区域森林资源可持续水平评价系统研建
|
摘要
区域森林资源可持续水平评价系统是区域森林资源可持续水平评价工作信息化、智能化的标志。本系统融计算机技术、GIS技术、人工神经网络技术于一体，利用MAPGIS的二次开发耦合GA_BP评价网络模型，本着充分利用现有各区域的林业空间数据库信息的思想，实现了评价工作的实时化、动态化。
本文中率先提出区域森林资源可持续水平评价的智能化、信息化问题，改变了目前人们对此问题的解决模式，并提供了一个应用评价平台，并在区域森林可持续水平评价领域首次引入了GA_BP模型：在评价指标方面实现了智能提取和归一化，以及评价指标的灵活选取功能，实现了评价自主化原则，做到“因人而异、因地制宜”—即可根据评价者所关心的问题域来动态选取评价指标，可根据当地具体情况具体分析，最大程度的体现了评价平台与用户的互动性；耦合了GA_BP模型与GIS，建立了评价系统，利用VC++以及基于VC++的MAPGIS二次开发，实现了系统的设计；实现了评价结果表达的自然化，即以三原色立体坐标空间来描述系统的可持续水平，其中红色值代表社会指标体系、绿色值代表生态指标体系、蓝色值代表经济评价结果；实现了评价数据管理的信息化，根据各区域情况实时变化，数据库实时更新，评价结果也相应的更新，方便实现跟踪评价。
本系统开发严格遵照软件工程的方法和把评价工作视为一个系统工程的思想，采用面向对象技术和基于MFC类库的MAPGIS二次开发方法。首先，在文中的第一部分指出了该项研究的内容和进行该项工作的意义所在；接下来对评价系统的用户需求、功能需求以及系统结构模块进行了详细的分析，指出了系统开发的策略、方法以及系统运行的环境；在文中的第三部分对所要使用的评价模型的应用可行性进行了说明，并得出了应用结合GA_BP模型作为评价模型的结论，进而给出了区域森林可持续GA_BP评价模型的设计，以及对模型中功能划分、各模块的功能做了介绍，并给出了系统设计的各模块应用界面。
文中的软件设计与实现部分描述了系统从概念设计到具体设计实现数据管理、系统的空间设计分析与管理、系统的属性数据管理、GA_BP评价模型的实现与评价结果的表达各个预定功能模块的过程；最后，利用实例对系统的功能进行了验证并取得了比较满意的结果。在结束语中笔者分别对所研建系统的创新点、缺点以及以后的发展方向做了说明。
The evaluation system of regional forestry resources sustainable level marks the informationizatton and intellectualization of the evaluation work in this field. Merging computer technology and GIS techniques with the artificial neuro-netmork skills and utilizing the secondary development of MAPGIS coupled with the model of GA-BP appraisal network, the system makes the real-time process possible and the evaluation work dynamic in time with the concept of making full use of the present information of each regional forestry space database.
Being the first to put forward the matter of the informationization and intellectualization of regional forestry sustainable level evaluation and intellectualization of regional forestry sustainable level evaluation and introduce GA-BP model to it, this paper changes the existing mode which people use to solve the problem and provides a platform for application evaluation. By realizing the unity and artificial withdrawal as well as the flexible selection function of the evaluation indices, the system carries out the principle of being independent. It succeeds in varying with each individual and being in liae with local conditions.i.e. Dealing with concrete problems according to specific situations and choosing evaluation indices dynamically on the ground of the questions that the evaluators are widely concerned about. Thus it reflects the maximum interaction between the evaluation platform and its consumers. The evaluation system is constructed through coupling GIS and GA-BP model and by utilizing VC++ to de
sign the system. As a result the evaluation outcome can be expressed naturally. That is to describe the sustainable level of the system through using a three-dimensional coordinate space in three primary colours, with the value in red standing for social index system, the value in green referring to ecological index system and the value in blue representing the outcome of economic evaluation respectively. Consequently the informationization of the evaluation data management is fulfilled. At the same time the real-time renewal and the renewal of the evaluation result are achieved on the basis of the real-time variation of each region, whkh makes it convenient to realize tracing evaluation.
The exploration of this system is in strict accordance with the software project made and treating evaluation work as a systematic project. Based on the MAPGIS secondary development method of the database of MFC kind, it adopts the facing object techniques. Accordingly, this paper faHs into the following pants. First, the content of this research and its significance are presented; Secondly, detailed analyses on the demand of consumers, the functional demand and the structural model of the system are made. Also the development strategy and methods of the system as well as the environment in which it can operate are pointed out; Thirdly, instructions to the applied feasibility of the model is given. It includes by saying that GA-BP model can be combined and used as evaluation model. In the fourth part, the design of GA-BP evaluation model is illustrated. Then the functional division of the model and the function of each part are mentioned. The application interface designed by the system of each part is also
discussed. In this paper the design and realization part of the software elaborates on the system from its conceptual planning to concrete
design which carries out the management of data, the management and analysis on space design of the system, its property data management, the realization of GA-BP evaluation model and the process of each predetermined functional part expressed as evaluation outcome. Finally, an example is used to verify the function of the system and a comparative satisfactory outcome has been obtained. To conclude, the author focuses on the originality, drawbacks and the direction in which the system constructed will develop.
本文中率先提出区域森林资源可持续水平评价的智能化、信息化问题，改变了目前人们对此问题的解决模式，并提供了一个应用评价平台，并在区域森林可持续水平评价领域首次引入了GA_BP模型：在评价指标方面实现了智能提取和归一化，以及评价指标的灵活选取功能，实现了评价自主化原则，做到“因人而异、因地制宜”—即可根据评价者所关心的问题域来动态选取评价指标，可根据当地具体情况具体分析，最大程度的体现了评价平台与用户的互动性；耦合了GA_BP模型与GIS，建立了评价系统，利用VC++以及基于VC++的MAPGIS二次开发，实现了系统的设计；实现了评价结果表达的自然化，即以三原色立体坐标空间来描述系统的可持续水平，其中红色值代表社会指标体系、绿色值代表生态指标体系、蓝色值代表经济评价结果；实现了评价数据管理的信息化，根据各区域情况实时变化，数据库实时更新，评价结果也相应的更新，方便实现跟踪评价。
本系统开发严格遵照软件工程的方法和把评价工作视为一个系统工程的思想，采用面向对象技术和基于MFC类库的MAPGIS二次开发方法。首先，在文中的第一部分指出了该项研究的内容和进行该项工作的意义所在；接下来对评价系统的用户需求、功能需求以及系统结构模块进行了详细的分析，指出了系统开发的策略、方法以及系统运行的环境；在文中的第三部分对所要使用的评价模型的应用可行性进行了说明，并得出了应用结合GA_BP模型作为评价模型的结论，进而给出了区域森林可持续GA_BP评价模型的设计，以及对模型中功能划分、各模块的功能做了介绍，并给出了系统设计的各模块应用界面。
文中的软件设计与实现部分描述了系统从概念设计到具体设计实现数据管理、系统的空间设计分析与管理、系统的属性数据管理、GA_BP评价模型的实现与评价结果的表达各个预定功能模块的过程；最后，利用实例对系统的功能进行了验证并取得了比较满意的结果。在结束语中笔者分别对所研建系统的创新点、缺点以及以后的发展方向做了说明。
The evaluation system of regional forestry resources sustainable level marks the informationizatton and intellectualization of the evaluation work in this field. Merging computer technology and GIS techniques with the artificial neuro-netmork skills and utilizing the secondary development of MAPGIS coupled with the model of GA-BP appraisal network, the system makes the real-time process possible and the evaluation work dynamic in time with the concept of making full use of the present information of each regional forestry space database.
