台湾海峡表层叶绿素含量的季节、年际变化特征研究[J].台湾海峡, 2007, 26(1): 36-45.
[105]邹斌,邹亚荣,金振刚.渤海海温与叶绿素季节空间变化特征分析[J].海洋科学进展, 2005, 4(23): 487-492.
[106]朱伟,姜谋余,赵联芳,等.悬浮泥沙对藻类生长影响的实测与分析[J].水科学进展, 2010, 21(2): 241-247.
[107]张昭涛.数据挖掘聚类算法研究[D].成都:西南交通大学, 2005.
[108] Tobler W. A computer movie simulating urban growth in the Detroit Region[J]. Economic Geography, 1970, 46: 234-240.
[109]张新峰.空间自相关的数据分析方法与应用研究[D].兰州:兰州大学, 2009.
[110]张彤辉,詹海刚,陈楚群.南海表层叶绿素的空间变异分析[J].热带海洋学报, 2007, 26(5): 9-14.
[111]张新峰,戴小杰,汪俭彬,等.空间自相关指数进展及其在南亚海啸期间叶绿素a异常波动检测中的应用[J].兰州大学学报(自然科学版), 2010, 46: 226-237.
[112]王远飞,何洪林.空间数据分析方法[M].北京:科学出版社, 2007.
[113]裴小琴,冯子健,李晓松,等. 2004-2005年内蒙古自治区布鲁氏菌病发病的空间自相关分析[J].中华疾病控制杂志, 2009, 13(6): 654-658.
[114] Cliff A, Ord J. Spatial Proeesses: Models and Applications[M]. London: Pion, 1981.
[115] Anselin L. Spatial Econometrics: Methods and Models[M]. Boston: Kluwer Academic, 1988.
[116] Anselin L. Exploring Spatial Data with GeoDa: a Workbook[EB/OL]. http://www.csiss.org/clearinghouse/GeoDa/geodaworkbook.pdf, 2005-3-6.
[117] Anselin L. Local indicators of spatial association - LISA[J]. Geographical Analysis, 1995, 27: 93-115.
[118] Andrews D. A note on the unbiasedness of feasible GIS, quasi-maximum likelihood, robust, adaptive and spectral estimators of the linear model[J]. Econometrica, 1986, 54(3): 687-698.
[119] Burridge P. On the Cliff-Ord test for spatial autocorrelation[J]. Journal of the Royal Statistical Society, 1980, B42: 107-108.
[120] Anselin L, Florax R, Rey S. Advanced in Spatial Econometrics: Methodology, Tools and Applications[M]. Berlin: Apringer-Verlag, 2004.
[121] Chen Q. Cellular Automata and Artificial Intelligence in Ecohydraulics Modelling[M]. London: Taylor & Francis Group, 2004.
[122] Lee J, Huang Y, Dickman M, et al. Neural network modelling of coastal algal blooms[J]. Ecological Modelling, 2003, 159: 179-201.
[123] Recknagel F. ANNA - artificial neural network model for predicting species abundance and succession of blue green algae[J]. Hydrobiologia, 1997, 349: 47-57.
[124]陈求稳, Mynett A,王菲.软计算在生态模型中的应用[J].生态学报, 2006, 26(8): 2594-2601.
[125]王攀,万君康,冯珊.创建计算智能的软计算的混合方法研究[J].武汉理工大学学报, 2005, 27(2): 76-83.
[126] Zadeh L. Soft computing and fuzzy logic[J]. IEEE Software, 1994, 11(6): 48-56.
[127]吴京洪,杨秀环,唐宝英,等.人工神经网络预报浮游植物生长趋势的研究[J].中山大学学报(自然科学版), 2000, 39(6): 54-58.
[128]王凌.智能优化算法及其应用[M].北京:清华大学出版社&施普林格出版社, 2001.
[129] Jang J, Sun C, Mizutani E. Neural-fuzzy and Soft Computing[M]. Englewood Cliffs: Prentice Hall, 1997.
[130] Keller J, Tahari H. Implementation of conjunctive and disjunctive fuzzy logic rules with neural networks[J]. International Journal of Approximate Reasoning, 1992, 6(2): 221-240.
[131] Lee S, Lee E. Fuzzy neural networks[J]. Mathematical Biosciences, 1975, 23: 151-177.
[132] Pedrycz W. Neurocomputations in relational systems[J]. Pattern Analysis and Machine Intelligence, 1991, 13: 289-296.
