论文部分内容阅读
以海上丝绸之路沿线的11个超大城市为例,基于长时间序列的Landsat MSS/TM/ETM+/OLI和HJ-1卫星CCD数据,利用基于面向对象的支持向量机SVM(Support Vector Machine)分类方法提取20世纪70年代到2015年的城市不透水层,并结合景观格局指数—最大斑块指数LPI(Largest Patch Index)、斑块密度PD(Patch Density)和欧几里得最邻近距离ENN(Euclidean Nearest Neighbor Distance)分析了超大城市的发展模式。研究结果表明:基于面向对象的SVM分类方法能够高效提取城市不透水层;平均总精度高于87.9%,平均Kappa系数高于0.87;过去40余年,各超大城市的面积扩张了4—13倍,中国和印度的超大城市扩张最快,广州、上海超过12倍;各城市以“中心—边缘”或“沿海—内陆”的方向扩张,表现为“扩散—聚集—再扩散”的扩张模式;总体来看,沿线的城市化进程仍处于上升期。本研究为建设“21世纪海上丝绸之路”提供了科学依据,对当地生态环境保护和新型城镇化建设具有重要意义。
Taking 11 megacities along the Maritime Silk Road as an example, based on the long time series CCDS data of Landsat MSS / TM / ETM + / OLI and HJ-1 satellite, this paper uses object-oriented Support Vector Machine (SVM) Methods The urban impermeable layer from the 1970s to 2015 was extracted. Combined with the landscape pattern indices - Largest Patch Index (LPI), Patch Density (Patch Density) and Euclidean Nearest Neighbor (ENN) Euclidean Nearest Neighbor Distance) analyzes the development of megacities. The results show that the object-oriented SVM classification method can effectively extract the urban impervious layer; the average total accuracy is higher than 87.9% and the average Kappa coefficient is higher than 0.87; in the past 40 years, the area of each mega-city has expanded by 4-13 times, The megacities in China and India have the fastest expansion, with Guangzhou and Shanghai over 12 times. The cities are expanding in the direction of “center-periphery” or “coastal-inland”, showing “diffusion-aggregation-re-diffusion ”In general, the process of urbanization along the line is still on the rise. This study provides a scientific basis for building the “21st Century Maritime Silk Road” and is of great significance to the protection of local ecological environment and new urbanization.