元胞自动机在城市模拟中的误差传递与不确定性的特征分析

Analysis of error propagation and uncertainties in urban cellular automata

元胞自动机(Cellular Automata,简称CA)已越来越多地用于地理现象的模拟中,如城市系统的演化等。城市模拟经常要使用GIS数据库中的空间信息,数据源中的误差将会通过CA模拟过程发生传递。此外,CA模型只是对现实世界的近似模拟,这就使得其本身也具有不确定性。这些不确定因素将对城市模拟的结果产生较大的影响,有必要探讨CA在模拟过程中的误差传递与不确定性问题。本文采用蒙特卡罗方法模拟了CA误差的传递特征,并从转换规则、邻域结构、模拟时间以及随机变量等几个方面分析了CA不确定性产生的根源。发现与传统的GIS模型相比,城市CA模型中的误差和不确定性的很多性质是非常独特的。例如,在模拟过程中由于邻域函数平均化的影响,数据源误差将减小;随着可用的土地越来越少,该限制也使城市模拟的误差随时间而减小;模拟结果的不确定性主要体现在城市的边缘。这些分析结果有助于城市建模和规划者更好地理解CA建模的特点。

The issues of data errors, error propagation and model uncertainties are important but often neglected in urban CA models. This paper has examined and addressed some of these issues by carrying out experiments with GIS data. Many model errors are related to model configurations, i.e. how to define a proper model to reflect the real process of urban development. This study demonstrates that some of them, however, are quite unique to CA; 1） data source errors will be reduced during simulation because of the averaging effects of neighborhood functions ; 2） simulation errors will decrease with time because the availability of land suitable for urban development will be decreased in constrained urban CA as the urban areas grow in size; 3） the number of time steps （iterations） can cause different spatial patterns and simulation closer to actual development can be achieved with the increase in time steps; and 4） the major uncertainties of simulation are mainly found at the edge of simulated urban areas. These characteristics are quite different from those of general GIS modeling. The study shows that errors and uncertainties of urban CA are less severe than what one would normally expect from a simulation model. The uncertainties of the simulation will be re- duced if more amounts of land are developed and the uncertainties are mainly located at the urban fringe. The findings of the study can help urban modelers and planners to understand more clearly the characteristics of errors and uncertainties in urban CA so that they can be used more effectively in urban planning.