[133] Li R, Zhang Y. Fuzzy logic controller based on genetic algorithm[J]. Fuzzy Sets and Systems, 1996, 83(5): 1-10.
[134] Bonissone P, Chen Y, Goebel K, et al. Hybrid soft computing systems: industrial and commercial applications[J]. Proceedings of the IEEE, 1999, 87(9): 1641-1671.
[135]向先全,陶建华.基于模糊识别和遗传神经网络的渤海湾叶绿素a预测研究[J].海洋环境科学, 2011, 30(2): 239-242.
[136] Vapnik V.统计学习理论的本质[M].张学工,译.北京:清华大学出版社, 2000.
[137]刘靖旭,蔡怀平,谭跃进.支持向量回归参数调整的一种启发式算法[J].系统仿真学报, 2007, 19(7): 1540-1547.
[138]向先全,陶建华.基于GA-SVM的渤海湾富营养化模型[J].天津大学学报, 2011, 44(3): 215-220.
[139]徐海根,王顺庆,王万雄.数学生态学稳定性理论与方法[M].北京:科学出版社, 2004.
[140]叶飞,陈求稳,吴世勇,等.空间显式模型模拟河流岸边带植被在水库运行作用下的演替[J].生态学报, 2008, 28(6): 7-16.
[141]黎夏,叶嘉安,刘小平,等.地理模拟系统:元胞自动机与多智能体[M].北京:科学出版社, 2007.
[142] David A, Ricard V. The DivGame simulator: a stochastic cellular automata model of rainforest dynamics[J]. Ecological Modelling, 2000, 133: 131-l41.
[143] Chen Q, Mynett A, Minns A. Application of cellular automata to modelling competitive growths of two underwater species Chara aspera and Potamogeton pectinatus in Lake Veluwe[J]. Ecological Modelling, 2002, 147: 253-265.
[144] Chen Q, Ye F. Unstructured cellular automata and the application to model river riparian vegetation dynamics[J]. Lecture Notes in Computer Sciences, 2008, 5191: 337-344.
[145]管玉娟,张利权,陈春祥.基于CO-CA的海岸带盐沼植被动态扩散模型研究[J].武汉大学学报(信息科学版), 2009, 34(6): 701-705.
[146] Ellison A, Bedford B. Response of a wetland vascular plant community to disturbance: a simulation study[J]. Ecological Applications, 1995, 5: 109-123.
[147] Clarke K, Gaydos L. Loose-coupling a cellular automaton model and GIS: long-term urban growth prediction for San Francisco and Washington Baltimore[J]. International Geographical Information Systems, 1998, 12(7): 699-714.
[148] Gardner M. Wheels, Life, and Other Mathematical Amusements[M]. New York: W. H. Freeman, 1983.
[149] Wolfram S. Statistical mechanics of cellular automata[J]. Reviews of Modern Physics, 1983, 55(3): 601-644.
[150]刘亚敏.元胞自动机在自然灾害预警和模拟方面的应用研究[D].青岛:中国海洋大学, 2005.
[151]贾斌,高自友,李克平,等.基于元胞自动机的交通系统建模与模拟[M].北京:科学出版社, 2007.
[152]曹中初,孙苏南. CA与GIS的集成用于地理信息的动态模拟和建模[J].测绘通报, 1999, 11: 7-9.
[153]陈求稳.河流生态水动力学坝下河道生态效应与水库生态友好调度[M].北京:科学出版社, 2010.
[154] Wu F, Webster C. Simulation of land development through the integration of cellular automata and multicriteria evaluation[J]. Environment and Planning, 1998, 25: 103-126.
[155] Chen Q, Mynett A. Predicting Phaeocystis globosa bloom in Dutch coastal waters by decision trees and nonlinear piecewise regression[J]. Ecological Modelling, 2004, 176: 277-290.
[156]黎夏,叶嘉安.基于神经网络的元胞自动机及模拟复杂土地利用系统[J].地理研究, 2005, 24(1): 19-27.
[157]杨青生,黎夏.基于支持向量机的元胞自动机及土地利用变化模拟[J].遥感学报, 2006, 10(6): 836-846.
[158]杨青生,黎夏.基于粗集的知识发现与地理模拟以深圳市土地利用为例[J].地理学报, 2006, 61(8): 882-894.
[159]黎夏,叶嘉安.基于神经网络的单元自动机以及真实和优化的城市模拟[J].地理学报, 2002, 57(2): 159-166.
