Please wait a minute...
 首页  期刊介绍 期刊订阅 广告合作 联系我们 English
 
最新录用  |  当期目录  |  过刊浏览  |  热点文章  |  阅读排行  |  下载排行  |  引用排行
地理研究  2005, Vol. 24 Issue (1): 19-27    DOI: 10.11821/yj2005010003
  论文 本期目录 | 过刊浏览 | 高级检索 |
基于神经网络的元胞自动机及模拟复杂土地利用系统
黎夏1, 叶嘉安2
1. 中山大学地理科学与规划学院, 广州 510275;
2. 香港大学城市规划及环境管理研究中心, 香港
Cellular automata for simulating complex land use systems using neural networks
LI Xia1, Anthony Gar-On Yeh2
1. School of Geography and Planning, Zhongshan University, Guangzhou 510275, China;
2. Centre of Urban Planning and Environmental Management, the University of Hong Kong, Hong Kong, China
全文: PDF(802 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 

本文提出了基于神经网络的元胞自动机(CellularAutomata),并将其用来模拟复杂的土地利用系统及其演变。国际上已经有许多利用元胞自动机进行城市模拟的研究,但这些模型往往局限于模拟从非城市用地到城市用地的转变。模拟多种土地利用的动态系统比一般模拟城市演化要复杂得多,需要使用许多空间变量和参数,而确定模型的参数值和模型结构有很大困难。本文通过神经网络、元胞自动机和GIS相结合来进行土地利用的动态模拟,并利用多时相的遥感分类图像来训练神经网络,能十分方便地确定模型参数和模型结构,消除常规模拟方法所带来的弊端。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
关键词 神经网络元胞自动机遥感土地利用GIS    
Abstract

This paper presents a new method to simulate the dynamics of multiple land uses based on the integration of neural networks,cellular automata and GIS. Recently, cellular automata (CA) have been increasingly used to simulate urban growth and land use dynamics. However, simulation of multiple land use changes using CA models is difficult because numerous spatial variables and parameters have to be utilized. Conventional CA models have problems in defining simulation parameter values, transition rules and model structures. In this paper, a three-layer neural network with multiple output neurons is designed to calculate conversion probabilities for competing multiple land uses. The neural-network-based CA model is directly developed in a GIS environment by using ARC/INFO GRID AML. The GIS provides both data and spatial analysis functions for constructing the neural network. Real data are conveniently retrieved from the GIS database for calibrating and testing the model. The GIS functions are also used for the neural network calculations. The neural network has multiple output neurons to generate conversion probabilities at each iteration. Land use conversion is decided by comparing the conversion probabilities. The model is carried out by iterative looping the neural network for simulating multiple land use changes. Complex global patterns can be generated from local interactions through the neural network. The simulation results are not deterministic because a stochastic variable is used and site attributes are dynamically updated at the end of each loop. The proposed method can overcome some of the shortcomings of the currently used CA models in simulating complex urban systems and multiple land use changes by significantly reducing the tedious work in defining parameter values, transition rules and model structures. The model has been successfully applied to the simulation of land use dynamics in the Pearl River Delta.

Key wordsneural networks    cellular automata    remote sensing    land use    GIS
收稿日期: 2004-05-25      出版日期: 2005-02-15
基金资助:

国家自然科学基金资助项目(40471105);高等学校博士学科点专项科研基金资助(20040558023)

作者简介: 黎夏(1962-),男,广西梧州人,中山大学特聘教授,博士生导师。1983年硕士毕业于北京大学, 1996年获香港大学博士学位,1997~98年在香港大学进行博士后研究。主要从事遥感和地理信息系统 研究。在国内外刊物上发表近100篇学术论文。Email:gplx@zsu.edu.cn
引用本文:   
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.
LI Xia, Anthony Gar-On Yeh. Cellular automata for simulating complex land use systems using neural networks. GEOGRAPHICAL RESEARCH, 2005, 24(1): 19-27.
链接本文:  
http://www.dlyj.ac.cn/CN/10.11821/yj2005010003      或      http://www.dlyj.ac.cn/CN/Y2005/V24/I1/19