Being the first to put forward the matter of the informationization and intellectualization of regional forestry sustainable level evaluation and intellectualization of regional forestry sustainable level evaluation and introduce GA-BP model to it, this paper changes the existing mode which people use to solve the problem and provides a platform for application evaluation. By realizing the unity and artificial withdrawal as well as the flexible selection function of the evaluation indices, the system carries out the principle of being independent. It succeeds in varying with each individual and being in liae with local conditions.i.e. Dealing with concrete problems according to specific situations and choosing evaluation indices dynamically on the ground of the questions that the evaluators are widely concerned about. Thus it reflects the maximum interaction between the evaluation platform and its consumers. The evaluation system is constructed through coupling GIS and GA-BP model and by utilizing VC++ to de
sign the system. As a result the evaluation outcome can be expressed naturally. That is to describe the sustainable level of the system through using a three-dimensional coordinate space in three primary colours, with the value in red standing for social index system, the value in green referring to ecological index system and the value in blue representing the outcome of economic evaluation respectively. Consequently the informationization of the evaluation data management is fulfilled. At the same time the real-time renewal and the renewal of the evaluation result are achieved on the basis of the real-time variation of each region, whkh makes it convenient to realize tracing evaluation.
The exploration of this system is in strict accordance with the software project made and treating evaluation work as a systematic project. Based on the MAPGIS secondary development method of the database of MFC kind, it adopts the facing object techniques. Accordingly, this paper faHs into the following pants. First, the content of this research and its significance are presented; Secondly, detailed analyses on the demand of consumers, the functional demand and the structural model of the system are made. Also the development strategy and methods of the system as well as the environment in which it can operate are pointed out; Thirdly, instructions to the applied feasibility of the model is given. It includes by saying that GA-BP model can be combined and used as evaluation model. In the fourth part, the design of GA-BP evaluation model is illustrated. Then the functional division of the model and the function of each part are mentioned. The application interface designed by the system of each part is also
discussed. In this paper the design and realization part of the software elaborates on the system from its conceptual planning to concrete
design which carries out the management of data, the management and analysis on space design of the system, its property data management, the realization of GA-BP evaluation model and the process of each predetermined functional part expressed as evaluation outcome. Finally, an example is used to verify the function of the system and a comparative satisfactory outcome has been obtained. To conclude, the author focuses on the originality, drawbacks and the direction in which the system constructed will develop.
引文
[1] Niu Wen-yuan et al, 1993,Spatial systems approach to sustainable development:a conceptual framework, Environment Management: 179～186
[2] 邢金香，李良厚等．林业在社会经济可持续发展中的作用[J]，河南林业科技，2003年9月第23卷第3期：31～32
[3] 张建国．现代林业论[M]，北京：中国林业出版社，1996：70～74
[4] 李禄康．政策机构和达到可持续发展的手段．第十一届世界林业大会文献选编．北京：中国环境科学出版社，1998：305～310
[5] 韩亚军．综合评价理论与方法[M]．北京：科学出版社．2002年8月第一版：8
[6] 谢金生，徐秋生，曹建华等．区域可持续林业评价指标体系及评价标准的研究[J]，江西农业大学学报，1999年9月，第21卷第3期443～446
[7] 张守功，朱春全，肖文发．森林可持续经营导论[M]，北京：中国林业出版社，2001年7月第一版，8～9
[8] 刘璨．林业持续发展政策设计[J]，世界林业研究，1994，7(5)，11～18
[9] The Santiago Agreement.Criteria and indicators for the conservation and sustainable manegement of temperate and boreal forests[J].J For,1995,93(4): 18～21
[10] 何汉杏，何华春．县级林场可持续林业建设研究[J]．中南林学院学报．第21卷第2期，2001年6月：6～12
[11] 王海，张玉岩．吉林省国有林区可持续发展综合评价指标体系研究[R]．林业经济．2000年第6期：32～36
[12] 郭正刚，程国栋等．甘肃省白龙江林区森林资源可持续发展力的评价[J]．应用生态学报．2003年9月．第14卷第9期：1433～1438
[13] 李宝根，汪正铨．福建省森林资源可持续发展评价指标体系的研究[J]．琳业勘察设计(福建)．2003年第2期：1～5
[14] 蔡为茂．森林持续经营的评价系统[J]．森林工程．1998年9月．第14卷第3期：4～6
[15] 李朝洪，许俊杰，于波涛．中国森林资源可持续发展综合评价方法[J]．东北林业大学学报．第20卷第2期．2002年3月：73～76
[16] 杨学民，姜志林，张慧．徐州市林业可持续发展评价[J]．福建林学院学报．2003，23(2)：177～181
[17] 郭仁鉴，陈法荣，朱铨．淳安县林业可持续发展能力的评价和分析[J]．浙江林学院学报，2001，18(4)：337～344
[18] 张万里，李雷鸿．大兴安岭新林林业局可持续发展能力评价[J]．东北林业大学学报．第28卷第5期．2000年．9月：125～129
[19] 罗明灿．区域森林资源可持续发展综合评价研究[J]．四川林勘设计1999年第2期：25～33
[20] 吴延熊．区域森林资源可持续发展动态评价的理论探讨[J]．北京林业大学学报．第21卷第1期．1999年1月：62～67
[21] 李朝洪，郝爱民．中国森林资源可持续发展描述指标体系框架的构建[J]，东北林业大学学报，第28卷第5期，2000年9月，122～124
[22] 王伟英．论国有林区的可持续发展[J]，世界林业研究，1998年第5期，70～77
[23] 陈炳浩．我国林业持续发展的原则、内容和途径[J]，世界林业研究，1994，7(2)：19～24
[24] 邓守严，卢振兰，李德志．经济生态系统持续发展的实现途径及其测度体系[J]，世界林业研究，1998(5)：52～57
[25] 史忠植．神经计算[M]．电子工业出版社，1993
[26] 沈政，林庶芝．脑模拟与神经计算机[M]．北京大学出版社，1992
[27] Simon Haykin, Neural Networks [M], Beijing: China Machine Press, Second Edition, 2004,1:1～10
[28] H.Lachowski, et al. Integrating remote sensing with GIS.Journal O Forestry, 1992(12): 16～21
[29] 邬伦，刘瑜，张晶，韦中亚，田愿编著．地理信息系统——原理、方法和应用[M]．北京：科学出版社，2002年2月第一版：172
[30] Huang, W. and R. Lippmann 1987. Comparisons between neural net and conventional classifies [J], IEEE First International Conference on Neural Networks, Vol. Ⅳ. San Diego, California, 21-24 June: 485～494
[31] Hepner, G.F. and N. Ritter, 1989. Application of an artificial neural network to land covers classification of
thematic mapper imagery [M] JPL Int. Tech.l Rep.