[160]黎夏,叶嘉安.知识发现及地理元胞自动机[J].中国科学D辑地球科学, 2004, 34(9): 865-872.
[161]陈求稳,欧阳志云.生态水力学耦合模型及其应用[J].水利学报, 2005, 36(11): 1273-1279.
[162] Chen Q, Mynett A. Modelling algal blooms in the dutch coast waters by integrated numerical and fuzzy cellular automata approaches[J]. Ecological Modelling, 2006, 199(1): 73-81.
[163]孙健.海湾、近岸海域水交换研究的关联矩阵方法及应用[D].天津:天津大学, 2007.
[164]聂红涛.近岸海域水环境综合管理中的若干基础问题研究及应用[D].天津:天津大学, 2010.
[165]张娜.生态学中的尺度问题尺度上推[J].生态学报, 2007, 27(10): 4252-4266.
[2]聂红涛,陶建华.渤海湾海岸带开发对近海水环境影响分析[J].海洋工程, 2008, 26(3): 44-50.
[3] Sun T, Tao J. Experimental and numerical study of wave-induced long-shore currents on a mild slope beach[J]. China Ocean Engineering, 2005, 19(3): 469-484.
[4]国家海洋局. 2008年中国海洋环境质量公报[R].北京:国家海洋局, 2009.
[5]赵海萍.渤海湾浮游细菌及水层生态水动力学模拟[D].天津:天津大学, 2006.
[6]阚文静,张秋丰,石海明,等.近年来渤海湾营养盐变化趋势研究[J].海洋环境科学, 2010, 29(2): 238-241.
[7]王勇,焦念志.营养盐对浮游植物生长的上行效应的研究方法[J].海洋科学, 2000, 24(11): 16-18.
[8]齐雨藻,楚建华,黄奕华.诱发海洋褐胞藻赤潮的环境因素分析[J].海洋通报, 1993, 12(2): 30-34.
[9] Handan C, Nilsun D, Arzu K, et al. Use of principal component scores in multiple linear regression models for prediction of chlorophyll-a in reservoirs[J]. Ecological Modelling, 2005, 181: 581-589.
[10]桑艳丽.统计分析在渤海湾浮游动物数据处理中的应用[D].济南:山东大学, 2009.
[11]许勇,张鹰,刘吉堂,等.基于支持向量机分类的海州湾赤潮判别[J].海洋湖沼通报, 2009, 3: 60-65.
[12] Chau K, Muttil N. Data mining and multivariate statistical analysis for ecological system in coastal waters[J]. Journal of Hydroinformatics, 2007, 9(4): 305-317.
[13]夏静.长江口浮游植物变化及影响因子初步研究[D].上海:上海师范大学, 2005.
[14]齐雨藻,洪英,吕颂辉,等.中国赤潮生物新纪录种海洋褐胞藻[J].暨南大学学报(自然科学报), 1991, 12(3): 92-95.
[15]徐祖信,廖振良.水质数学模型研究的发展阶段与空间层次闭[J].上海环境科学, 2003, 22(2): 79-85.
[16]穆迪.渤海湾生态水质动力学模型研究[D].天津:天津大学, 2006.
[17]张素香,李瑞杰,罗锋,等.海洋生态动力学模型的研究进展[J].海洋湖沼通报, 2006, 4: 121-127.
[18] Moll A. Regional distribution of primary production in the North Sea simulation by a three dimentional model[J]. Journal of Marine Systems, 1998, 16(1-2): 151-170.
[19] Skogen M, Moll A. Interannual variability of the North Sea primary production: comparison from two model studies[J]. Continental Shelf Research. 2000, 20: 129-151.
[20]吴增茂,俞光耀,张志南,等.胶州湾北部水层生态动力学模型与模拟II:胶州湾北部水层生态动力学的模拟研究[J].青岛海洋大学学报, 1999, 29(3): 429-435.
[21] Cui M, Zhang H. Coupled physical ecological modeling of the central part of Jiaozhou bay II: coupled with an ecological model[J]. Chinese Journal of Oceanology Liminology, 2001, 19(1): 21-28.
[22]魏皓,赵亮,冯士筰.渤海浮游植物生物量与初级生产力变化的三维模拟[J].海洋学报, 2003, 25(2): 66-72.
[23]魏皓,赵亮,冯士筰.渤海碳循环与浮游植物动力学过程研究[J].海洋学报, 2003, 25(2): 151-156.
