轨道交通建设影响下土地利用性质空间分异的组合预测模型

在先验数据有限且存在不确定因素情形下，为解决城市轨道交通沿线土地利用性质空间分异的预测问题，提出一种基于系统云灰色模型和马尔可夫链的组合预测模型。采用系统云灰色模型，使用较少量的历史数据完成城市轨道交通沿线各类性质用地面积变化曲线的粗略拟合；借助马尔可夫链进行系统状态划分，通过缩小预测区间以提高预测精确度；运用组合预测模型，对2003-2015年南京市轨道交通1号线主要吸引范围内土地利用性质的空间分异进行了预测分析。计算结果表明：轨道交通建设加剧了城市土地利用性质的空间分异，其周边各种性质的土地利用面积变化趋势呈现出非平稳随机过程特性；轨道交通建设对不同性质土地利用的影响方式与影响强度各不相同，其中，对居住用地具有强烈的吸引作用，对公建用地吸引作用不明显，对工业用地具有明显的排斥作用。

Integrated Forecasting Model for the Space Differentiation of Land Use Type under the Influence of Rail Transit Construction

An integrated model based on system cloud grey model and Markov chain was established to forecast differentiation of land type along urban rail transit when many random factors exist and statistics are scarce. Firstly, system cloud grey model was used to get the dynamic baseline for area change of every land type along the rail transit. Secondly, Markov chain was applied to achieve the state transition probability matrix, by which the forecasting result based on system cloud grey model was modified. Lastly, land use differentiation along the rail transit Line 1 in Nanjing from the year 2003 to 2015 was taken as an example to illustrate the application of the model. The forecasting results show as follows. Rail transit construction accelerates land use differentiation, and the process of land use differentiation is a non-stationary random process. The impacts of rail transit construction on different kinds of land use are different. The residence land is attracted by rail transit, whereas the manufacture land is excluded from rail transit. Rail transit has no obvious action on the land of public utilities.