[32] Hepner, G.F., T. Logan, N. Ritter, and N. Bryant 1990. Artificial neural network classification using a minimal training set: Comparison to conventional supervised classification [M]. Photogrammetric
[33] Civco, D.L. 1993. Artificial neural networks for land cover classification and mapping [M] International Journal of Geographical Information Systems 7: 173～186.
[34] Gong, P. and J. Chen 1996. Mapping ecological land systems and classification uncertainties from digital elevation and forest-cover data using neural network [M]. Photogrammetrie Engineering and Remote Sensing 62:1249-1260
[35] Markham L.S. Tags dale, C.T., combining neural networks and statistical predictions to solve the classification problem in discriminate analysis [J]. Deeis. Sci.26 (2), 229～242
[36] Jock.A.Blackard, Denis J.Dean Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables [M] Computers and electronics in agriculture 24(1999)131～151
[37] Decatur, S. E. 1989. Application of neural networks to terrain classification[R]. Proceedings of International Joint Conference on Neural Networks 1: 283～288.
[38] Campbell, W.J., S.E. Hill, and R.F. Cromp 1989. Automatic labeling and characterization of objects using artificial neural networks [J]. Telemetric and Informatics 6: 259-271.
[39] MeClelland, G. E., R.N. Dewitt, T.H. Hemmer, L.N. Matheson, and G.O. Moe, 1989. Multispectral Image-processing with a three-layer back-propagation network[R] Proceedings of International Joint Conference on Neural Networks 1: 151～153
[40] Hepner, G.F., T. Logan, N. Ritter, and N. Bryant 1990. Artificial neural network classification using a minimal training set: Comparison to conventional supervised classification.[M] Photogrammetric Engineering and Remote Sensing 56:469～473
[41] Downey, I.D., C.H. Power, I. Kanellopoulos, and G.G. Wilkinson, 1992. A performance comparison of Land sat thematic mapper land cover classification based on neural network techniques and traditional maximum likelihood algorithms and minimum distance algorithms[R]. Proceeding of the Annual Conference of the Remote Sensing Society: 518～528.
[42] Benedicts, J. A., P.H. Swain, and O.K. Esroy 1990. Neural network approaches versus statistical methods in classification of multisource remote sensing data [A]. IEEE Transaction on Geosciences and Remote Sensing 28: 540～552
[43] Peddle, D.R. G.M. Foody, A. Zhang, S.E. Franklin, and E.F. Ledrew 1994. Multisource image classification Ⅱ: an empirical comparison of evidential reasoning, linear diseriminant analysis, and maximum likelihood algorithms for alpine land cover classification [J]. Can. J. Remote Sensing 20:397～408
[44] Gong, P. and J. Chen 1996. Mapping ecological land systems and classification uncertainties from digital elevation and forest-cover data using neural network [M]. Photogrammetric Engineering and Remote Sensing 62: 1249～1260
[45] Ritter, N.D, T.L. Logan, and N.A. Bryant 1988. Integration of neural network technologies with Geographic information systems [J], in: GISSymposium-Intenerating Technology and Geoseiences Applications, Denver, CO,:102～103.
[46] Gong, P. 1994. Integrated analysis of spatial data from multiple sources: An overview. Can. [J]. Remote Sensing 20:349～359
[47] Sui, D.Z., 1994. Recent applications of neural networks for spatial data handling. Can. [J]. Remote Sensing 20: 368～380.
[48] Peuquet, D. J. 1991. An overview of the applications of artificial intelligence approaches for geographic Information Systems[R], In: Proceedings of the Seventh Annual Conference on Interactive Information and Processing Systems for Meteorology Oceanography and Hydrology, New Orleans, LO.
[49] Sui, D.Z, 1993. A neural network-based GIS approach to spatial decision-making [J], The Operational Gcographer 11: 12～20
[50] Wang, F.J. 1992. Incorporating a neural network into GIS for agricultural land suitability analysis [M].
GIS/LIS'922: 804～815.
[51] Zhou, J. and D.L. Civco 1996. Using genetic learning neural networks for spatial decision making in GIS [J].Photogrammetric Engineering and Remote Sensing 11:1287～1295
[52] Deadman, P.J. and H.R. Gimblett, 1997. Applying neural networks to vegetation management plan Development [J]. AI Application 11:107～112.
