城市土地集约利用潜力评价研究
|
摘要
城市土地集约利用是指在城市规划、土地利用总体规划及相关法规的指导下,充分挖掘城市土地的利用潜力,实现城市和国民经济的可持续性发展。城市土地集约利用是当前建设节约型社会的需要,是缓解城市土地供需矛盾的重要课题。
合理、有效地利用城市土地,需要对其潜力进行评价,以方便相关部门进行决策,达到城市土地集约利用的目的。因此,潜力评价方法的研究以及潜力评价系统的研发成为当务之急。
本课题以城市土地集约利用潜力评价为研究对象,确定城市土地集约利用潜力评价方法和指标体系。并针对当前潜力评价中存在的问题和不足,研究城市功能区自动划分和现状与规划差异分析关键技术。在地理信息系统基本理论和空间数据挖掘技术的基础上,设计并实现了城市土地集约利用潜力评价系统。具体工作如下:
分析和研究其它试点城市土地集约利用潜力评价的研究成果,确定城市土地集约利用潜力评价方法及指标体系,为潜力评价提供了依据;
在功能区评价方法研究中,提出并研究基于自组织神经网络的功能区自动划分算法,有效地解决了传统手工划分的缺点;
通过对空间数据库的分析,确定了土地利用现状与规划的差异性要素,实现了土地利用现状与规划的差异性分析,为城市土地集约利用发展提供可比的数据;
设计并开发“城市土地集约利用潜力评价系统”,并对成都市的城市土地利用现状进行评价,获得了良好的效果,从而为不同城市的土地集约利用潜力评价提供了帮助。
城市土地集约利用潜力评价系统是基于.NET和GeoMedia组件技术进行的设计和开发,具有实用性好、开放性强等特点,并为城市土地集约利用潜力评价项目的研究提供技术支持和决策支持。城市土地集约利用潜力评价成果的应用,对于推动城市存量土地潜力挖掘、提高城市土地供应和用地管理水平,起到了至关重要的作用。
Under the guidance of urban planning and overall plan of land utilization and relevant regulations, Intensive Utilization of Urban Land (IUUL) is how to mine the potention of the urban land and implement the continuable development of the city and the country economy, which is also quite necessary to currently build the economical society and relieve the imbalance between supply and demand of the urban land.
To use the urban land reasonably and effectively, it is necessary to evaluate the potention of the urban land, which is convenient for the government to make decisions.And finally, the aim of intensive utilization of the urban land will be achieved. Therefore, it is quite urgent to research on the methods of potention evaluation and develop the potention evaluation system.
Potential Evaluation of Intensive Utilization of Urban Land (PEIUUL) is consideres as research object, and the methods and index system of PEIUUL is confirmed.To deal with the problems and the shortages of PEIUUL, this paper makes a research on the key technology of the auto-partition method of urban function regiones and the difference analysis between the parcel and the plan.Based on the theory of Geographic Information System (GIS) and the technology of Spatial Data Mining (SDM), the PEIUUL system is designed and implemented.The research work is as follows:
According to the analysis and research on the results of PEIUUL of the other experimental cities, this paper confirms the methods and index system of PEIUUL, which provides the basis for PEIUUL project.
During the reseach on the evaluation of the function region, the auto-partition algorithm is put forward, which is based on the reseach of the self-organization feature map. This method effectively solves the disadvantages of function region partition by hand.
According to the analysis of spatial database, this paper confirms the difference-analysis elements of the urban land utilization between the parcel and the plan, and implements the difference anylysis, which provides the comparable data for the development of the IUUL.
Design and develope the PEIUUL system.This paper makes an experiment on the parcel land of Chengdu, and ends with a good result, which is quite helpful for other cities to do the research on PEIUUL.
Based on .NET and the COM technology of GeoMedia, the PEIUUL system is designed and developed with the characteristics of good practicability and strong openness, and provides the PEIUUL project with both technological and decision-making supports. The application of the results will promote to evaluate the potential of the remnant urban land, and improve the ability to supply and manage the urban land.
