您好，欢迎访问河南省农业科学院 机构知识库！
河南省农业科学院机构知识库

全部

  • 全部
  • 标题
  • 学者
  • 机构
  • 关键词

Estimation of Tree Species Diversity in Warm Temperate Forests via GEDI and GF-1 Imagery

文献类型： 外文期刊

作者： Zhang, Lei 1 ; Yang, Liu 1 ; Sun, Jinhua 1 ; Zhu, Qimeng 1 ; Wang, Ting 1 ; Zhao, Hui 2 ;

作者机构： 1.Henan Agr Univ, Coll Forestry, Zhengzhou 450046, Peoples R China

2.Henan Acad Agr Sci, Zhengzhou 450008, Peoples R China

3.Henan Yuzhou Forest Ecosyst Natl Positioning Obser, Yuzhou 461670, Peoples R China

关键词： forest; diversity index; spectral image; LiDAR; machine learning

期刊名称：FORESTS （ 影响因子：2.5； 五年影响因子：2.7 ）

ISSN：

年卷期： 2025 年 16 卷 4 期

页码：

收录情况： SCI

摘要： Estimates of tree species diversity via traditional optical remote sensing are based only on the spectral variation hypothesis (SVH); however, this approach does not account for the vertical structure of a forest. The relative height (RH) indices derived from GEDI spaceborne LiDAR provide vertical vegetation structure information through waveform decomposition. Although RH indices have been widely studied, the optimal RH index for tree species diversity estimation remains unclear. This study integrated GF-1 optical imagery and GEDI LiDAR data to estimate tree species diversity in a warm temperate forest. First, random forest plus residual kriging (RFRK) was employed to achieve wall-to-wall mapping of the GEDI-derived indices. Second, recursive feature elimination (RFE) was applied to select relevant spectral and LiDAR features. The random forest (RF), support vector machine (SVM), and k-nearest neighbor (kNN) methods were subsequently applied to estimate tree species diversity through remote sensing data. The results indicated that multisource data achieved greater accuracy in tree species diversity estimation (average R2 = 0.675, average RMSE = 0.750) than single-source data (average R2 = 0.636, average RMSE = 0.754). Among the three machine learning methods, the RF model (R2 = 0.760, RMSE = 2.090, MAE = 1.624) was significantly more accurate than the SVM (R2 = 0.571, RMSE = 2.556, MAE = 1.995) and kNN (R2 = 0.715, RMSE = 2.084, MAE = 1.555) models. Moreover, mean_mNDVI, mean_RDVI, and mean_Blue were identified as the most important spectral features, whereas RH30 and RH98 were crucial features derived from LiDAR for establishing models of tree species diversity. Spatially, tree species diversity was high in the west and low in the east in the study area. This study highlights the potential of integrating optical imagery and spaceborne LiDAR for tree species diversity modeling and emphasizes that low RH indices are most indicative of middle- to lower-canopy tree species diversity.

  • 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：河南省农业科学院

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