[53] 庄家礼，陈良富，徐希儒 地表组分温度反演[J]北京大学学报(自然科学版)，第36卷，第6期，2000年11月：850～857
[54] Atkinson, P.M. and A.R. Tatnall 1997. Introduction: Neural networks in remote sensing, Int.[J]. Remote Scnsing 18:699～709
[55] Ryan, T.W., P.J. Sementilli, P. Yuen, and B.R. Hunt 1991. Extractions of shoreline features by neural nets and image processing [M], Photogrammetric Engineering and Remote Sensing 57:947～955
[56] Hermann, P.D. and N. Khazenie 1992. Classification of multispectral remote sensing data using a back propagation neural network [A]. IEEE Transaction on Geoscience and Remote Sensing 30:81～88
[57] Pierce, L.E., D. Sarabandi, and F. T. Ulaby, 1992. Application of artificial neural networks in canopy scattering inversion [A]. IEEE Transaction on Geoscience and Remote Sensing 91:1067～1069
[58] Wilkinson, G.G., I. Kaneilopoulos, C. Kontoes, and J.Megier 1992. A comparison of neural network and expert system methods for analysis of remotely sensed imagery [A]. IEEE Transaction on Geoscience and Remote Sensing 91:62～64
[59] Jan, J.F. 1997. Artificial neural networks for classification of remote sensing data [J], Quart. J. Exp. For. Nat. Taiwan Univ. 11: 79～89
[60] Yoshitomi, K., A. Ishimaru, J. N., Wang and J.S. Chen, 1993. Surface roughness determinations sing spectral correlation of scattered intensities and an artificial neural network technique [A]. IEEE Transaction on Geoscience and Remote Sensing 41:498～502
[61] Tsang, L., Z. Chen, S. Oh, R.J., Marks Ⅱ, and A.T. Chang, 1992. Inversion of snow parameters rum passive microwave remote sensing measurements by a neural network trained with a multiple scattering model[A]. IEEE Transaction on Geoscienee and Remote Sensing 30:1015～1024
[62] Jin, Q.Y. and C. Liu 1997. Biomass retrieval from high dimensional active/passive remote sensing data by using artifieial neural networks. Int. [J]. Remote Sensing 18:971～979
[63] Zhang X., C. Li, and Y. Yuan 1997. Application of neural networks to identifying vegetation types from satellite images [J]. AI Application 11: 99～106
[64] 秦其明，陆荣建．分形与神经网络方法在卫星数字图像分类中的应用[M]．遥感技术2000-11-20 Vol．36No．6．：858～864
[65] Yang, X.B. and W.D. Batehelor 1997. Modeling plant disease dynamics using neural networks [J]. AI Application 11:47～55
[66] Yang, X.B., W.D. Batchelor and A.T. Tschanz 1995. A neural network model to predict soybean us. [J] Psychopathology 75:1172
[67] Batchelor, W.D., X.B. Yang and A.T. Tschanz 1997. Development of a neural network for soybean epidemics[J] Transactions ASAE 40:247～252
[68] Francl, L.J., S. Panigrahi, and T. Pahdi, 1995. Neural network models that predict leaf wemess [M]. Psychopathology 85:1182
[69] Francl, L.J. and S. Panigrahi 1997. Artificial neural network models of wheat leaf wetness [M]. Bicultural and Forest Meteorology 88:57～65
[70] McClendon, R.W. and W.D. Batehelor 1995. Insect pest management neural network [A]. American Society of Agricultural Engineers, St. Joseph, Miehigan, ASAE Paper No. 95,35～60
[71] Cook, D.F. and M.L. Wolfe 1991. A back-propagation neural network to predict average air temperature [J]. AI Applications 5:40～46
[72] Derr, V.E. and R.J. Slutz 1994. Prediction of El Niflo events in the Pacific by means of neural networks [J]. AI Applications 8:51-63
[73] Tangang, F.T., W. W. Hsieh and B. Tang 1997. Forecasting the equatorial pacific temperatures by neural
networrk models [J]. Climate Dynamics 13:135～147
[74] Tangang, F.T., B.Tang, A.H. Monahan, and W. W. Hsieh, 1998. Forecasting ENSO events: A eural network-extended EOF approach [J] Climate 11:29～41
[75] Yi, J. and V.R. Prybutok 1996. A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area [M]. Environ. Pollut. 84:349～357
[76] Keller, T., 1994. Elaborion d'une base de donn(?)es en dendroclimatologie en vue d'une reconstruction climatique dans les Atpes ET la region Mediterranean[R]. Memories de DEA de l'Universit(?) Axi-Marseiile Ⅲ,:33
[77] Guiot, J., R. Cheddadi, I.C. Prentice and D. Jolly 1996. A method of biome and land surface mapping from pollen data: Application to Europe 6000 years ago [J], Palaeoclimate 1: 311～324.
[78] A.L.M aclean,et ai.Using GIS to estimate forest resource changes.Journal of Forestry, 1992(12):22～26
[79] Levine, E.R. and D. Kimes 1997. Predicting soil carbon in Mollisols using neural networks, In: Soil Processes and the Carbon Cycle [M], R. Lal, J.K. Kimble, and R.F.Follett (eds.), CRC Press, FL,: 608.
[80] Ehrman, J.M., T.A. Clair, and A. Bouchard, 1996. Using neural networks to predict pH changes in acidified eastern Canadian lakes [J]. AI Applications 10: 1～8.
[81] Vega-Garcia, C. B.S. Lee, P.M. Woodard, and S.J. Titus 1996. Applying neural network echnology to human-cauaed wildfire occurrence prediction [J], AI Applications 10: 9-18.
[82] 黎粤华，梁颖红，王述洋，人工神经网络技术在林火重灾年预测中的应用前景[J] 林业劳动安全Vol 14,Nol Feb．2001：28～30．
[83] 吴龙标，张本矿，连加锐基于遗传算法的前馈神经网络火灾探测[J]Fire Safety Science Volume 7，Issue 2 (June 1998)
[84] Merobian, E. And Skrzypek, J.A general-purpose simulation for neural models [J]. Simulation, 1992, VOL.59, NO.5
[85] B.T.Guaan and G.Gertner. Using a parallel Distributed Processing System to Model Individual Tree Mortality [J]. For Sci, 1991, 37 (3)
[86] G.Gertner and B.T.Guan, Conceptal Classification: An AI Alternative to Statistical Problems for Classification Problem [J]. For Sci, 1992, 39(3)
[87] 李际平．BP模型在单木树高、胸径生长模拟中的应用[J]．中南林学院学报，1996，6(2)
[88] 李际平．林业专家模拟系统研究[J]．林业资源管理，1996，(特刊)：37～39
[89] 李际平．关于林业决策支持系统的设计思想[J]．决策与决策支持系统，1994，4(1)
[90] 李际平．林业决策支持系统设计模式探讨[J]．中南林学院学报，1991，11(2)
[91] 洪伟，吴承祯．闽东南土壤流失人工神经网络预报研究[J]．土壤侵蚀与水土保持学报，1997，3(3)：52～57
[92] 洪伟，吴承祯，何东进．基于人工神经网络的森林资源管理模型的研究[J]自然资源学报，1998，13(1)：69～72
[93] 何东进，洪伟，吴承祯．人工神经网络用于杉木壮苗定向培育规律的研究[J]．浙江林学院学报，1997，14(4)：339～343
[94] 李际平，邓立斌，何建华．基于人工神经网络的森林资源预测研究[J]中南林学院学报Vol．21 No．4Dec．2001
[95] Maier, H.R. and G. C. Dandy 1996. The use of artificial neural networks for the predition of water quality parameters [J]. Water Resources Research 32: 1013～1022.