合理、有效地利用城市土地,需要对其潜力进行评价,以方便相关部门进行决策,达到城市土地集约利用的目的。因此,潜力评价方法的研究以及潜力评价系统的研发成为当务之急。
本课题以城市土地集约利用潜力评价为研究对象,确定城市土地集约利用潜力评价方法和指标体系。并针对当前潜力评价中存在的问题和不足,研究城市功能区自动划分和现状与规划差异分析关键技术。在地理信息系统基本理论和空间数据挖掘技术的基础上,设计并实现了城市土地集约利用潜力评价系统。具体工作如下:
分析和研究其它试点城市土地集约利用潜力评价的研究成果,确定城市土地集约利用潜力评价方法及指标体系,为潜力评价提供了依据;
在功能区评价方法研究中,提出并研究基于自组织神经网络的功能区自动划分算法,有效地解决了传统手工划分的缺点;
通过对空间数据库的分析,确定了土地利用现状与规划的差异性要素,实现了土地利用现状与规划的差异性分析,为城市土地集约利用发展提供可比的数据;
设计并开发“城市土地集约利用潜力评价系统”,并对成都市的城市土地利用现状进行评价,获得了良好的效果,从而为不同城市的土地集约利用潜力评价提供了帮助。
城市土地集约利用潜力评价系统是基于.NET和GeoMedia组件技术进行的设计和开发,具有实用性好、开放性强等特点,并为城市土地集约利用潜力评价项目的研究提供技术支持和决策支持。城市土地集约利用潜力评价成果的应用,对于推动城市存量土地潜力挖掘、提高城市土地供应和用地管理水平,起到了至关重要的作用。
Under the guidance of urban planning and overall plan of land utilization and relevant regulations, Intensive Utilization of Urban Land (IUUL) is how to mine the potention of the urban land and implement the continuable development of the city and the country economy, which is also quite necessary to currently build the economical society and relieve the imbalance between supply and demand of the urban land.
To use the urban land reasonably and effectively, it is necessary to evaluate the potention of the urban land, which is convenient for the government to make decisions.And finally, the aim of intensive utilization of the urban land will be achieved. Therefore, it is quite urgent to research on the methods of potention evaluation and develop the potention evaluation system.
Potential Evaluation of Intensive Utilization of Urban Land (PEIUUL) is consideres as research object, and the methods and index system of PEIUUL is confirmed.To deal with the problems and the shortages of PEIUUL, this paper makes a research on the key technology of the auto-partition method of urban function regiones and the difference analysis between the parcel and the plan.Based on the theory of Geographic Information System (GIS) and the technology of Spatial Data Mining (SDM), the PEIUUL system is designed and implemented.The research work is as follows:
According to the analysis and research on the results of PEIUUL of the other experimental cities, this paper confirms the methods and index system of PEIUUL, which provides the basis for PEIUUL project.
During the reseach on the evaluation of the function region, the auto-partition algorithm is put forward, which is based on the reseach of the self-organization feature map. This method effectively solves the disadvantages of function region partition by hand.
According to the analysis of spatial database, this paper confirms the difference-analysis elements of the urban land utilization between the parcel and the plan, and implements the difference anylysis, which provides the comparable data for the development of the IUUL.
Design and develope the PEIUUL system.This paper makes an experiment on the parcel land of Chengdu, and ends with a good result, which is quite helpful for other cities to do the research on PEIUUL.
Based on .NET and the COM technology of GeoMedia, the PEIUUL system is designed and developed with the characteristics of good practicability and strong openness, and provides the PEIUUL project with both technological and decision-making supports. The application of the results will promote to evaluate the potential of the remnant urban land, and improve the ability to supply and manage the urban land.
引文
[1]孙在宏,乔伟峰.GIS辅助下的城市土地集约利用潜力评价方法研究——以江苏省苏州市为例[J].国土资源科技管理,2004,(1).
[2]倪绍祥.土地类型与土地评价概论 第二版[M].北京:高等教育出版社,1999:135-145.
[3]张晏.2006年度城市土地集约利用潜力评价项目启动[N].中国国土资源报,2006-10-12.
[4]张静.城市土地集约利用潜力评价研究的问题与建议[J].保定师范专科学校学报,2007,20(2):42-43.
[5]汪波,郑家响,樊丰.我国大城市土地集约利用评价研究[J].北京科技大学学报(社会科学报),2006,22(1).
[6]彭建,王仰麟,刘松.海岸带土地持续利用景观生态评价[J].地理学报,2003,58(3).
[7]郑新奇.城市土地优化配置与集约利用评价——理论 方法 技术 实证[M].北京:科学出版社,2004.
[8]李新运.城市空间数据挖掘方法与应用[M].济南:山东大学出版社,2005:67-70.
[9]国土资源部土地利用管理司.城市土地集约利用潜力评价技术规程(试行).中国土地勘测规划院,2006.