[24]李清雪.海湾浮游生物及氮营养盐生态水动力学模拟[D].天津:天津大学, 2007.
[25]宋文筠.渤海湾浮游生态系统动力学模型[D].天津:天津大学, 2002.
[26]向先全,陶建华.水信息学及其在水环境中的应用研究综述[J].生态环境学报, 2009, 18(4): 1587-1593.
[27]李树平.水信息学概述[J].给水排水, 2002, 28(4): 90-94.
[28] Michael B. Introducing hydroinformatics[J]. Journal of Hydroinformatics, 1999, 1(1): 3-l9.
[29] Appignanesi R, Garatt C. Postmodernism for Beginners[M]. Cambridge: Cambridge University Press, 1995.
[30]王泽良,陶建华.海湾水质模型的信息化研究[J].海洋通报, 1999, 18(4): 55-63.
[31] Los F, Villars M, Van M. A 3-dimensional primary production model (BLOOM/GEM) and its applications to the (southern) North Sea (coupled physical chemical ecological model)[J]. Journal of Marine Systems, 2008, 74(1-2): 259-294.
[32] Xu J, Hood R. Modeling biogeochemical cycles in Chesapeake Bay with a coupled physical-biological model[J]. Estuarine, Coastal and Shelf Science, 2006, 69(1-2): 19-46.
[33] Yamane N, Nakatsuji K, Muraoka K. Field data collection and modeling for verification of an ecosystem model in Osaka Bay[J]. Estuarine and Coastal Modeling, 1997, 4: 196-210.
[34] Murray A, Parslow J. Modelling of nutrient impacts in Port Phillip Bay - a semi-enclosed marine Australian ecosystem[J]. Marine and Freshwater Research, 1999, 50(6): 597-611.
[35]李德仁,王树良,史文中,等.论空间数据挖掘和知识发现[J].武汉大学学报(信息科学), 2001, 26(6): 491-499.
[36]梁秀菊.浅析统计学与数据挖掘[J].经济与社会发展, 2008, 6(8): 38-42.
[37]张小娟.数据挖掘技术在水资源领域的应用研究[D].北京:中国水利水电科学研究院, 2007.
[38]夏登文,石绥祥,于戈,等.海洋数据仓库及数据挖掘技术方法研究[J].海洋通报, 2005, 24(3): 60-65.
[39]宁勇.数据挖掘在海洋环境在线监测及赤潮灾害智能预警系统中的应用[D].济南:山东大学, 2008.
[40]罗文静.数据挖掘中可视化技术研究与实现[D].成都:电子科技大学, 2007.
[41]魏红宇,张峰,李四海.海洋数据挖掘技术应用研究[J].海洋通报, 2008, 27(6): 82-87.
[42] Bridges S, Hodges J, Wooley B, et al. Knowledge discovery in an oceanographic database[J]. Applied Intelligence, 1999, 11(2): 135-148.
[43]马超飞,刘建强.遥感图像多维量化关联规则挖掘[J].遥感技术与应用, 2003, 18(4): 243-247.
[44] Kitamoto A. Spatio-temporal data mining for typhoon image collection[J]. Journal of Intelligent Information Systems, 2002, 19(1): 25-41.
[45]冯剑丰,王洪礼,孙景.渤海赤潮预测的研究现状及展望[J].气象水文海洋仪器, 2004, 1: 10-13.
[46]武孔春.概念驱动的加工与数据驱动的加工——科学信息是怎样进化的[J].自然杂志, 2002, 24(3): 178-181.
[47]周涛.软计算与人工智能[J].福建电脑, 2006, 1: 55-56.
[48] Zadeh L. Fuzzy logic, neural networks and soft computing[J]. Communications of the ACM, 1994, 37(3): 77-84.
[49]张颖,刘艳秋.软计算方法[M].北京:科学出版社, 2002.
[50]王攀,万君康,冯珊.创建计算智能的新方法软计算的若干问题研究[J].武汉理工大学学报, 2004, 28(4): 618-621.
[51]温显斌,张桦,张颖,等.软计算及其应用[M].北京:科学出版社, 2009.
[52] Hugh W, Friedrich R. Towards a genetic artificial neural network model for dynamic prediction of algal abundance in freshwater lakes[J]. Ecological Modelling, 2001, 146: 69-84.
[53]杨建强,罗先香,丁德文,等.赤潮预测的人工神经网络方法初步研究[J].海洋科学进展, 2003, 21(3): 318-324.