[96] Tamari, S., W(?)sten, and J.C. Ruiz-Su(?)Rez, 1996. Testing an artificial neural network for predicting soil hydraulic conductivity [J]. Soil Sci. Am. 60: 1732～1741.
[97] Levine, E.R. and D. Kimes 1997. Predicting soil carbon in Mollisols using neural networks, In: Soil Processes and the Carbon Cycle [M], R. Lal, J.K. Kimble, and R.F.Follett (eds.), CRC Press, FL,: 608.
[98] Ehrman, J.M., T.A. Clair, and A. Bouchard, 1996. Using neural networks to predict pH changes in acidified eastern Canadian lakes [J]. AI Applications 10: 1～8.
[99] 楼文高，王延政．基于BP网络的水质综合评价模型及其应用[J]，环境污染治理技术与设备，2003年8月，第4卷第8期，23～26
[100] 楼文高．BP神经网络模型在水环境质量综合评价应用中的一些问题[J]，水产学报，第26卷第1期，2002年2月90～96
[101] 杨志英．BP神经网络在水质评价中的应用[J]，中国农村水利水电。2001年第9期，27～29
[102] 唐婉莹，杨宇川，黄刚．BP神经网络用于水体中N综合污染评价[J]，计算机应用化学，第19卷第4期，2002年7月28日。438～440
[103] 虞登梅，江晓益．地下水水质评价的人工神经网络方法[J]，西安科技学院学报，Vol．23 No．1 Mar．2003． 27～29，37
[104] 杨立民，许有鹏．改进遗传神经网络方法在大气环境质量评价中的应用[J]，环境科学研究，Vol．12，No，2，1999，28～31)
[105] 李新春，孙艳，陶学禹．应用神经网络评价矿区可持续发展[J]，中国矿业大学学报，Vol．30 No．4 July．2001 392～395
[106] 谢贤平，赵梓成．矿井通风系统评价的人工神经网络模型
[107] 李嘉庆，张在旭等．炼油企业可持续发展评价模型
[108] 潘大丰，李群．神经网络多指标综合评价方法研究[J]，农业系统科学与综合研究。1999．15(2)：105～107，110
[109] 冯利华．地区综合实力的ANN分析[J]，经济地理，Vol．23，No．1，Jan．，2003：9～11
[110] 周延刚，张笃建．单亲遗传误差反向传播算法及其在县级生态农业综合评价中的应用[J]，西南师范法学学报(自然科学版)，2002年10月，第27卷第5期816～819
[111] 彭荔红，李祚泳，伍开宝．城市环境质量的BP网络综合评价[J]，厦门大学学报(自然科学版)第38卷第5期，1999年9月745～749
[112] 白润才，殷伯良，孙庆宏．BP神经网络模型在城市环境质量评价中的应用[J]，辽宁工程技术大学学报(自然科学版)，第20卷 第3期，2001年6月373～375
[113] 戴文战．基于三层BP网络的多指标综合评估方法及应用[J]，系统工程理论与实践，1999年5月，第5期。29～34，40
[114] 徐英卓．基于神经网络的储层敏感性评价专家系统[J]，计算机应用研究，1997年第1期，52～54
[115] 周学军，刘颖琦．基于人工神经网络BP算法的教育评估专家评价研究[J]．数量经济技术经济研究，2003年第11期：40～44
[116] 张新红．综合评价管理信息系统的在专家神经网络方法[J]，情报理论与实践，第24卷2001年第3期，188～189
[117] 汤洁，林年丰，卞建民，金燕，应用GIS-ANN进行土地盐碱化危险度评价[J]，自然灾害学报，第12卷第4期，2003年11月，34～39
[118] 郭亚军著．综合评价理论与方法(第一版)[M]，北京：科学出版社8～13页，2002年8月
[119] 杨城，余松柏，魏安世．广东省林业空间数据库系统的建设与应用[J]，广东林业科技，2003年第19卷第3期，28～31
[120] 武汉中地信息工程有限公司．地理信息系统开发手册[M]，2000年9月
[121] 周学军，刘颖琦．基于人工神经网络BP算法的教育评估专家评价研究，数量经济技术经济研究，2003年第11期，46～44
[122] 闻新，周露，王丹立，熊晓英编著．MATLAB神经网络应用设计[M]，北京：科学出版社，2000年9月第一版，231～232
[123] TIAN Sheng-feng. Artificial intelligence theory [M]. Beijing: Beijing science and engineering college press, 1993
[124] 顾洁，范春菊．TSP的混合遗传算法——人工神经网络模型电力系统及其自动化学报[J] 第13卷第3期2001年6月：17～19，29
[125] 肖本贤，昂卫兵，王群京．用混合遗传算法实现神经网络快速训练[J]，合肥工业大学学报(自然科学版)，第24卷第5期2001年10月，901～906
[126] 昂卫兵．基于神经网络的轮廓控制[D]，合肥：合肥工业大学电气工程学院，硕士论文，2001
[127] Bjarne Stroustrup.《The C++ programming language (Special Editon)》by Bjarne Stroustrup Addison Wesley 1998
[2] 邢金香，李良厚等．林业在社会经济可持续发展中的作用[J]，河南林业科技，2003年9月第23卷第3期：31～32
[3] 张建国．现代林业论[M]，北京：中国林业出版社，1996：70～74
[4] 李禄康．政策机构和达到可持续发展的手段．第十一届世界林业大会文献选编．北京：中国环境科学出版社，1998：305～310
[5] 韩亚军．综合评价理论与方法[M]．北京：科学出版社．2002年8月第一版：8
[6] 谢金生，徐秋生，曹建华等．区域可持续林业评价指标体系及评价标准的研究[J]，江西农业大学学报，1999年9月，第21卷第3期443～446
[7] 张守功，朱春全，肖文发．森林可持续经营导论[M]，北京：中国林业出版社，2001年7月第一版，8～9
[8] 刘璨．林业持续发展政策设计[J]，世界林业研究，1994，7(5)，11～18
[9] The Santiago Agreement.Criteria and indicators for the conservation and sustainable manegement of temperate and boreal forests[J].J For,1995,93(4): 18～21
[10] 何汉杏，何华春．县级林场可持续林业建设研究[J]．中南林学院学报．第21卷第2期，2001年6月：6～12
[11] 王海，张玉岩．吉林省国有林区可持续发展综合评价指标体系研究[R]．林业经济．2000年第6期：32～36
[12] 郭正刚，程国栋等．甘肃省白龙江林区森林资源可持续发展力的评价[J]．应用生态学报．2003年9月．第14卷第9期：1433～1438
[13] 李宝根，汪正铨．福建省森林资源可持续发展评价指标体系的研究[J]．琳业勘察设计(福建)．2003年第2期：1～5
[14] 蔡为茂．森林持续经营的评价系统[J]．森林工程．1998年9月．第14卷第3期：4～6
[15] 李朝洪，许俊杰，于波涛．中国森林资源可持续发展综合评价方法[J]．东北林业大学学报．第20卷第2期．2002年3月：73～76
[16] 杨学民，姜志林，张慧．徐州市林业可持续发展评价[J]．福建林学院学报．2003，23(2)：177～181
[17] 郭仁鉴，陈法荣，朱铨．淳安县林业可持续发展能力的评价和分析[J]．浙江林学院学报，2001，18(4)：337～344
[18] 张万里，李雷鸿．大兴安岭新林林业局可持续发展能力评价[J]．东北林业大学学报．第28卷第5期．2000年．9月：125～129
[19] 罗明灿．区域森林资源可持续发展综合评价研究[J]．四川林勘设计1999年第2期：25～33
[20] 吴延熊．区域森林资源可持续发展动态评价的理论探讨[J]．北京林业大学学报．第21卷第1期．1999年1月：62～67
[21] 李朝洪，郝爱民．中国森林资源可持续发展描述指标体系框架的构建[J]，东北林业大学学报，第28卷第5期，2000年9月，122～124
[22] 王伟英．论国有林区的可持续发展[J]，世界林业研究，1998年第5期，70～77
[23] 陈炳浩．我国林业持续发展的原则、内容和途径[J]，世界林业研究，1994，7(2)：19～24
[24] 邓守严，卢振兰，李德志．经济生态系统持续发展的实现途径及其测度体系[J]，世界林业研究，1998(5)：52～57
[25] 史忠植．神经计算[M]．电子工业出版社，1993
[26] 沈政，林庶芝．脑模拟与神经计算机[M]．北京大学出版社，1992
[27] Simon Haykin, Neural Networks [M], Beijing: China Machine Press, Second Edition, 2004,1:1～10
[28] H.Lachowski, et al. Integrating remote sensing with GIS.Journal O Forestry, 1992(12): 16～21
[29] 邬伦，刘瑜，张晶，韦中亚，田愿编著．地理信息系统——原理、方法和应用[M]．北京：科学出版社，2002年2月第一版：172