[10]国土资源部土地利用管理司.成都市城市土地集约利用潜力评价实施方案,2006.
[11]张波.济南市城区土地集约利用潜力评价[D].山东:山东师范大学.2002.
[12]周勇,聂艳.土地信息系统——理论 方法 实践[M].北京:化学工业出版社,2005.
[13]郭爱请,葛京凤.河北省城市土地集约利用潜力评价方法探讨[J].资源科学,2006,28(4).
[14]何芳,吴正训.国内外城市土地集约利用研究综述与分析[J].国土经济2002,(3):35-37.
[15]于金羽,沈士芹,王淑娟.开发区土地资源集约利用——以江苏省为例[J].国土资源科技管理,2006,23(4).
[16]章其祥,孙在宏,沈剑荣,冯雪渔,范宇,张侠.城市土地集约利用潜力评价——以南京市为例[J].南京师范大学(自然科学版),2004,27(3):101-105.
[17]黎一畅,周寅康.江苏省城市土地集约利用空间差异的主成分研究[J].湖南工程学院学报(社会科学版),2006,16(2).
[18]钱紫华,毛蒋兴.1990年代以来我国城市土地集约利用研究述评[J].中山大学研究生学刊(自然科学版、医学版),2005,26(1).
[19]李霞,刘秀华.重庆市都市区城镇土地集约利用现状评价与分析[J].西南农业大学学报,2005,(4).
[20]郭爱请,葛京凤,于江海.河北省城市土地集约利用潜力研究[J].安徽农业科学,2005,33(12).
[21]郭爱请,葛京凤.河北省城市土地集约利用潜力评价方法探讨[J].资源科学,2006,28(4).
[22]陈成,吴群,王楠君.开发区土地集约利用研究——以徐州市开发区为例.国土资源科技管理[J],2005.22(4).
[23]过仲阳,陆衍,戴晓燕.空间数据挖掘系统及其应用[J].上海地质,2004,(4).
[24]李春梅,范全润.空间数据挖掘及其在地理信息系统中的应用[J].楚雄师范学院学报,2005,(3).
[25]毛克彪,覃志豪,李昕,李海涛.空间数据挖掘与GIS集成及应用研究[J].测绘与空间地理信息,2004,(1).
[26]田庆久,毛克彪.空间数据挖掘技术方法及应用[J].遥感技术与应用,2002,(4).
[27]Xavier Lopez.Oracle Locator和Oracle Spatial:商务白皮书[EB/OL].http://www.oracle.com,2003-12:5-10.
[28]Intergraph Corporation.GeoMedia Professional Object Reference[EB/CD],2006.
[29]Xavier Lopez,Jean Ihm,Jim Farley.Oracle Spatial选件和Oracle Locator:Oracle 数据库10g中的位置特性[EB/OL].http://www.oracle.com,2003-12:6-7.
[30]Daniel Geringer.Oracle Spatial最佳实践Oracle技术白皮书[EB/OL].http://www.oracle.com,2003-12.
[31]Kohonen T.Self-Organizing Maps[M].Spring:Berlin.1997.
[32] Shi Yufeng, Wang Yang. Study On Urban Function Partition Based On Self-organizing Neural Network[J]. Computer Engineering, 2006, 9.
[33] Hasi Bagan, Ma Jianwen, Li Qiqing. Study on aster data classification using Self-Organizing Neural Network method[J]. Advance in Earth Sciences, 2003, 18(3).
[34] Xu Xinzheng, Zeng Wenhua. Digital Pattern Recognition Based on Self-organizing Feature Map Neural Network [J]. Journal of Xiamen University(Natural Science), 2005, 41(3).
[35] Liqun Han. Initial weight selection methods for self-organizing training[J]. IEEE International Conference on Intelligent Processing Systems, 1997, 10.
[36] Hahn-Ming Lee, Member, IEEE, Chih-Ming Chen, Yung-Feng Lu.A Self-Organizing HCMAC Neural-Network Classifier[J]. IEEE Transactions on Neural Networks,2003, 14(1).
[37] John A. Flanagan. Neuron Weight Dynamics in the SOM and Self-Organized Criticality[J]. IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000, 5.
[38] Shaimaa Y. Lazem, Walaa M. Sheta. Automatic Landmark identification in Large Virtual Environment:A Spatial Data Mining Approach[J]. IEEE International Conference on Information Visualisation, 2005, 25.