[54] Salski A. Fuzzy clustering of fuzzy ecological data[J]. Ecological Informatics, 2007, 2(3): 262-269.
[55] Chen Q, Mynett A. Integration of data mining techniques with heuristic knowledge in a fuzzy logic modelling of eutrophication in Taihu Lake[J]. Ecological Modelling, 2003, 162: 55-67.
[56]沈菲,曲阳,李会民,等.浮游植物密度的人工神经网络预测研究[J].海洋技术, 2005, 24(1): 44-47.
[57]李祚泳,张欣莉,丁晶.水质污染损害指数评价的普适公式[J].水科学进展, 2001, 12(2): 160-164.
[58]李祚泳,彭荔红,吕玉嫦.基于遗传算法的普适卡森指数公式[J].中国环境科学, 2001, 21(2): 144-147.
[59]冯剑丰,王洪礼,李胜朋.基于支持向量机的浮游植物密度预测研究[J].海洋环境科学, 2007, 26(5): 438-441.
[60]王长江.渤海赤潮生态环境评价与非线性预测系统[D].天津:天津大学, 2005.
[61]窦君鸿.基于支持向量机的生态环境预警及环境指标预测方法研究[D].北京:中国农业人学, 2004.
[62] GAO S, Wu Z, Xie H. The development and applications of Kalman filters in meterrological data assimilation[J]. Advance in Earth Sciences, 2000, 15(5): 571-575.
[63] Friedrichs M. Assimilation of JGOFS EqPac and SeaWiFS data into a marine ecosystem model of the central equatorial Pacific Ocean[J]. Deep Sea Research II, 2002, 49: 289-319.
[64] Garcia G, Hoepffner N, Ouberdous M. Assimilation of SeaWiFS data in a coupled physical-biological model of the Adriatic sea[J]. Journal of Marine Systems, 2003, 40: 233-252.
[65] Allen J, Eknes M, Evensen G. An ensemble Kalman filter with a complex marine ecosystem model: hindcasting phytoplankton in the Cretan Sea[J]. Annales Geophysicae, 2002, 20: 1-13.
[66] Eknes M, Evensen G. An ensemble Kalman filter with a 1-D marine ecosystem model[J]. Journal of Marine Systems, 2002, 36: 75-100.
[67] Natvik L, Evensen G. Assimilation of ocean colour data into a biochemical model of the North Atlantic I: data assimilation experiments[J]. Journal of Marine Systems, 2003, 40: 127-153.
[68] Hurtt G, Armstrong R. A pelagic ecosystem model calibrated with BATS data[J]. Deep Sea Research II, 1996, 43: 653-683.
[69]万振文,袁业立,乔方立.海洋赤潮生态模型参数优化研究[J].海洋与湖沼, 2000, 31(2): 205-209.
[70]马寨璞,井爱芹.海洋科学中的数据同化方法意义、结构与发展现状[J].海岸工程, 2005, 24(4): 83-99.
[71] Roverso D. Intelligent system integration: guiding principles, examples and lessons learned[J]. Progress in Nuclear Energy, 2005, 46(3-4): 190-205.
[72]万显烈.利用离散点插值扩展法评价大连湾水质状况[J].辽宁城乡环境科技, 2004, 18(6): 41-42.
[73]穆迪,袁德奎,陶建华.地理信息系统在渤海湾水体富营养化研究中的应用[J].海洋技术, 2006, 25(1): 73-77.
[74]王桥,吴纪桃.空间决策支持系统中的模型标准化问题研究[J].测绘学报, 1999, 2(28): 172-176.
[75]张宇羽.水质预测与评价管理决策支持系统[D].广州:广东工业大学, 2002.
[76]黄添强.基于空间数据挖掘的环境调控空间决策支持系统研究[D].福州:福州大学, 2002.
[77]唐崇杰,林继发.区域水环境管理决策支持系统的研究和开发以湛江市为例[J].资源环境与发展, 2007, 3: 30-34.
[78]曾维华.多源信息融合技术在内陆湖库水华预警中的研究进展与展望[J].长江流域资源与环境, 2009, 18(1): 72-78.
[79]吴小一.河流水环境数值模拟及可视化研究[D].重庆:重庆大学, 2006.
[80]顾正华,唐洪武,李云,等.水信息学与智能水力学[J].河海大学学报(自然科学版), 2003, 31(5): 518-521.
