基于CLUE-S模型的深圳海岸带土地利用变化模拟

Stimulation on Land Use Change of Shenzhen Coastal Zone Based on CLUE-S Model

以深圳海岸带为研究区,基于1996、2005、2011年遥感影像得到研究区土地利用历史数据,选取自然、社会统计数据作为驱动因素,利用CLUE-S模型分别从不同时间尺度和空间尺度对研究区2005、2011年的土地利用分布予以模拟,并对模拟结果分别从类别和景观水平予以精度评价。从类别水平角度,选择ROC曲线对各地类的Logistic回归拟合精度进行评价;从景观水平角度,选取Kappa指数对模拟效果予以评估,以验证所选驱动因子的合理性。结果表明:在研究区范围内,CLUE-S模型的类别精度随着空间分辨率的改变而有所差异,100 m分辨率为本研究模拟的最佳尺度,各地类的ROC值均高于0.7;随着模拟时间的缩短模拟精度有所增加;东海岸由于受到人类影响较小,模拟效果整体相对较好。总体而言,CLUE-S模型适用于研究区土地利用模拟,所选驱动力因子能够对研究区土地利用变化予以较好的解释。

Based on 1996,2005 and 2011 remote sensing images,this paper used CLUE- S model to simulate the land use spatial patterns of 2005 and 2011 from different time and space scales in Shenzhen coastal zone. A series of natural and social statistics were used as driving factors,the simulation accuracy is evaluated from the different level to verify the rationality of the selected driving factors. In order to verify the reasonableness of the selected drive factors,the ROC curve was used to validate the fitting accuracy of the logistic regression model from the perspective of the category level,and the Kappa index was used to evaluate the simulation results of the CLUE- S model from the perspective of landscape level. The results showed that in the range of 100 m resolution the Logistic fitting accuracy has achieved the best results in the study area,the accuracy of each land use type were above 0. 7 in eastern and western coast in both 1996 and 2005. Landscape simulation accuracy increases with time shortened. The Landscape simulation accuracy of Eastern Coast is relatively better due to the small human influence. Overall,the CLUE- S model is suitable for simulating the spatial distribution patterns of the main land use types in Shenzhen coastal zone,and the selected driving factors can explain the changes of land use in the study area.