地理研究 ›› 2016, Vol. 35 ›› Issue (7): 1288-1300.doi: 10.11821/dlyj201607006

• 研究论文 • 上一篇    下一篇

基于GA-MCE算法的不规则邻域CA土地利用模拟

杨俊1,2(), 张永恒1, 葛全胜2, 李雪铭1   

  1. 1. 辽宁师范大学自然地理与空间信息科学辽宁省重点实验室,大连 116029
    2. 中国科学院陆地表层格局与模拟重点实验室,中国科学院地理科学与资源研究所,北京 100101
  • 收稿日期:2016-01-22 修回日期:2016-05-13 出版日期:2016-07-30 发布日期:2016-07-26
  • 作者简介:

    作者简介:杨俊(1978- ),男,湖北孝昌人,博士,副教授,主要从事人居环境、土地利用变化与地理信息系统应研究。E-mail: yangjun@lnnu.edu.cn

  • 基金资助:
    国家自然科学基金项目(41471140,41171137);辽宁省高等学校杰出青年学者成长计划(LJQ2015058)

Irregular neighborhood cellular automata land-use simulation based on the GA-MCE algorithm

Jun YANG1,2(), Yongheng ZHANG1, Quansheng GE2, Xueming LI1   

  1. 1. Liaoning Key Laboratory of Physical Geography and Geomatics, Liaoning Normal University, Dalian 116029, Liaoning, China
    2. Key Laboatory of Land Surface Pattern and Simulation, Institute of Geographic Sciences and Natural Resources Research, CAS, Beijing 100101, China
  • Received:2016-01-22 Revised:2016-05-13 Online:2016-07-30 Published:2016-07-26

摘要:

不规则邻域元胞自动机通过定义一定的邻域规则,将对中心元胞影响较大的邻域元胞进行识别与计算从而确定邻域形态与影响范围,与传统元胞自动机模型相同尺寸邻域形态相比,模拟更加真实有效。基于不规则邻域识别算法对元胞邻域范围进行划分,再通过遗传算法和多准则评价相结合获取转化规则参数,继而对大连市金石滩国家旅游度假区2004年和2010年土地利用变化进行模拟研究,通过比对分析以及Kappa系数检验法对模拟精度做一检验,研究模拟结果总体Kappa系数为81.62%,具有一定的可靠性,研究显示该模型在多地类碎小斑块之间的转化模拟具有一定的优势,对于模拟土地利用/覆盖变化模型具有一定的改进。

关键词: 不规则邻域, 元胞自动机, 土地利用变化模拟, 遗传算法, 土地利用转移概率, 大连市金石滩国家旅游度假区

Abstract:

The irregular neighborhood cellular automata land-use simulation determines the condition of cellular neighborhoods and their scope of influence in order to distinguish and calculate the cellular neighborhoods which have a high degree of influence on the central cellular by defining certain rules for the neighborhoods. Compared with the form of a neighborhood of the same size in the traditional cellular automaton model, irregular neighborhood cellular automata is far more realistic and effective. Based on modifying the cellular neighborhoods' range with the irregular neighborhood recognition algorithm and obtaining the parameters of the invert rules through a combination of the genetic algorithm and multi-criteria evaluation, we ran a simulation of land-use changes in Jinshitan National Tourist Holiday Resort from 2004 to 2010. The result shows that the coefficient of Kappa is 81.62%, which was obtained through Kappa analysis and testing of simulative accuracy and is highly reliable. In addition, the result shows that this approach has certain advantages regarding the simulation between class plots and smash plots plaque, which will improve the simulation model for land-use/cover changes.

Key words: irregular neighborhood, cellular automata, land-use change simulation, genetic algorithm, land-use transition probability, Jinshitan National Tourist Holiday Resort