[30] Huang, W. and R. Lippmann 1987. Comparisons between neural net and conventional classifies [J], IEEE First International Conference on Neural Networks, Vol. Ⅳ. San Diego, California, 21-24 June: 485～494
[31] Hepner, G.F. and N. Ritter, 1989. Application of an artificial neural network to land covers classification of
thematic mapper imagery [M] JPL Int. Tech.l Rep.
[32] Hepner, G.F., T. Logan, N. Ritter, and N. Bryant 1990. Artificial neural network classification using a minimal training set: Comparison to conventional supervised classification [M]. Photogrammetric
[33] Civco, D.L. 1993. Artificial neural networks for land cover classification and mapping [M] International Journal of Geographical Information Systems 7: 173～186.
[34] Gong, P. and J. Chen 1996. Mapping ecological land systems and classification uncertainties from digital elevation and forest-cover data using neural network [M]. Photogrammetrie Engineering and Remote Sensing 62:1249-1260
[35] Markham L.S. Tags dale, C.T., combining neural networks and statistical predictions to solve the classification problem in discriminate analysis [J]. Deeis. Sci.26 (2), 229～242
[36] Jock.A.Blackard, Denis J.Dean Comparative accuracies of artificial neural networks and discriminant analysis in predicting forest cover types from cartographic variables [M] Computers and electronics in agriculture 24(1999)131～151
[37] Decatur, S. E. 1989. Application of neural networks to terrain classification[R]. Proceedings of International Joint Conference on Neural Networks 1: 283～288.
[38] Campbell, W.J., S.E. Hill, and R.F. Cromp 1989. Automatic labeling and characterization of objects using artificial neural networks [J]. Telemetric and Informatics 6: 259-271.
[39] MeClelland, G. E., R.N. Dewitt, T.H. Hemmer, L.N. Matheson, and G.O. Moe, 1989. Multispectral Image-processing with a three-layer back-propagation network[R] Proceedings of International Joint Conference on Neural Networks 1: 151～153
[40] Hepner, G.F., T. Logan, N. Ritter, and N. Bryant 1990. Artificial neural network classification using a minimal training set: Comparison to conventional supervised classification.[M] Photogrammetric Engineering and Remote Sensing 56:469～473
[41] Downey, I.D., C.H. Power, I. Kanellopoulos, and G.G. Wilkinson, 1992. A performance comparison of Land sat thematic mapper land cover classification based on neural network techniques and traditional maximum likelihood algorithms and minimum distance algorithms[R]. Proceeding of the Annual Conference of the Remote Sensing Society: 518～528.
[42] Benedicts, J. A., P.H. Swain, and O.K. Esroy 1990. Neural network approaches versus statistical methods in classification of multisource remote sensing data [A]. IEEE Transaction on Geosciences and Remote Sensing 28: 540～552
[43] Peddle, D.R. G.M. Foody, A. Zhang, S.E. Franklin, and E.F. Ledrew 1994. Multisource image classification Ⅱ: an empirical comparison of evidential reasoning, linear diseriminant analysis, and maximum likelihood algorithms for alpine land cover classification [J]. Can. J. Remote Sensing 20:397～408
[44] Gong, P. and J. Chen 1996. Mapping ecological land systems and classification uncertainties from digital elevation and forest-cover data using neural network [M]. Photogrammetric Engineering and Remote Sensing 62: 1249～1260
[45] Ritter, N.D, T.L. Logan, and N.A. Bryant 1988. Integration of neural network technologies with Geographic information systems [J], in: GISSymposium-Intenerating Technology and Geoseiences Applications, Denver, CO,:102～103.
[46] Gong, P. 1994. Integrated analysis of spatial data from multiple sources: An overview. Can. [J]. Remote Sensing 20:349～359
[47] Sui, D.Z., 1994. Recent applications of neural networks for spatial data handling. Can. [J]. Remote Sensing 20: 368～380.
[48] Peuquet, D. J. 1991. An overview of the applications of artificial intelligence approaches for geographic Information Systems[R], In: Proceedings of the Seventh Annual Conference on Interactive Information and Processing Systems for Meteorology Oceanography and Hydrology, New Orleans, LO.
[49] Sui, D.Z, 1993. A neural network-based GIS approach to spatial decision-making [J], The Operational Gcographer 11: 12～20
[50] Wang, F.J. 1992. Incorporating a neural network into GIS for agricultural land suitability analysis [M].
