AUTHOR=Shu Meiyan , Zhou Long , Chen Haochong , Wang Xiqing , Meng Lei , Ma Yuntao 

TITLE=Estimation of amino acid contents in maize leaves based on hyperspectral imaging

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.885794

DOI=10.3389/fpls.2022.885794

ISSN=1664-462X

ABSTRACT=Estimation of the amino acid content in maize leaves is helpful to improve maize yield estimation and nitrogen use efficiency. Hyperspectral imaging can be used to obtain the physiological and biochemical parameters of maize leaves with the advantages of rapid, non-destructive and high throughput. The goal of this study is to estimate various amino acids contents in maize leaves using hyperspectral imaging data. Two nitrogen (N) fertilizer experiments were carried out to obtain the hyperspectral images of fresh maize leaves. The partial least squares regression (PLSR) method was used to build the estimation models of various amino acids contents by using the reflectance of all bands, sensitive band range and characteristic bands. The models were then validated with the independent data set. The results showed that: (1) most amino acids contents decreased with the decrease of N concentration. The asparagine, isoleucine, serine, glutamine and valine were more sensitive to the N treatment than other amino acids; (2) the spectral reflectance of most amino acids was more sensitive in the range of 400-717 nm than other bands. The estimation accuracy was better by using the reflectance of sensitive band range than that of all bands; (3) The characteristic bands of most amino acids were in the range of 505.39-605 nm and 651-714 nm; and (4) among the 24 amino acids, the estimation models of the β-aminobutyric acid, ornithine, citrulline, methionine and histidine achieved higher accuracy than those of other amino acids, with the R2, RE and RPD of the measured and estimated value of testing samples in the range of 0.84-0.96, 8.79 % -20.2 %, and 2.52-5.16, respectively. This study can provide a non-destructive and rapid diagnosis method for genetic characteristic analysis and variety improvement of maize.