Simulating urban growth by integrating landscape expansion index (LEI) and cellular automata
Simulating urban growth by integrating landscape expansion index (LEI) and cellular automata
复制标题
通过整合景观扩张指数 (LEI) 和元胞自动机来模拟城市增长
DOI：
10.1080/13658816.2013.831097
复制
发表时间：
2014-01-02
影响因子：
5.7
通讯作者：
He, Zhijian
中科院分区：
文献类型：
--
作者：
Liu, Xiaoping;Ma, Lei;He, Zhijian
传统的城市元胞自动机（CA）模型可以有效地模拟城市的填充和边缘扩展增长模式。然而，这些模型大多无法模拟外围的增长。本文提出了一种新的模型LEI-CA，它结合了景观扩展指数（LEI）和CA来模拟城市增长。通过计算各单元的LEI指数来识别城市增长类型。采用基于实例的推理技术，分别对相邻生长类型和远离生长类型发现不同的过渡规则。本文应用LEI-CA模型对东莞市的城市增长进行了模拟。通过与基于逻辑的CA和LEI-CA的比较，表明LEI-CA具有更好的性能。1993年、1999年和2005年，LEI-CA模型比基于物流的CA模型分别提高了13.8%、10.8%和6.9%的城市模拟精度。此外，基于逻辑的元胞自动机模型几乎不存在外围增长类型的模拟，而建议的LEI-CA模型在模拟不同的城市增长模式表现良好。实验表明，LEI-CA模型不仅克服了传统CA模型的不足，而且能够更好地理解城市演化过程。
Traditional urban cellular automata (CA) model can effectively simulate infilling and edge-expansion growth patterns. However, most of these models are incapable of simulating the outlying growth. This paper proposed a novel model called LEI-CA which incorporates landscape expansion index (LEI) with CA to simulate urban growth. Urban growth type is identified by calculating the LEI index of each cell. Case-based reasoning technique is used to discover different transition rules for the adjacent growth type and the outlying growth type, respectively. We applied the LEI-CA model to the simulation of urban growth in Dongguan in southern China. The comparison between logistic-based CA and LEI-CA indicates that the latter can yield a better performance. The LEI-CA model can improve urban simulation accuracy over logistic-based CA by 13.8%, 10.8% and 6.9% in 1993, 1999 and 2005, respectively. Moreover, the outlying growth type hardly exists in the simulation by logistic-based CA, while the proposed LEI-CA model performs well in simulating different urban growth patterns. Our experiments illustrate that the LEI-CA model not only overcomes the deficiencies of traditional CA but might also better understand urban evolution process.