GIS/LIS'922: 804～815.
[51] Zhou, J. and D.L. Civco 1996. Using genetic learning neural networks for spatial decision making in GIS [J].Photogrammetric Engineering and Remote Sensing 11:1287～1295
[52] Deadman, P.J. and H.R. Gimblett, 1997. Applying neural networks to vegetation management plan Development [J]. AI Application 11:107～112.
[53] 庄家礼，陈良富，徐希儒 地表组分温度反演[J]北京大学学报(自然科学版)，第36卷，第6期，2000年11月：850～857
[54] Atkinson, P.M. and A.R. Tatnall 1997. Introduction: Neural networks in remote sensing, Int.[J]. Remote Scnsing 18:699～709
[55] Ryan, T.W., P.J. Sementilli, P. Yuen, and B.R. Hunt 1991. Extractions of shoreline features by neural nets and image processing [M], Photogrammetric Engineering and Remote Sensing 57:947～955
[56] Hermann, P.D. and N. Khazenie 1992. Classification of multispectral remote sensing data using a back propagation neural network [A]. IEEE Transaction on Geoscience and Remote Sensing 30:81～88
[57] Pierce, L.E., D. Sarabandi, and F. T. Ulaby, 1992. Application of artificial neural networks in canopy scattering inversion [A]. IEEE Transaction on Geoscience and Remote Sensing 91:1067～1069
[58] Wilkinson, G.G., I. Kaneilopoulos, C. Kontoes, and J.Megier 1992. A comparison of neural network and expert system methods for analysis of remotely sensed imagery [A]. IEEE Transaction on Geoscience and Remote Sensing 91:62～64
[59] Jan, J.F. 1997. Artificial neural networks for classification of remote sensing data [J], Quart. J. Exp. For. Nat. Taiwan Univ. 11: 79～89
[60] Yoshitomi, K., A. Ishimaru, J. N., Wang and J.S. Chen, 1993. Surface roughness determinations sing spectral correlation of scattered intensities and an artificial neural network technique [A]. IEEE Transaction on Geoscience and Remote Sensing 41:498～502
[61] Tsang, L., Z. Chen, S. Oh, R.J., Marks Ⅱ, and A.T. Chang, 1992. Inversion of snow parameters rum passive microwave remote sensing measurements by a neural network trained with a multiple scattering model[A]. IEEE Transaction on Geoscienee and Remote Sensing 30:1015～1024
[62] Jin, Q.Y. and C. Liu 1997. Biomass retrieval from high dimensional active/passive remote sensing data by using artifieial neural networks. Int. [J]. Remote Sensing 18:971～979
[63] Zhang X., C. Li, and Y. Yuan 1997. Application of neural networks to identifying vegetation types from satellite images [J]. AI Application 11: 99～106
[64] 秦其明，陆荣建．分形与神经网络方法在卫星数字图像分类中的应用[M]．遥感技术2000-11-20 Vol．36No．6．：858～864
[65] Yang, X.B. and W.D. Batehelor 1997. Modeling plant disease dynamics using neural networks [J]. AI Application 11:47～55
[66] Yang, X.B., W.D. Batchelor and A.T. Tschanz 1995. A neural network model to predict soybean us. [J] Psychopathology 75:1172
[67] Batchelor, W.D., X.B. Yang and A.T. Tschanz 1997. Development of a neural network for soybean epidemics[J] Transactions ASAE 40:247～252
[68] Francl, L.J., S. Panigrahi, and T. Pahdi, 1995. Neural network models that predict leaf wemess [M]. Psychopathology 85:1182
[69] Francl, L.J. and S. Panigrahi 1997. Artificial neural network models of wheat leaf wetness [M]. Bicultural and Forest Meteorology 88:57～65
[70] McClendon, R.W. and W.D. Batehelor 1995. Insect pest management neural network [A]. American Society of Agricultural Engineers, St. Joseph, Miehigan, ASAE Paper No. 95,35～60
[71] Cook, D.F. and M.L. Wolfe 1991. A back-propagation neural network to predict average air temperature [J]. AI Applications 5:40～46
[72] Derr, V.E. and R.J. Slutz 1994. Prediction of El Niflo events in the Pacific by means of neural networks [J]. AI Applications 8:51-63
[73] Tangang, F.T., W. W. Hsieh and B. Tang 1997. Forecasting the equatorial pacific temperatures by neural
networrk models [J]. Climate Dynamics 13:135～147
[74] Tangang, F.T., B.Tang, A.H. Monahan, and W. W. Hsieh, 1998. Forecasting ENSO events: A eural network-extended EOF approach [J] Climate 11:29～41
[75] Yi, J. and V.R. Prybutok 1996. A neural network model forecasting for prediction of daily maximum ozone concentration in an industrialized urban area [M]. Environ. Pollut. 84:349～357
[76] Keller, T., 1994. Elaborion d'une base de donn(?)es en dendroclimatologie en vue d'une reconstruction climatique dans les Atpes ET la region Mediterranean[R]. Memories de DEA de l'Universit(?) Axi-Marseiile Ⅲ,:33
[77] Guiot, J., R. Cheddadi, I.C. Prentice and D. Jolly 1996. A method of biome and land surface mapping from pollen data: Application to Europe 6000 years ago [J], Palaeoclimate 1: 311～324.
[78] A.L.M aclean,et ai.Using GIS to estimate forest resource changes.Journal of Forestry, 1992(12):22～26
[79] Levine, E.R. and D. Kimes 1997. Predicting soil carbon in Mollisols using neural networks, In: Soil Processes and the Carbon Cycle [M], R. Lal, J.K. Kimble, and R.F.Follett (eds.), CRC Press, FL,: 608.
[80] Ehrman, J.M., T.A. Clair, and A. Bouchard, 1996. Using neural networks to predict pH changes in acidified eastern Canadian lakes [J]. AI Applications 10: 1～8.
[81] Vega-Garcia, C. B.S. Lee, P.M. Woodard, and S.J. Titus 1996. Applying neural network echnology to human-cauaed wildfire occurrence prediction [J], AI Applications 10: 9-18.