[39] Guojian Cheng, Tianshi Liu, Kuisheng Wang, Jiaxin Han.Soft Competitive Learning and Growing Self-Organizing Neural Networks for Pattern Classification[J]. IEEE International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, 2006,9.
[40] Sirkka-Liisa Joutsiniemi, Samuel Kaski, T. Andreo Larsen. Self-Organizing Map in Recognition of Topographic Patterns of EEG Spectra[J]. IEEE Transactions on Biomediacal Engineering, 1995, 42(11).
[41] William H. Hsu, Loretta S. Auvil, William M. Pottenger, David Tcheng, Michael Welge. Self-Organizing Systems for Knowledge Discovery in Large Databases[J].IEEE International Conference on Neural Networks,1999,4.
[42]Songiil Albayrak.A comparison of 1-D and 2-D Self-organizing Feature Map Algorithm on Color Image Quantization[J].IEEE International Conference on Neural Information Processing,2002,3.
[43]Chihli Hung,Stefan Wermeter.A Dynamic Adaptive Self-Organising Hybrid Model for Text Clustering[J].IEEE International Conference on Data Mining,2003,11.
[44]Takafumi Sasakawa,Jinglu Hu,Kotaro Hirasawa.Self-organized Function Localization Neural Network[J].IEEE International Joint Conference on Digital Object Identifier,2004,2.
[45]Dan Geringer.Oracle的空间技术:Oracle Locator,Oracle Spatial,OracleASMapViewer[EB/OL].Http://otn.oracle.com/produc ts/spatial,2005.
[46]Annalisa Appice,Antonietta Lanza,Donato Malerba.An Integrated Platform for Spatial Data Mining within a GIS Environment[J].IEEE 23~(rd)International Conference on Data Enqineering Workshop,2007.
[47]曾宪珪,廖超.SDM与GIS的集成模式探讨[J].上海地质,2005(2).
[48]倪步喜,章丽芙,姚敏.基于SOFM网络的聚类分析[J].计算机工程与设计,2006,27(5).
[49]王虹,时文.基于SOFM的聚类分析在数据挖掘中的应用研究[J].交通与计算机,2005,23(3).
[50]李大辉,王永红.基于神经网络模型的聚类分析技术研究[J].高师理科学刊,2007,27(2).
[51]赵闯,刘凯,李电生.SOFM神经网络在物流中心城市分类评价中的应用[J].中国公路学报,2004,17(4).
[52]许世刚,章跃.SOFM神经网络的聚类问题研究[J].淮阴工学院学报,2001,10(2).
[53]严会超,杨海东,肖莉,胡月明,陈飞香,王璐,杨培岭,吴文良.模糊SOFM-GIS空间聚类模型在农用地分等中的应用[J].农业工程学报,2006,22(6).
[54]李新运,郑新奇,闫弘文.坐标与属性一体化的空间聚类方法研究[J]. 地理与地理信息科学,2004,20(2).
[55]郑新奇,王筱明,王爱萍,张波.城市宗地集约利用潜力评价方法研究—以济南市城区为例[J].资源科学,2005,27(6).
[56]库向阳,彭文祥,薛惠锋,李继军.基于GIS的空间聚类算法研究[J].计算机工程与应用,2005,29.
[57]崔阳,王华.城市地下管网GIS中的空间数据挖掘模型设计[J].计算机工程与设计,20006,27,(17).
[58]贾泽露,张彤.基于GIS与SDM技术的可视化空间数据分类研究[J].测绘科学,2007,32(1).
[59]吴为英.基于GIS的空间数据挖掘技术[J].山东科技大学学报(自然科学报),2004,23(3).
[60]骆阳,洪波.如何使用GeoMedia组件(控件)开发GIS地理信息系统[J].计算机时代,2002,(5).
[61]Bashir Magomedov.Self-Organizing Feature Maps[EB/OL].Http://www.codeproject.com/KB/recipes/sofm.aspx.2006-11.
[2]倪绍祥.土地类型与土地评价概论 第二版[M].北京:高等教育出版社,1999:135-145.
[3]张晏.2006年度城市土地集约利用潜力评价项目启动[N].中国国土资源报,2006-10-12.
[4]张静.城市土地集约利用潜力评价研究的问题与建议[J].保定师范专科学校学报,2007,20(2):42-43.
[5]汪波,郑家响,樊丰.我国大城市土地集约利用评价研究[J].北京科技大学学报(社会科学报),2006,22(1).