[81]杨世民,董树刚,李锋,等.渤海湾海域生态环境的研究Ⅰ:浮游植物种类组成和数量变化[J].海洋环境科学, 2007, 26(5): 442-445.
[82]杨世民,董树刚,窦明武,等.渤海湾海域生态环境的研究Ⅱ:水体富营养化的评价与分析[J].海洋环境科学, 2007, 26(6): 541-545.
[83]朱静.近岸海域水污染物输移规律及环境容量研究[D].南京:河海大学, 2007.
[84]王洪礼,冯剑丰,沈菲.渤海赤潮藻类生态动力学模型的非线性动力学研究[J].海洋技术, 2002, 21(3): 8-12.
[85]赵亮,魏皓,冯士筰.渤海氮磷营养盐的循环和收支[J].环境科学, 2002, 23(1): 78-81.
[86]何恩业,李海,任湘湘,等. BP人工神经网络在渤海湾叶绿素预测中的应用[J].海洋预报, 2008, 25(2): 1-10.
[87] Tao J, Wang Z. Refined water quality modeling of Bohai Bay[J]. Environmental and Coastal Hydraulics, 1997, 2: 3-8.
[88]王泽良,陶建华,季民,等.渤海湾中化学需氧量(COD)扩散、降解过程研究[J].海洋通报, 2004, 23(1): 27-31.
[89]王泽良,王日新,陶建华.渤海湾流场以及污染物分布的数值模拟研究[J].海洋与湖沼, 1999, 30(2): 224-230.
[90]邓华健.渤海湾沉积物-水界面营养盐交换通量的研究[D].天津:天津大学, 2004.
[91]张洁帆.渤海湾沉积物和水界面间营养盐的交换通量研究[D].天津:天津大学, 2007.
[92]高庆春.渤海湾赤潮监控区细菌对浮游生态系统影响的研究[D].天津:天津大学, 2007.
[93]安斐.渤海湾富营养化模糊评价与预测研究[D].天津:天津大学, 2007.
[94]向先全.基于模糊理论和神经网络方法的渤海湾富营养化模型研究[D].天津:天津大学, 2008.
[95]罗文静.数据挖掘中可视化技术研究与实现[D].成都:电子科技大学, 2007.
[96]朱绍文,王泉德,黄浩,等.关联规则挖掘技术及发展动向[J].计算机工程, 2000, 26(9): 4-6.
[97]郭崇慧,田凤占,靳晓明,等.数据挖掘教程[M].北京:清华大学出版社, 2005.
[98] Aggarwal C, Yu P. Mining large itemsets for association rules[J]. Data Engineering Bulletin, 1998, 21(l): 23-31.
[99]邵晶峰,于忠清.数据挖掘原理与算法[M].北京:中国水利水电出版社, 2003.
[100]廖芹,郝志峰,陈志宏.数据挖掘与数学建模[M].北京:国防工业出版社, 2010.
[101] Nikolay P. Patterns of seasonal and interannual variability of remotely sensed chlorophyll[J]. Earth and Environmental Science, 2005, 5: 143-157.
[102] Yoder O, Reilly J, Barnard A, et al. Variability in coastal zone color canner (CZCS) chlorophyll imagery of ocean margin waters off the US East Coast[J]. Continental Shelf Research, 2001, 21: 1191-1218.
[103] Iida T, Saitoh S. Temporal and spatial variability of chlorophyll concentrations in the Bering Sea using empirical orthogonal function (EOF) analysis of remote sensing data[J]. Deep Sea Research, 2007, 54: 2657-2671.
[104]万小芳.台湾海峡表层叶绿素含量的季节、年际变化特征研究[J].台湾海峡, 2007, 26(1): 36-45.
[105]邹斌,邹亚荣,金振刚.渤海海温与叶绿素季节空间变化特征分析[J].海洋科学进展, 2005, 4(23): 487-492.
[106]朱伟,姜谋余,赵联芳,等.悬浮泥沙对藻类生长影响的实测与分析[J].水科学进展, 2010, 21(2): 241-247.
[107]张昭涛.数据挖掘聚类算法研究[D].成都:西南交通大学, 2005.
[108] Tobler W. A computer movie simulating urban growth in the Detroit Region[J]. Economic Geography, 1970, 46: 234-240.
[109]张新峰.空间自相关的数据分析方法与应用研究[D].兰州:兰州大学, 2009.
