基于粗集的知识发现与地理模拟——以深圳市土地利用变化为例

为了更有效地模拟地理现象的复杂演变过程,提出了用粗集理论来确定元胞自动机 (CA)不确定性转换规则的新方法。CA可以通过局部规则来有效地模拟许多地理现象的演变过程。但目前缺乏很好定义CA转换规则的方法。往往采用启发式的方法来定义CA的转换规则,这些转换规则是静态的,而且其参数值多是确定的。在反映诸如城市扩张、疾病扩散等不确定性复杂现象时,具有一定的局限性。利用粗集从GIS和遥感数据中发现知识,自动寻找CA的不确定性转换规则,基于粗集的CA在缩短建模时间的同时,能提取非确定性的转换规则,更好地反映复杂系统的特点。采用所提出的方法模拟了深圳市的城市发展过程,取得了比传统MCE方法更好的模拟效果。

Mining Transition Rules for Geo-simulation Using Rough Sets

This paper presents a new method to simulate complex land use systems by integrating rough sets (RS), cellular automata, and GIS. Recently, cellular automata (CA) have been increasingly used to simulate urban growth and land use dynamics. Traditional CA models simulate urban development with static transition rules in large areas. Most of them are expressed by mathematical formulas and the transition rules are fixed. These models have limitations to simulate complex land use change. The transition rules should be subject to uncertainties and they should vary spatially. In this study, a CA model based on rough sets is developed using Visual Basic and ArcObjects of GIS. The GIS provides both data and spatial analysis functions for constructing RS-CA model. Training data are conveniently retrieved from remote sensing and GIS database for calibrating and testing the model. The rough sets method is used to obtain the uncertainty and dynamic transition rules. The RS-CA model can be applied to the simulation of urban development. Complex global patterns can be generated from the local interactions with the RS-CA model. This paper demonstrates that the proposed model can overcome some of the shortcomings of the existing CA models in simulating complex urban systems by using the rough set method. The model has been successfully applied to the simulation of urban development in Shenzhen city of the Pearl River Delta.