[6]彭建,王仰麟,刘松.海岸带土地持续利用景观生态评价[J].地理学报,2003,58(3).
[7]郑新奇.城市土地优化配置与集约利用评价——理论 方法 技术 实证[M].北京:科学出版社,2004.
[8]李新运.城市空间数据挖掘方法与应用[M].济南:山东大学出版社,2005:67-70.
[9]国土资源部土地利用管理司.城市土地集约利用潜力评价技术规程(试行).中国土地勘测规划院,2006.
[10]国土资源部土地利用管理司.成都市城市土地集约利用潜力评价实施方案,2006.
[11]张波.济南市城区土地集约利用潜力评价[D].山东:山东师范大学.2002.
[12]周勇,聂艳.土地信息系统——理论 方法 实践[M].北京:化学工业出版社,2005.
[13]郭爱请,葛京凤.河北省城市土地集约利用潜力评价方法探讨[J].资源科学,2006,28(4).
[14]何芳,吴正训.国内外城市土地集约利用研究综述与分析[J].国土经济2002,(3):35-37.
[15]于金羽,沈士芹,王淑娟.开发区土地资源集约利用——以江苏省为例[J].国土资源科技管理,2006,23(4).
[16]章其祥,孙在宏,沈剑荣,冯雪渔,范宇,张侠.城市土地集约利用潜力评价——以南京市为例[J].南京师范大学(自然科学版),2004,27(3):101-105.
[17]黎一畅,周寅康.江苏省城市土地集约利用空间差异的主成分研究[J].湖南工程学院学报(社会科学版),2006,16(2).
[18]钱紫华,毛蒋兴.1990年代以来我国城市土地集约利用研究述评[J].中山大学研究生学刊(自然科学版、医学版),2005,26(1).
[19]李霞,刘秀华.重庆市都市区城镇土地集约利用现状评价与分析[J].西南农业大学学报,2005,(4).
[20]郭爱请,葛京凤,于江海.河北省城市土地集约利用潜力研究[J].安徽农业科学,2005,33(12).
[21]郭爱请,葛京凤.河北省城市土地集约利用潜力评价方法探讨[J].资源科学,2006,28(4).
[22]陈成,吴群,王楠君.开发区土地集约利用研究——以徐州市开发区为例.国土资源科技管理[J],2005.22(4).
[23]过仲阳,陆衍,戴晓燕.空间数据挖掘系统及其应用[J].上海地质,2004,(4).
[24]李春梅,范全润.空间数据挖掘及其在地理信息系统中的应用[J].楚雄师范学院学报,2005,(3).
[25]毛克彪,覃志豪,李昕,李海涛.空间数据挖掘与GIS集成及应用研究[J].测绘与空间地理信息,2004,(1).
[26]田庆久,毛克彪.空间数据挖掘技术方法及应用[J].遥感技术与应用,2002,(4).
[27]Xavier Lopez.Oracle Locator和Oracle Spatial:商务白皮书[EB/OL].http://www.oracle.com,2003-12:5-10.
[28]Intergraph Corporation.GeoMedia Professional Object Reference[EB/CD],2006.
[29]Xavier Lopez,Jean Ihm,Jim Farley.Oracle Spatial选件和Oracle Locator:Oracle 数据库10g中的位置特性[EB/OL].http://www.oracle.com,2003-12:6-7.
[30]Daniel Geringer.Oracle Spatial最佳实践Oracle技术白皮书[EB/OL].http://www.oracle.com,2003-12.
[31]Kohonen T.Self-Organizing Maps[M].Spring:Berlin.1997.
[32] Shi Yufeng, Wang Yang. Study On Urban Function Partition Based On Self-organizing Neural Network[J]. Computer Engineering, 2006, 9.
[33] Hasi Bagan, Ma Jianwen, Li Qiqing. Study on aster data classification using Self-Organizing Neural Network method[J]. Advance in Earth Sciences, 2003, 18(3).
[34] Xu Xinzheng, Zeng Wenhua. Digital Pattern Recognition Based on Self-organizing Feature Map Neural Network [J]. Journal of Xiamen University(Natural Science), 2005, 41(3).
[35] Liqun Han. Initial weight selection methods for self-organizing training[J]. IEEE International Conference on Intelligent Processing Systems, 1997, 10.
[36] Hahn-Ming Lee, Member, IEEE, Chih-Ming Chen, Yung-Feng Lu.A Self-Organizing HCMAC Neural-Network Classifier[J]. IEEE Transactions on Neural Networks,2003, 14(1).