[110]张彤辉,詹海刚,陈楚群.南海表层叶绿素的空间变异分析[J].热带海洋学报, 2007, 26(5): 9-14.
[111]张新峰,戴小杰,汪俭彬,等.空间自相关指数进展及其在南亚海啸期间叶绿素a异常波动检测中的应用[J].兰州大学学报(自然科学版), 2010, 46: 226-237.
[112]王远飞,何洪林.空间数据分析方法[M].北京:科学出版社, 2007.
[113]裴小琴,冯子健,李晓松,等. 2004-2005年内蒙古自治区布鲁氏菌病发病的空间自相关分析[J].中华疾病控制杂志, 2009, 13(6): 654-658.
[114] Cliff A, Ord J. Spatial Proeesses: Models and Applications[M]. London: Pion, 1981.
[115] Anselin L. Spatial Econometrics: Methods and Models[M]. Boston: Kluwer Academic, 1988.
[116] Anselin L. Exploring Spatial Data with GeoDa: a Workbook[EB/OL]. http://www.csiss.org/clearinghouse/GeoDa/geodaworkbook.pdf, 2005-3-6.
[117] Anselin L. Local indicators of spatial association - LISA[J]. Geographical Analysis, 1995, 27: 93-115.
[118] Andrews D. A note on the unbiasedness of feasible GIS, quasi-maximum likelihood, robust, adaptive and spectral estimators of the linear model[J]. Econometrica, 1986, 54(3): 687-698.
[119] Burridge P. On the Cliff-Ord test for spatial autocorrelation[J]. Journal of the Royal Statistical Society, 1980, B42: 107-108.
[120] Anselin L, Florax R, Rey S. Advanced in Spatial Econometrics: Methodology, Tools and Applications[M]. Berlin: Apringer-Verlag, 2004.
[121] Chen Q. Cellular Automata and Artificial Intelligence in Ecohydraulics Modelling[M]. London: Taylor & Francis Group, 2004.
[122] Lee J, Huang Y, Dickman M, et al. Neural network modelling of coastal algal blooms[J]. Ecological Modelling, 2003, 159: 179-201.
[123] Recknagel F. ANNA - artificial neural network model for predicting species abundance and succession of blue green algae[J]. Hydrobiologia, 1997, 349: 47-57.
[124]陈求稳, Mynett A,王菲.软计算在生态模型中的应用[J].生态学报, 2006, 26(8): 2594-2601.
[125]王攀,万君康,冯珊.创建计算智能的软计算的混合方法研究[J].武汉理工大学学报, 2005, 27(2): 76-83.
[126] Zadeh L. Soft computing and fuzzy logic[J]. IEEE Software, 1994, 11(6): 48-56.
[127]吴京洪,杨秀环,唐宝英,等.人工神经网络预报浮游植物生长趋势的研究[J].中山大学学报(自然科学版), 2000, 39(6): 54-58.
[128]王凌.智能优化算法及其应用[M].北京:清华大学出版社&施普林格出版社, 2001.
[129] Jang J, Sun C, Mizutani E. Neural-fuzzy and Soft Computing[M]. Englewood Cliffs: Prentice Hall, 1997.
[130] Keller J, Tahari H. Implementation of conjunctive and disjunctive fuzzy logic rules with neural networks[J]. International Journal of Approximate Reasoning, 1992, 6(2): 221-240.
[131] Lee S, Lee E. Fuzzy neural networks[J]. Mathematical Biosciences, 1975, 23: 151-177.
[132] Pedrycz W. Neurocomputations in relational systems[J]. Pattern Analysis and Machine Intelligence, 1991, 13: 289-296.
[133] Li R, Zhang Y. Fuzzy logic controller based on genetic algorithm[J]. Fuzzy Sets and Systems, 1996, 83(5): 1-10.
[134] Bonissone P, Chen Y, Goebel K, et al. Hybrid soft computing systems: industrial and commercial applications[J]. Proceedings of the IEEE, 1999, 87(9): 1641-1671.
[135]向先全,陶建华.基于模糊识别和遗传神经网络的渤海湾叶绿素a预测研究[J].海洋环境科学, 2011, 30(2): 239-242.
[136] Vapnik V.统计学习理论的本质[M].张学工,译.北京:清华大学出版社, 2000.
[137]刘靖旭,蔡怀平,谭跃进.支持向量回归参数调整的一种启发式算法[J].系统仿真学报, 2007, 19(7): 1540-1547.