[1] Mertens B,Lambin E F. Land-cover-change trajectories in Southern Cameroon1 Annals of the A ssociation of American Geographers,2000,93(3):467~494.
[2] 刘纪远,张增祥,等.20世纪90年代中国土地利用变化时空特征及其成因分析.地理研究,2003,22(1):1~12.
[3] 何春阳,史培军,陈晋,等.北京地区土地利用/覆盖变化研究.地理研究,2001,20(6):679~687.
[4] Batty M,Xie Y1 From cells to cities. Environment and Planning B:Planning and Design,1994,21:531~548.
[5] W hite R,Engelen G,U ijee I1 The use of constrained cellular automata for high-resolution modelling of urban land-use dynam ics. Environment and Planning B:Planning and Design,1997,24:323~343.
[6] W u F,W ebster C J. Simulation of land development through the integration of cellular automata and multicriteria evaluation. Environment and Planning B:Planning and Design,1998,25:103~126.
[7] Clarke K C,Hoppen S,Gaydos L. A self-modifying cellular automaton model of historical urbanization in the San Francisco Bay area. Environment and Planning B:Planning and Design,1997,24:247~261.
[8] Clarke K C,Gaydos L J. Loose-coup ling a cellular automata model and GIS:long-term urban growth p rediction for SanFrancisco and W ashington/Baltimore. International Journal of Geographical Information Science,1998,12(7):699~714.
[9] L i X,Yeh A G O. Modelling sustainable urban development by the integration of constrained cellular automata and GIS.International Journal of Geographical Information Science,2000,14(2):131~152.
[10] 黎夏,叶嘉安.约束性单元自动演化CA模型及可持续城市发展形态的模拟.地理学报,1999,54(4):289~298.
[11] L i X,Yeh A G O. Zoning for agricultural land p rotection by the integration of remote sensing,GIS and cellular automata.Photogrammetric Engineering&Remote Sensing,2001,67(4):471~477.
[12] 黎夏,叶嘉安.主成分分析与Cellular Automata在空间决策与城市模拟中的应用.中国科学,2001,31(8):683~690.
[13] Newkirk R T,W ang F1A common knowledge database for remote-sensing and geographic information in a change2detectionexpert system. Environment and Planning B,1990,17(4):395~404.
[14] L i X,Yeh A G O1 Principal component analysis of stacked multi-temporal images for monitoring of rap id urban expansionin the Pearl R iver Delta. International Journal of Remote Sensing,1998,19(8):1501~1518.
[15] Openshaw S1 Neural network,genetic,and fuzzy logic models of spatial interaction1 Environment and Planning A,1998,30:1857~1872.
[16] 黎夏,叶嘉安.利用遥感监测和分析珠江三角洲的城市扩张过程———以东莞市为例.地理研究,1997,16(4):56~61.
[17] 黎夏,叶嘉安.利用主成分分析来改善土地利用变化的遥感监测精度.遥感学报,1997,1(4):282~289.
[18] W u F1 Calibration of stochastic cellular automata:the app lication to rural-urban land conversions1 International Journal ofGeographical Information Science,2002,16(8):795~818.
[19] W ang F. The use of artificial neural networks in a geographical information system for agricultural land-suitability assessment. Environment and Planning A,1994,26:265~284.

[1] 孙喆. 北京中心城区内涝成因[J]. 地理研究, 2014, 33(9): 1668-1679.
[2] 刘凤山, 陶福禄, 肖登攀, 张帅, 王猛, 张贺, 柏会子. 土地覆被变化过程中叶面积指数与降水量对地表能量平衡的贡献——基于SiB2的模拟结果[J]. 地理研究, 2014, 33(7): 1264-1274.
[3] 王祺, 蒙吉军, 毛熙彦. 基于邻域相关的漓江流域土地利用多情景模拟与景观格局变化[J]. 地理研究, 2014, 33(6): 1073-1084.
[4] 侯松岩, 姜洪涛. 基于城市公共交通的长春市医院可达性分析[J]. 地理研究, 2014, 33(5): 915-925.
[5] 王娇, 程维明, 祁生林, 周成虎, 张文杰, 仝迟鸣. 基于USLE和GIS的水土流失敏感性空间分析——以河北太行山区为例[J]. 地理研究, 2014, 33(4): 614-624.
[6] 宋小青, 吴志峰, 欧阳竹. 耕地转型的研究路径探讨[J]. 地理研究, 2014, 33(3): 403-413.
[7] 葛淼, 薛然尹, 何进伟, 胡燕宇. 中国男性儿童呼气高峰流量参考值地理分布[J]. 地理研究, 2014, 33(3): 451-466.
[8] 李行, 张连蓬, 姬长晨, 刘红樱, 黄巧华. 基于遥感和GIS的江苏省海岸线时空变化[J]. 地理研究, 2014, 33(3): 414-426.
[9] 王露, 杨艳昭, 封志明, 游珍. 基于分县尺度的2020-2030年中国未来人口分布[J]. 地理研究, 2014, 33(2): 310-322.
[10] 刘耀林, 李纪伟, 侯贺平, 刘艳芳. 湖北省城乡建设用地城镇化率及其影响因素[J]. 地理研究, 2014, 33(1): 132-142.
[11] 乔伟峰, 盛业华, 方斌, 王亚华. 基于转移矩阵的高度城市化区域土地利用演变信息挖掘——以江苏省苏州市为例[J]. 地理研究, 2013, 32(8): 1497-1507.
[12] 祝合勇, 杨太保, 田洪阵. 1973-2010年阿尔金山冰川变化[J]. 地理研究, 2013, 32(8): 1430-1438.
[13] 王万同, 王卷乐, 杜佳. 基于ETM+与MODIS数据融合的伊洛河流域地表蒸散估算[J]. 地理研究, 2013, 32(5): 817-827.
[14] 张学儒, 张镱锂, 刘林山, 张继平. 基于SOFM神经网络模型的土地类型分区尝试——以青藏高原东部样带为例[J]. 地理研究, 2013, 32(5): 839-847.
[15] 袁林旺, 俞肇元, 罗文, 易琳, 闾国年. 多维统一GIS构建与实现的几何代数方法[J]. 地理研究, 2013, 32(5): 974-983.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《地理研究》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn