Regional Scale Inversion of Chlorophyll Content of Dendrocalamus giganteus by Multi-Source Remote Sensing

文献类型： 外文期刊

第一作者： Xia, Cuifen

作者： Xia, Cuifen;Zhou, Wenwu;Shu, Qingtai;Wu, Zaikun;Xu, Li;Yang, Huanfen;Qin, Zhen;Wang, Mingxing;Duan, Dandan

作者机构：

关键词： RS; machine learning; chlorophyll content; Dendrocalamus giganteus; inversion

期刊名称：FORESTS （ 影响因子：2.4； 五年影响因子：2.7 ）

ISSN：

年卷期： 2024 年 15 卷 7 期

页码：

收录情况： SCI

摘要： The spectrophotometer method is costly, time-consuming, laborious, and destructive to the plant. Samples will be lost during the transportation process, and the method can only obtain sample point data. This poses a challenge to the estimation of chlorophyll content at the regional level. In this study, in order to improve the estimation accuracy, a new method of collaborative inversion of chlorophyll using Landsat 8 and Global Ecosystem Dynamics Investigation (GEDI) is proposed. Specifically, the chlorophyll content data set is combined with the preprocessed two remote-sensing (RS) factors to construct three regression models using a support vector machine (SVM), BP neural network (BP) and random forest (RF), and the better model is selected for inversion. In addition, the ordinary Kriging (OK) method is used to interpolate the GEDI point attribute data into the surface attribute data for modeling. The results showed the following: (1) The chlorophyll model of a single plant was y = 0.1373x(1.7654). (2) The optimal semi-variance function models of pai, pgap_theta and pgap_theta_a3 are exponential models. (3) The top three correlations between the two RS data and the chlorophyll content were B2_3_SM, B2_3_HO, B2_5_EN and pai, pgap_theta, pgap_theta_a3. (4) The combination of the Landsat 8 imagery and GEDI resulted in the highest modeling accuracy, and RF had the best performance, with R-2, RMSE and P values of 0.94, 0.18 g/m(2) and 83.32%, respectively. This study shows that it is reliable to use Landsat 8 images and GEDI to retrieve the chlorophyll content of Dendrocalamus giganteus (D. giganteus), revealing the potential of multi-source RS data in the inversion of forest ecological parameters.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序