[138]向先全,陶建华.基于GA-SVM的渤海湾富营养化模型[J].天津大学学报, 2011, 44(3): 215-220.
[139]徐海根,王顺庆,王万雄.数学生态学稳定性理论与方法[M].北京:科学出版社, 2004.
[140]叶飞,陈求稳,吴世勇,等.空间显式模型模拟河流岸边带植被在水库运行作用下的演替[J].生态学报, 2008, 28(6): 7-16.
[141]黎夏,叶嘉安,刘小平,等.地理模拟系统:元胞自动机与多智能体[M].北京:科学出版社, 2007.
[142] David A, Ricard V. The DivGame simulator: a stochastic cellular automata model of rainforest dynamics[J]. Ecological Modelling, 2000, 133: 131-l41.
[143] Chen Q, Mynett A, Minns A. Application of cellular automata to modelling competitive growths of two underwater species Chara aspera and Potamogeton pectinatus in Lake Veluwe[J]. Ecological Modelling, 2002, 147: 253-265.
[144] Chen Q, Ye F. Unstructured cellular automata and the application to model river riparian vegetation dynamics[J]. Lecture Notes in Computer Sciences, 2008, 5191: 337-344.
[145]管玉娟,张利权,陈春祥.基于CO-CA的海岸带盐沼植被动态扩散模型研究[J].武汉大学学报(信息科学版), 2009, 34(6): 701-705.
[146] Ellison A, Bedford B. Response of a wetland vascular plant community to disturbance: a simulation study[J]. Ecological Applications, 1995, 5: 109-123.
[147] Clarke K, Gaydos L. Loose-coupling a cellular automaton model and GIS: long-term urban growth prediction for San Francisco and Washington Baltimore[J]. International Geographical Information Systems, 1998, 12(7): 699-714.
[148] Gardner M. Wheels, Life, and Other Mathematical Amusements[M]. New York: W. H. Freeman, 1983.
[149] Wolfram S. Statistical mechanics of cellular automata[J]. Reviews of Modern Physics, 1983, 55(3): 601-644.
[150]刘亚敏.元胞自动机在自然灾害预警和模拟方面的应用研究[D].青岛:中国海洋大学, 2005.
[151]贾斌,高自友,李克平,等.基于元胞自动机的交通系统建模与模拟[M].北京:科学出版社, 2007.
[152]曹中初,孙苏南. CA与GIS的集成用于地理信息的动态模拟和建模[J].测绘通报, 1999, 11: 7-9.
[153]陈求稳.河流生态水动力学坝下河道生态效应与水库生态友好调度[M].北京:科学出版社, 2010.
[154] Wu F, Webster C. Simulation of land development through the integration of cellular automata and multicriteria evaluation[J]. Environment and Planning, 1998, 25: 103-126.
[155] Chen Q, Mynett A. Predicting Phaeocystis globosa bloom in Dutch coastal waters by decision trees and nonlinear piecewise regression[J]. Ecological Modelling, 2004, 176: 277-290.
[156]黎夏,叶嘉安.基于神经网络的元胞自动机及模拟复杂土地利用系统[J].地理研究, 2005, 24(1): 19-27.
[157]杨青生,黎夏.基于支持向量机的元胞自动机及土地利用变化模拟[J].遥感学报, 2006, 10(6): 836-846.
[158]杨青生,黎夏.基于粗集的知识发现与地理模拟以深圳市土地利用为例[J].地理学报, 2006, 61(8): 882-894.
[159]黎夏,叶嘉安.基于神经网络的单元自动机以及真实和优化的城市模拟[J].地理学报, 2002, 57(2): 159-166.
[160]黎夏,叶嘉安.知识发现及地理元胞自动机[J].中国科学D辑地球科学, 2004, 34(9): 865-872.
[161]陈求稳,欧阳志云.生态水力学耦合模型及其应用[J].水利学报, 2005, 36(11): 1273-1279.
[162] Chen Q, Mynett A. Modelling algal blooms in the dutch coast waters by integrated numerical and fuzzy cellular automata approaches[J]. Ecological Modelling, 2006, 199(1): 73-81.
[163]孙健.海湾、近岸海域水交换研究的关联矩阵方法及应用[D].天津:天津大学, 2007.
[164]聂红涛.近岸海域水环境综合管理中的若干基础问题研究及应用[D].天津:天津大学, 2010.
[165]张娜.生态学中的尺度问题尺度上推[J].生态学报, 2007, 27(10): 4252-4266.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |