AutoLogistic方法在土地利用格局模拟中的应用——以张家界市永定区为例

土地利用/ 土地覆被变化(LUCC) 是当前研究全球变化的重要内容, 而区域土地利用 格局模拟是LUCC 研究的核心内容之一。以张家界市永定区为研究单元, 根据由2005 年土地 利用现状图和数字高程模型数据源得到的土地利用、地形、河流以及道路等空间数据, 对区 域土地利用类型空间格局的空间自相关性特征进行了建模研究, 并通过在传统Logistic 模型 中引入描述空间自相关性的成份, 实现了能够考虑自相关性因素的回归分析模型 (AutoLogistic 模型), 同时应用该模型对区域土地利用格局进行了模拟和分析。结果显示, 通 过与没有考虑空间自相关性的回归模型(传统Logistic 模型) 相比较, 该模型显示了更好的拟 合优度和更高的拟合准确率(耕地、林地、建设用地及未利用地的ROC 值分别从0.851、 0.913、0.877 和0.852 提高到0.893、0.940、0.907 和0.863)。研究结果说明了基于 AutoLogistic 方法的土地利用格局的相关性建模在一定意义上是合理的。同时研究结果也可以 为永定区及其相似地区的土地利用规划决策提供更为科学的依据。

Simulation on Spatial Land Use Patterns Using AutoLogistic Method: A Case Study of Yongding County, Zhangjiajie

Land use/land cover change (LUCC) is an important content of geographical research on global change today, while spatial simulation on regional land use patterns is one of the key contents of LUCC research because modeling is an important tool for simulating land use patterns due to its ability to integrate measurements of changes in land cover and the associated drivers. Spatial data, like land-use data, have a tendency to be dependent (spatial autocorrelation), which means that when using spatial models, a part of the variance may be explained by neighbouring values. The classic regression model can only analyze the correlation between land use types and driving factors, but cannot depict spatial autocorrelation. Land uses in Yongding County, which is one of the typical karst mountain areas in northwestern Hunan province, were investigated by means of modeling the spatial autocorrelation of land use types for the purpose of deriving better spatial land use patterns on the basis of terrain characteristics and infrastructural conditions. All driving factors such as distance to town, distance to river, distance to road, population density, altitude, slope and aspect were produced with ArcGis spatial analysis means. Then the weighting coefficient of every land use type was analysed with SPSS13.0. Through incorporating components describing the spatial autocorrelation into a classic Logistic model, this paper sets up a regression model (AutoLogistic model), which considers the spatial autocorrelation factor, and uses the model to simulate and analyze the spatial land use patterns in Yongding County. In addition, the results of two different models are validated by an ROC method. The ROC can compare a map of actual land use distribution to maps of modeled probability for land use types. Through comparison with the classic logistic model without considering the spatial autocorrelation, this model showed better goodness of fitting and higher accuracy of fitting. The ROC curves (AUC) of cultivated land, forest land, construction land and virgin land from classic Logistic regression model were 0.851, 0.913, 0.877 and 0.852 respectively. They were improved to 0.893, 0.940, 0.907 and 0.863 accordingly when using AutoLogistic model. It is argued that the improved model based on autologistic method is reasonable to some degree. At the same time, these types of analysis can provide valuable information for modeling future land use change scenarios that need to consider local and regional conditions of actual land use, and the probability maps of land use types obtained from this study can also support government decisions on land use management for Yongding County and similar areas.