[82] 黎粤华，梁颖红，王述洋，人工神经网络技术在林火重灾年预测中的应用前景[J] 林业劳动安全Vol 14,Nol Feb．2001：28～30．
[83] 吴龙标，张本矿，连加锐基于遗传算法的前馈神经网络火灾探测[J]Fire Safety Science Volume 7，Issue 2 (June 1998)
[84] Merobian, E. And Skrzypek, J.A general-purpose simulation for neural models [J]. Simulation, 1992, VOL.59, NO.5
[85] B.T.Guaan and G.Gertner. Using a parallel Distributed Processing System to Model Individual Tree Mortality [J]. For Sci, 1991, 37 (3)
[86] G.Gertner and B.T.Guan, Conceptal Classification: An AI Alternative to Statistical Problems for Classification Problem [J]. For Sci, 1992, 39(3)
[87] 李际平．BP模型在单木树高、胸径生长模拟中的应用[J]．中南林学院学报，1996，6(2)
[88] 李际平．林业专家模拟系统研究[J]．林业资源管理，1996，(特刊)：37～39
[89] 李际平．关于林业决策支持系统的设计思想[J]．决策与决策支持系统，1994，4(1)
[90] 李际平．林业决策支持系统设计模式探讨[J]．中南林学院学报，1991，11(2)
[91] 洪伟，吴承祯．闽东南土壤流失人工神经网络预报研究[J]．土壤侵蚀与水土保持学报，1997，3(3)：52～57
[92] 洪伟，吴承祯，何东进．基于人工神经网络的森林资源管理模型的研究[J]自然资源学报，1998，13(1)：69～72
[93] 何东进，洪伟，吴承祯．人工神经网络用于杉木壮苗定向培育规律的研究[J]．浙江林学院学报，1997，14(4)：339～343
[94] 李际平，邓立斌，何建华．基于人工神经网络的森林资源预测研究[J]中南林学院学报Vol．21 No．4Dec．2001
[95] Maier, H.R. and G. C. Dandy 1996. The use of artificial neural networks for the predition of water quality parameters [J]. Water Resources Research 32: 1013～1022.
[96] Tamari, S., W(?)sten, and J.C. Ruiz-Su(?)Rez, 1996. Testing an artificial neural network for predicting soil hydraulic conductivity [J]. Soil Sci. Am. 60: 1732～1741.
[97] Levine, E.R. and D. Kimes 1997. Predicting soil carbon in Mollisols using neural networks, In: Soil Processes and the Carbon Cycle [M], R. Lal, J.K. Kimble, and R.F.Follett (eds.), CRC Press, FL,: 608.
[98] Ehrman, J.M., T.A. Clair, and A. Bouchard, 1996. Using neural networks to predict pH changes in acidified eastern Canadian lakes [J]. AI Applications 10: 1～8.
[99] 楼文高，王延政．基于BP网络的水质综合评价模型及其应用[J]，环境污染治理技术与设备，2003年8月，第4卷第8期，23～26
[100] 楼文高．BP神经网络模型在水环境质量综合评价应用中的一些问题[J]，水产学报，第26卷第1期，2002年2月90～96
[101] 杨志英．BP神经网络在水质评价中的应用[J]，中国农村水利水电。2001年第9期，27～29
[102] 唐婉莹，杨宇川，黄刚．BP神经网络用于水体中N综合污染评价[J]，计算机应用化学，第19卷第4期，2002年7月28日。438～440
[103] 虞登梅，江晓益．地下水水质评价的人工神经网络方法[J]，西安科技学院学报，Vol．23 No．1 Mar．2003． 27～29，37
[104] 杨立民，许有鹏．改进遗传神经网络方法在大气环境质量评价中的应用[J]，环境科学研究，Vol．12，No，2，1999，28～31)
[105] 李新春，孙艳，陶学禹．应用神经网络评价矿区可持续发展[J]，中国矿业大学学报，Vol．30 No．4 July．2001 392～395
[106] 谢贤平，赵梓成．矿井通风系统评价的人工神经网络模型
[107] 李嘉庆，张在旭等．炼油企业可持续发展评价模型
[108] 潘大丰，李群．神经网络多指标综合评价方法研究[J]，农业系统科学与综合研究。1999．15(2)：105～107，110
[109] 冯利华．地区综合实力的ANN分析[J]，经济地理，Vol．23，No．1，Jan．，2003：9～11
[110] 周延刚，张笃建．单亲遗传误差反向传播算法及其在县级生态农业综合评价中的应用[J]，西南师范法学学报(自然科学版)，2002年10月，第27卷第5期816～819
[111] 彭荔红，李祚泳，伍开宝．城市环境质量的BP网络综合评价[J]，厦门大学学报(自然科学版)第38卷第5期，1999年9月745～749
[112] 白润才，殷伯良，孙庆宏．BP神经网络模型在城市环境质量评价中的应用[J]，辽宁工程技术大学学报(自然科学版)，第20卷 第3期，2001年6月373～375
[113] 戴文战．基于三层BP网络的多指标综合评估方法及应用[J]，系统工程理论与实践，1999年5月，第5期。29～34，40
[114] 徐英卓．基于神经网络的储层敏感性评价专家系统[J]，计算机应用研究，1997年第1期，52～54
[115] 周学军，刘颖琦．基于人工神经网络BP算法的教育评估专家评价研究[J]．数量经济技术经济研究，2003年第11期：40～44
[116] 张新红．综合评价管理信息系统的在专家神经网络方法[J]，情报理论与实践，第24卷2001年第3期，188～189
[117] 汤洁，林年丰，卞建民，金燕，应用GIS-ANN进行土地盐碱化危险度评价[J]，自然灾害学报，第12卷第4期，2003年11月，34～39
[118] 郭亚军著．综合评价理论与方法(第一版)[M]，北京：科学出版社8～13页，2002年8月
[119] 杨城，余松柏，魏安世．广东省林业空间数据库系统的建设与应用[J]，广东林业科技，2003年第19卷第3期，28～31
[120] 武汉中地信息工程有限公司．地理信息系统开发手册[M]，2000年9月
[121] 周学军，刘颖琦．基于人工神经网络BP算法的教育评估专家评价研究，数量经济技术经济研究，2003年第11期，46～44
[122] 闻新，周露，王丹立，熊晓英编著．MATLAB神经网络应用设计[M]，北京：科学出版社，2000年9月第一版，231～232
[123] TIAN Sheng-feng. Artificial intelligence theory [M]. Beijing: Beijing science and engineering college press, 1993
[124] 顾洁，范春菊．TSP的混合遗传算法——人工神经网络模型电力系统及其自动化学报[J] 第13卷第3期2001年6月：17～19，29
[125] 肖本贤，昂卫兵，王群京．用混合遗传算法实现神经网络快速训练[J]，合肥工业大学学报(自然科学版)，第24卷第5期2001年10月，901～906
[126] 昂卫兵．基于神经网络的轮廓控制[D]，合肥：合肥工业大学电气工程学院，硕士论文，2001
[127] Bjarne Stroustrup.《The C++ programming language (Special Editon)》by Bjarne Stroustrup Addison Wesley 1998