A new version of this entry is available:
Loading...
Article
2022
Maize characteristics estimation and classification by spectral data under two soil phosphorus levels
Maize characteristics estimation and classification by spectral data under two soil phosphorus levels
Abstract (English)
As an essential element, the effect of Phosphorus (P) on plant growth is very significant. In the early growth stage of maize, it has a high sensitivity to the deficiency of phosphorus. The main purpose of this paper is to monitor the maize status under two phosphorus levels in soil by a nondestructive testing method and identify different phosphorus treatments by spectral data. Here, the Analytical Spectral Devices (ASD) spectrometer was used to obtain canopy spectral data of 30 maize inbred lines in two P-level fields, whose reflectance differences were compared and the sensitive bands of P were discovered. Leaf Area Index (LAI) and yield under two P levels were quantitatively analyzed, and the responses of different varieties to P content in soil were observed. In addition, the correlations between 13 vegetation indexes and eight phenotypic parameters were compared under two P levels so as to find out the best vegetation index for maize characteristics estimation. A Back Propagation (BP) neural network was used to evaluate leaf area index and yield, and the corresponding prediction model was established. In order to classify different P levels of soil, the method of support vector machine (SVM) was applied. The results showed that the sensitive bands of P for maize canopy included 763 nm, 815 nm, and 900–1000 nm. P-stress had a significant effect on LAI and yield of most varieties, whose reduction rate reached 41% as a whole. In addition, it was found that the correlations between vegetation indexes and phenotypic parameters were weakened under low-P level. The regression coefficients of 0.75 and 0.5 for the prediction models of LAI and yield were found by combining the spectral data under two P levels. For the P-level identification in soil, the classification accuracy could reach above 86%. These abilities potentially allow for phenotypic parameters prediction of maize plants by spectral data and different phosphorus contents identification with unknown phosphorus fertilizer status.
File is subject to an embargo until
This is a correction to:
A correction to this entry is available:
This is a new version of:
Notes
Publication license
Publication series
Published in
Remote sensing, 14 (2022), 3, 493.
https://doi.org/10.3390/rs14030493.
ISSN: 2072-4292
Faculty
Institute
Examination date
Supervisor
Edition / version
Citation
DOI
ISSN
ISBN
Language
English
Publisher
Publisher place
Classification (DDC)
630 Agriculture
Collections
Original object
Free keywords
Standardized keywords (GND)
Sustainable Development Goals
BibTeX
@article{Qiao2022,
url = {https://hohpublica.uni-hohenheim.de/handle/123456789/16842},
doi = {10.3390/rs14030493},
author = {Qiao, Baiyu and He, Xiongkui and Liu, Yajia et al.},
title = {Maize Characteristics Estimation and Classification by Spectral Data under Two Soil Phosphorus Levels},
journal = {Remote sensing},
year = {2022},
}