Spectroscopy and Spectral Analysis, Volume. 42, Issue 10, 3263(2022)

Comparison of Forest Stock Volume Inversion Methods Coupled With Multiple Features——A Case Study of Forest in Yarlung Zangbo River Basin

Zi-zhao LI*, Shou-dong BI, Yu-huan CUI, and Shuang HAO*;
Author Affiliations
  • School of Science, Anhui Agricultural University, Hefei 230036, China
  • show less
    Figures & Tables(6)
    Location and sample plots of the study area
    Relationship of the number of decision trees and the error
    The importance of each feature
    Scatter plots of different inversion models
    Comparison of accuracy
    • Table 1. Modeling result

      View table
      View in Article

      Table 1. Modeling result

      特征组合模型名称R2MAE/
      (m3·ha-1)
      RMSE/
      (m3·ha-1)
      地形因子和
      波段比值
      多元逐步回归0.43668.72578.012
      BP神经网络0.39770.16980.003
      随机森林0.61763.87572.457
      地形因子和
      纹理特征
      多元逐步回归0.50261.99774.948
      BP神经网络0.44368.25877.864
      随机森林0.70458.86367.712
      地形、 波段和
      纹理特征
      多元逐步回归0.54158.31771.562
      BP神经网络0.47767.50373.226
      随机森林0.73955.35263.195
    Tools

    Get Citation

    Copy Citation Text

    Zi-zhao LI, Shou-dong BI, Yu-huan CUI, Shuang HAO. Comparison of Forest Stock Volume Inversion Methods Coupled With Multiple Features——A Case Study of Forest in Yarlung Zangbo River Basin[J]. Spectroscopy and Spectral Analysis, 2022, 42(10): 3263

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Research Articles

    Received: Jun. 29, 2021

    Accepted: Jan. 28, 2022

    Published Online: Nov. 23, 2022

    The Author Email: Zi-zhao LI (691039258@qq.com)

    DOI:10.3964/j.issn.1000-0593(2022)10-3263-06

    Topics