您好，欢迎访问广东省农业科学院 机构知识库！
广东省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

A Novel Method for Mapping Moso Bamboo Forests Using Remote Sensing Data With the Consideration of Phenological Status

文献类型： 外文期刊

作者： Huang, Xuying 1 ; Ju, Weimin 3 ; Xu, Zhanghua 4 ; Li, Jing 1 ;

作者机构： 1.Nanjing Univ, Int Inst Earth Syst Sci, Sch Geog & Ocean Sci, Nanjing 210023, Jiangsu, Peoples R China

2.Guangdong Acad Agr Sci, Inst Agr Econ & Informat, Guangzhou 510640, Guangdong, Peoples R China

3.Jiangsu Ctr Collaborat Innovat Geog Informat Resou, Int Inst Earth Syst Sci, Nanjing 210023, Jiangsu, Peoples R China

4.Fuzhou Univ, Acad Digital China, Coll Environm & Safety Engn, Fuzhou 350108, Fujian, Peoples R China

关键词： Forest; generative adversarial networks (GANs); machine learning; moso bamboo; remote sensing; spectral

期刊名称：IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING （ 影响因子：7.5； 五年影响因子：7.6 ）

ISSN： 0196-2892

年卷期： 2024 年 62 卷

页码：

收录情况： SCI

摘要： Precisely delineating the distribution of moso bamboo forests is critical for forestry management and regional carbon cycle research. The unique phonological characteristics (i.e., on- and off-year phenomenon) of bamboo impose difficulties in bamboo identification. This study aims to develop a new algorithm for mapping bamboo distribution using remote sensing data with the consideration of bamboo phenological characteristics. Three optical indices were proposed based on canopy reflectance retrieved from Sentinel-2 and field inventory data, including modified bamboo index (MBI), bamboo phenological characteristic index (BPCI), and BPCI 2 (BPCI-2). The collaboration of these three indices with the recursive feature elimination (RFE) and extreme gradient boosting (XGBoost) methods can precisely map bamboo distribution and its phenological status. The model based on MBI, BPCI, and BPCI-2 outperformed the model driven by the existing bamboo extracting indices, i.e., bamboo index (BI), yearly change bamboo index (YCBI), and monthly change bamboo index (MCBI), increasing in overall accuracy (OA) by about 1.5%. Additionally, the proposed indices were calculated using the data synthesized from Sentinel-1 synthetic aperture radar (SAR) imageries by the cycle-consistent adversarial network (CycleGAN) method under the condition without cloudy-free Sentinel-2 data available to fill the time series data gaps. The performance of the model based on augmented data improved notably in comparison with the model driven only by indices from original optical images, with the identification accuracy for on- and off-year bamboo samples over 96%. The generated moso bamboo distribution map aligns well with forestry inventory data in terms of both area and spatial distribution. The proposed indices are less sensitive to terrain than the existing bamboo extracting indices. This merit is valuable for better mapping bamboo forests, which are mostly distributed in mountainous areas.

  • 相关文献
作者其他论文 更多>>
置顶
购物车
反馈

© 京ICP备09089781号-29 主办单位：广东省农业科学院

学术资源： 中国农业科学院 农业专业知识服务系统 农科联盟资源共建共享平台 中国农业科技文献与信息服务平台 中国农业期刊集成服务平台