[37] John A. Flanagan. Neuron Weight Dynamics in the SOM and Self-Organized Criticality[J]. IEEE-INNS-ENNS International Joint Conference on Neural Networks, 2000, 5.
[38] Shaimaa Y. Lazem, Walaa M. Sheta. Automatic Landmark identification in Large Virtual Environment:A Spatial Data Mining Approach[J]. IEEE International Conference on Information Visualisation, 2005, 25.
[39] Guojian Cheng, Tianshi Liu, Kuisheng Wang, Jiaxin Han.Soft Competitive Learning and Growing Self-Organizing Neural Networks for Pattern Classification[J]. IEEE International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, 2006,9.
[40] Sirkka-Liisa Joutsiniemi, Samuel Kaski, T. Andreo Larsen. Self-Organizing Map in Recognition of Topographic Patterns of EEG Spectra[J]. IEEE Transactions on Biomediacal Engineering, 1995, 42(11).
[41] William H. Hsu, Loretta S. Auvil, William M. Pottenger, David Tcheng, Michael Welge. Self-Organizing Systems for Knowledge Discovery in Large Databases[J].IEEE International Conference on Neural Networks,1999,4.
[42]Songiil Albayrak.A comparison of 1-D and 2-D Self-organizing Feature Map Algorithm on Color Image Quantization[J].IEEE International Conference on Neural Information Processing,2002,3.
[43]Chihli Hung,Stefan Wermeter.A Dynamic Adaptive Self-Organising Hybrid Model for Text Clustering[J].IEEE International Conference on Data Mining,2003,11.
[44]Takafumi Sasakawa,Jinglu Hu,Kotaro Hirasawa.Self-organized Function Localization Neural Network[J].IEEE International Joint Conference on Digital Object Identifier,2004,2.
[45]Dan Geringer.Oracle的空间技术:Oracle Locator,Oracle Spatial,OracleASMapViewer[EB/OL].Http://otn.oracle.com/produc ts/spatial,2005.
[46]Annalisa Appice,Antonietta Lanza,Donato Malerba.An Integrated Platform for Spatial Data Mining within a GIS Environment[J].IEEE 23~(rd)International Conference on Data Enqineering Workshop,2007.
[47]曾宪珪,廖超.SDM与GIS的集成模式探讨[J].上海地质,2005(2).
[48]倪步喜,章丽芙,姚敏.基于SOFM网络的聚类分析[J].计算机工程与设计,2006,27(5).
[49]王虹,时文.基于SOFM的聚类分析在数据挖掘中的应用研究[J].交通与计算机,2005,23(3).
[50]李大辉,王永红.基于神经网络模型的聚类分析技术研究[J].高师理科学刊,2007,27(2).
[51]赵闯,刘凯,李电生.SOFM神经网络在物流中心城市分类评价中的应用[J].中国公路学报,2004,17(4).
[52]许世刚,章跃.SOFM神经网络的聚类问题研究[J].淮阴工学院学报,2001,10(2).
[53]严会超,杨海东,肖莉,胡月明,陈飞香,王璐,杨培岭,吴文良.模糊SOFM-GIS空间聚类模型在农用地分等中的应用[J].农业工程学报,2006,22(6).
[54]李新运,郑新奇,闫弘文.坐标与属性一体化的空间聚类方法研究[J]. 地理与地理信息科学,2004,20(2).
[55]郑新奇,王筱明,王爱萍,张波.城市宗地集约利用潜力评价方法研究—以济南市城区为例[J].资源科学,2005,27(6).
[56]库向阳,彭文祥,薛惠锋,李继军.基于GIS的空间聚类算法研究[J].计算机工程与应用,2005,29.
[57]崔阳,王华.城市地下管网GIS中的空间数据挖掘模型设计[J].计算机工程与设计,20006,27,(17).
[58]贾泽露,张彤.基于GIS与SDM技术的可视化空间数据分类研究[J].测绘科学,2007,32(1).
[59]吴为英.基于GIS的空间数据挖掘技术[J].山东科技大学学报(自然科学报),2004,23(3).
[60]骆阳,洪波.如何使用GeoMedia组件(控件)开发GIS地理信息系统[J].计算机时代,2002,(5).
[61]Bashir Magomedov.Self-Organizing Feature Maps[EB/OL].Http://www.codeproject.com/KB/recipes/sofm.aspx.2006-11.