Analysis and Comprehensive Evaluation of Urban Green Space Information Based on Gaofen 7: Considering Beijing's Fifth Ring Area as an Example

文献类型： 外文期刊

第一作者： Li, Bin

作者： Li, Bin;Xu, Xiaotian;Wang, Hongyu;Duan, Yingrui;Lei, Hongjuan;Liu, Chenchen;Zhao, Na;Li, Shaoning;Lu, Shaowei;Li, Bin;Xu, Xiaotian;Wang, Hongyu;Duan, Yingrui;Lei, Hongjuan;Liu, Chenchen;Zhao, Na;Li, Shaoning;Lu, Shaowei;Wang, Hongyu;Duan, Yingrui;Lei, Hongjuan;Liu, Chenchen;Li, Shaoning;Lu, Shaowei;Liu, Xu

作者机构：

关键词： urban green space; high-resolution remote sensing; machine learning; green space information analysis; evaluation system

期刊名称：REMOTE SENSING （ 影响因子：4.1； 五年影响因子：4.8 ）

ISSN：

年卷期： 2024 年 16 卷 21 期

页码：

收录情况： SCI

摘要： Urban green spaces constitute a vital component of the ecosystem. This study focused on urban green spaces located within the Fifth Ring Road of Beijing, using Gaofen 7 (GF-7) as the primary data source for analysis. The main objective was to develop a system for extracting and classifying urban green spaces in Beijing by applying deep learning and machine learning algorithms, and further, the results were validated with ground survey samples. This study provides detailed extraction and classification of urban green space coverage by creating a comprehensive evaluation system. The primary findings indicate that the deep learning algorithm enhances the precision of green space information extraction by 10.68% compared to conventional machine learning techniques, effectively suppresses "pretzel noise", and eventually aids in extracting green space information with complete edges. The thorough assessment of green spaces within the study area indicated favorable outcomes showing the high service capacity of park green spaces. The overall classification accuracy of the final extraction results was 94.31%. Nonetheless, challenges, such as unequal distribution of green zones and a significant fragmentation level throughout the study area, were still encountered. Consequently, the use of GF-7 high-resolution imagery, in conjunction with the collaborative application of deep learning and machine learning techniques, enabled the acquisition of highly accurate information regarding urban green zone coverage. According to the established grading standards of evaluation indices, the landscape pattern of urban green spaces within the study area was comprehensively assessed. This evaluation offers essential data support for monitoring urban green spaces and planning landscape patterns, thereby contributing to the achievement of sustainable development objectives related to urban greening and ecological conservation.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序