AUTHOR=Li Junmeng , Ren Jie , Cui Ruiyan , Yu Keqiang , Zhao Yanru 

TITLE=Optical imaging spectroscopy coupled with machine learning for detecting heavy metal of plants: A review

JOURNAL=Frontiers in Plant Science

VOLUME=Volume 13 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/plant-science/articles/10.3389/fpls.2022.1007991

DOI=10.3389/fpls.2022.1007991

ISSN=1664-462X

ABSTRACT=Heavy metals destroy the internal structure of plants and affect the growth, development, and metabolism of plants, even threatening the health of humans and animals by the food chain. Excessive heavy metals affect the phenotypic information changes of plants, resulting in root branching, root tip number reduction, leaves wilting, and seed germination rate reduction. Therefore, finding advanced methods to characterize the phenotypic information of plants under heavy metals stress is a significant problem for precision agriculture management and breeding. As an efficient, accurate, sensitive, and reliable method, spectral analysis has broad application in plant growth monitoring, pest and disease detection, and heavy metal phenotype detection. This paper briefly introduces the principles and characteristics of some spectral techniques and their applications in detecting heavy metals in the roots, stems, leaves, and fruits of plants. Moreover, this review critically discusses the advantages and limitations of these spectral techniques and the prospects of their application in heavy metal stress detection.