跳到主要导航 跳到搜索 跳到主要内容

Multi-dimensional variables and feature parameter selection for aboveground biomass estimation of potato based on UAV multispectral imagery

  • Shanjun Luo
  • , Xueqin Jiang
  • , Yingbin He*
  • , Jianping Li*
  • , Weihua Jiao
  • , Shengli Zhang
  • , Fei Xu
  • , Zhongcai Han
  • , Jing Sun
  • , Jinpeng Yang
  • , Xiangyi Wang
  • , Xintian Ma
  • , Zeru Lin
  • *此作品的通讯作者
  • Chinese Academy of Agricultural Sciences
  • Nanjing University of Information Science & Technology
  • Shandong University of Finance & Economics
  • Jilin Acad Vegetables & Flower Sci
  • Tiangong University

科研成果: 期刊稿件 › 论文 › 同行评审

49 引用 (Scopus)

摘要

Aboveground biomass (AGB) is an essential assessment of plant development and guiding agricultural production management in the field. Therefore, efficient and accurate access to crop AGB information can provide a timely and precise yield estimation, which is strong evidence for securing food supply and trade. In this study, the spectral, texture, geometric, and frequency-domain variables were extracted through multispectral imagery of drones, and each variable importance for different dimensional parameter combinations was computed by three feature parameter selection methods. The selected variables from the different combinations were used to perform potato AGB estimation. The results showed that compared with no feature parameter selection, the accuracy and robustness of the AGB prediction models were significantly improved after parameter selection. The random forest based on out-of-bag (RF-OOB) method was proved to be the most effective feature selection method, and in combination with RF regression, the coefficient of determination (R-2) of the AGB validation model could reach 0.90, with root mean square error (RMSE), mean absolute error (MAE), and normalized RMSE (nRMSE) of 71.68 g/m(2), 51.27 g/m(2), and 11.56%, respectively. Meanwhile, the regression models of the RF-OOB method provided a good solution to the problem that high AGB values were underestimated with the variables of four dimensions. Moreover, the precision of AGB estimates was improved as the dimensionality of parameters increased. This present work can contribute to a rapid, efficient, and non-destructive means of obtaining AGB information for crops as well as provide technical support for high-throughput plant phenotypes screening.
源语言英语
期刊论文编号948249
页数13
期刊FRONTIERS IN PLANT SCIENCE
卷13
DOI
出版状态已出版 - 29 7月 2022

基金资助

This work was supported by the National Natural Science Foundation of China`s "Study on temporally and spatially precise assessment on potato cultivation suitability based on dynamic process-oriented mode" (41771562) and "Innovation Project" of the Chinese Academy of Agricultural Sciences (20212025, IARRP).

联合国可持续发展目标

此成果有助于实现下列可持续发展目标:

  1. 可持续发展目标 2 - 零饥饿
    可持续发展目标 2 零饥饿

关键词

  • remote sensing phenotypes
  • spectral indices
  • texture
  • geometric parameters
  • frequency-domain indicators
  • variables preference

收录

  • SCIE
  • Scopus

学术指纹

探究 'Multi-dimensional variables and feature parameter selection for aboveground biomass estimation of potato based on UAV multispectral imagery' 的科研主题。它们共同构成独一无二的学术指纹。

引用此