基于分形理论和Kohonen网络的城镇体系的非线性研究——以长江三角洲地区为例

doi:10.11867/j.issn.1001-8166.2003.04.0521

地球科学进展 ›› 2003, Vol. 18 ›› Issue (4): 521 -526. doi: 10.11867/j.issn.1001-8166.2003.04.0521

凌怡莹,徐建华

华东师范大学资源与环境科学学院地理学系，上海 200062

收稿日期:2002-09-29 修回日期:2003-04-01 出版日期:2003-12-20
通讯作者: 凌怡莹 E-mail:lingyiying＠sohu.com
基金资助:
国家自然科学基金项目“基于地学信息图谱的城市景观镶嵌结构分形模型研究”（编号：40171069）；上海市教委学术发展基金项目“城市可持续发展的人地关系协调计算模型研究———以上海市为例”（编号：00JG05040）资助.

A NONLINEAR STUDY ON THE URBAN SYSTEM IN YANGTZE DELTA BASED ON THE FRACTAL THEORY AND THE KONHONEN NET

Ling Yiying,Xu Jianhua

Department of Geography，East China Normal University，Shanghai 200062，China

Received:2002-09-29 Revised:2003-04-01 Online:2003-12-20 Published:2003-08-01

下载PDF ( 1196 )

结合长江三角洲地区，探讨分形理论、人工神经网络（Kohonen网络）在城镇体系研究中的应用问题：运用分形理论，计算长江三角洲地区城镇体系规模结构分形分布的分维数和城镇体系空间结构的关联维数，并分析其规模结构和空间结构的分形结构特征；运用Kohonen神经网络模型，对长江三角洲地区的城市进行城市职能分类，分析其职能结构；提出长江三角洲地区城镇体系的发展对策，同时分别评述分形理论和Kohonen网络方法在城镇体系研究中存在的优势与不足，并提出其改进方法。

关键词: 分形, Kohonen网络, 城镇体系, 城市职能分类, 长江三角洲地区

    The paper presents two non-linear methods, namely the fractal and the Konhonen net, used in the study of the urban system in Yangtze delta. Primacy index and the distribution curve of city scale in Yangtze delta are measured. Furthermore, the dimension of the scale structure is worked out to reveal the scale distribution in Yangtze delta. Then, spatial correlation dimension of the town-size distribution in Yangtze delta is also measured to analyses the spatial structure of urban system . In addition, based on the Kohonen net, using the data of the urban work force structure, all cities in Yangtze delta are classified into 5 groups in terms of the comprehensive urban function.
    According all above analyses it points out three character and deficiencies of the urban system in Yangtze delta, such as：（1）The scale distributing in Yangtze delta is mainly distributed with city-size distributing, partly possessing the characteristics of the first placed distribution；（2）The traffic networks in Yangtze delta does not coordinate with the urban system very much, and the capacity of spatial interaction is a little infirm；（3）Most cities are all-around cities, and the travel function is extremely outstanding in over half cities. But a few middle-small cities lack the special urban function.
    Some advice on developing the urban system of Yangtze delta is proposed based on the studying result：The integration of regional should be realized to form regional integration advantage, leading the whole economic development in delta. Such as：（1）Accelerate the step of the internationalization of Shanghai, develop the economy of big-cities, and the integration construction of the three core cities should be further promoted；（2）Perfect the traffic networks and communication networks to strengthen the relation among cities；（3）Realize the effective arrange of the urban function in Yangtze delta；（4）Develop the industry of travel and accelerate the intercity collaboration to build a big tourism circle. At last, the fractal theory was affirmed and the strongpoint of the Kohonen net was presented, namely its unsupervised learning. On the other hand, the improvement method is also put forward.

Key words: Fractal, Kohonen net, Urban system, Urban function classification, Yangtze delta．

中图分类号:

K928.5

[1] Mandelbrot B B. The Fractal Geometry of Nature[M]. New York: W H Freeman＆Company,1977.

[2] Kohonen T. Self-Organization and Associative Memory[M]．Berlin:Springer,1984.

[3] Kohonen T. Self-Organizing Maps(2nd)[M]. Berlin:Springer,1997.

[4] Gu Chaolin, Zhang Min. Study on the characteristics and dynamics of Yangtze delta megalopolis[J]. Advances in Earth Science,2001,16(3):332-338.[顾朝林,张敏.长江三角洲都市连绵区性状特征与形成机制研究[J].地球科学进展,2001,16(3):332-338.]

[5] Xu Xueqiang, Zhou Yixing, Ning Yuemin. Urban Geography[M]. Beijing:Higher Education Press,1996.104-108. [许学强,周一星,宁越敏.城市地理学[M].北京:高等教育出版社,1996. 104-108.]

[6] Chen Yanguang, Liu Jisheng. Fractals and fractal dimensions of city-size distributions[J]. Human Geography, 1999,14(2):43-48.[陈彦光,刘继生.城市规模分布的分形和分维[J].人文地理,1999,14(2):43-48.]

[7] Yue Wenze, Xu Jianhua, Si Youyuan, et al. Applications of fractal geometry theory in the study of human geography[J]. Geography and Territorial Research,2001,17(2):52-56.[岳文泽,徐建华,司有元,等.分形理论在人文地理学中的应用研究[J].地理学与国土研究,2001,17(2):52-56.]

