Research of the content of nutrient elements caused by anthracnose to Camellia oleifera using LIBS technology

• Published in: Applied physics. B, Lasers and optics Lasers and optics, 2022, Vol.128 (1), Article 6
• Main Authors: Gao, Xue, Liu, Yande, Wang, Qiu, Li, Bin, Jiang, Xiaogang
• Format: Article
• Language: English
• Subjects: Anthrax; Applied physics; Artificial neural networks; Back propagation networks; Copper; Discriminant analysis; Engineering; Industrial development; Laser induced breakdown spectroscopy; Lasers; Manganese; Optical Devices; Optics; Photonics; Physical Chemistry; Physics; Physics and Astronomy; Quantitative analysis; Quantum Optics; Support vector machines
• ISSN: 0946-2171; 1432-0649
• DOI: 10.1007/s00340-021-07726-2

The anthracnose is a highly destructive disease in the Camellia oleifera industry, severely restricting the development of the Camellia oleifera industry. In this paper, the correlation between the content of nutrient elements and the health status of Camellia oleifera leaves was explored. Laser-induced breakdown spectroscopy (LIBS) technology was used to detect the changes of nutrient elements in Camellia oleifera to realize rapid and effective early detection of anthracnose. By comparing and observing the LIBS spectrum of healthy and infected leaves with different degrees of anthrax, we could find that the characteristic peak intensity of Fe, Mn, Cu, Zn, Ca, and Mg will be reduced to a certain extent with the aggravation of anthracnose. The external standard method, partial least square (PLS), and backpropagation artificial neural network (BP-ANN) were used to establish the quantitative detection model of nutrient content. Support vector machine (SVM) was used to establish the discriminant analysis model of Camellia oleifera anthracnose leaves. The experimental results showed that the quantitative analysis performance of the BP-ANN model was better than that of the external standard method and PLS method, and it could accurately predict the concentration of nutrient elements in Camellia oleifera leaves. The LIBS technology combined with the SVM model can be used to realize the discriminant analysis of Camellia oleifera anthracnose. The results showed that the early detection of anthracnose of Camellia oleifera could be realized based on LIBS technology.