[8] Liu Jisheng, Chen Tao. A preliminary study of fractal features of size distribution of cities in northeast China[J]. Scientia Geographica Sinica,1995,15(2):463-476.[刘继生,陈涛.东北地区城市体系空间结构的分形研究[J].地理科学,1995,15(2):463-476.]

[9] Liu Jisheng, Chen Yanguang. Fractal dimensions of spatial structure of an urban system and the methods of their determination[J].Geographical Research,1999,18(1):171-172.[刘继生,陈彦光.城镇体系空间结构的分形维数及其测算方法[J].地理研究,1999,18(1):171-172.]

[10] Abbas H M, Fahmy M M, et al. Neural networks for maximum likelihood clustering[J]. Signal Processing, 1994,36(1):111-126.

[11] Li Shuangcheng. The analysis on regional diferentiations of sustainable by using artificial neural networks[J]. Economic Geography,2001,21(5):523-526.[李双成.中国可持续发展水平区域差异的人工神经网络判定[J].经济地理,2001,21(5):523-526.]

[12] Wen Xin, Zhou Lu, Wang Danli, et al. Neural Networks Design Using MATLAB[M]. Beijing: Science Press,2001. 274-275.[闻新,周露,王丹力,等. MATLAB神经网络设计[M].北京:科学出版社,2001. 274-275.]

[13] Zhou Yixing, Sun Zexin. Rediscussion on China’s urban function classification[J]. Geographical Research, 1997, 16(1):11-22.[周一星,孙则昕.再论中国城市的职能分类[J].地理研究,1997,16(1):11-22.]

[14] Gan Qiaolin, Chen Zhongnuan. The urban function classification of Yunnan[J]. Journal of Sichuan Normal University(NaturalScience),1998,21(5):593-598.[甘巧林,陈忠暖.云南城市的职能分类[J].四川师范大学学报:自然科学版,1998,21(5):593-598.]

[15] Xu Jianhua. Mathematical Methods in Contemporary Geography(2nd)[M]. Beijing: Higher Education Press,2002. 396-440.[徐建华.现代地理学中的数学方法(2nd)[M].北京:高等教育出版社,2002. 436-456.]

[16] Tsao Chen-K, Bezdek J C, Pal N R. Fuzzy Kohonen clustering networks[J]. Pattern Recognition, 1994, 27(5):757-764.

[1]	高俊峰,苏强. 群落物种多度的分形模型和一般性分布规律的验证与探讨[J]. 地球科学进展, 2021, 36(6): 625-631.
[2]	孟宪萌,张鹏举,周宏,刘登峰. 水系结构分形特征的研究进展[J]. 地球科学进展, 2019, 34(1): 48-56.
[3]	栾海军, 田庆久, 章欣欣, 聂芹, 朱晓玲. 定量遥感地表参数尺度转换研究趋势探讨[J]. 地球科学进展, 2018, 33(5): 483-492.
[4]	孙寅森, 郭少斌. 基于图像分析技术的页岩微观孔隙特征定性及定量表征[J]. 地球科学进展, 2016, 31(7): 751-763.
[5]	苏强. 群落物种多度格局的分形解析[J]. 地球科学进展, 2015, 30(10): 1144-1150.
[6]	张朝林，宋长青. “复杂构型涡旋移动动力学的研究”研究成果介绍[J]. 地球科学进展, 2013, 28(9): 1062-1063.
[7]	栾海军，田庆久，余涛，胡新礼，黄彦，刘李，杜灵通，魏曦. 定量遥感升尺度转换研究综述[J]. 地球科学进展, 2013, 28(6): 657-664.
[8]	郭毅,赵景波. 1368—1948年陇中地区干旱灾害时间序列分形特征研究[J]. 地球科学进展, 2010, 25(6): 630-637.
[9]	文战久,高星,姚振兴. 基于“元素含量—面积”模型方法的地球化学场的多重分形模式分析[J]. 地球科学进展, 2007, 22(6): 598-604.
[10]	万丽,王庆飞. 成矿元素品位有序数据集自仿射分形方法应用性评价[J]. 地球科学进展, 2007, 22(4): 357-361.
[11]	朱晓华,蔡运龙. 中国断层系分维及其灰色预测研究[J]. 地球科学进展, 2006, 21(5): 496-503.
[12]	陈彦光,刘继生. 城市人口分布空间自相关的功率谱分析[J]. 地球科学进展, 2006, 21(1): 1-9.
[13]	杨茂森;黎清华;杨海巍. 分形方法在地球化学异常分析中的运用研究——以胶东矿集区为例[J]. 地球科学进展, 2005, 20(7): 809-814.
[14]	李庆谋. 多维分形克里格方法[J]. 地球科学进展, 2005, 20(2): 248-256.
[15]	刘显东;陆现彩;侯庆锋;崔举庆;陆志均;孙岩;徐士进. 基于吸附等温线的表面分形研究及其地球科学应用[J]. 地球科学进展, 2005, 20(2): 201-206.

阅读次数

全文

摘要