Improving the detection accuracy of the nitrogen content of fresh tea leaves by combining FT-NIR with moisture removal method. (30th March 2023)

• Record Type: Journal Article
• Authors: Guo, Jiaming; Huang, Han; He, Xiaolong; Cai, Jinwei; Zeng, Zhixiong; Ma, Chengying; Lü, Enli; Shen, Qunyu; Liu, Yanhua
• Is Part Of: Food chemistry. Volume 405:Part A(2023)
• Publication Date: 2023-03-30
• Subjects: Yinghong NO. 9 black tea -- NIR spectroscopy -- External parameter orthogonalization -- Variables selection; Food -- Analysis -- Periodicals; Food -- Composition -- Periodicals; 664
• DOI: 10.1016/j.foodchem.2022.134905
• Languages: English
• ISSNs: 0308-8146

Abstract

Graphical abstract: Highlights: The reason of moisture on the spectral information of fresh tea leaves was revealed. Applied spectral transformation methods to eliminate the effect of moisture on spectra. EPO-PLS performs better than raw spectral in predicting the nitrogen content of tea. VCPA-IRIV selects informative wavelength improved EPO-PLS performance. Abstract: The nitrogen content (NC) is one of the critical indicators of tea quality, and many studies have been conducted using NIR spectroscopy to determine tea constituents. However, this method has been found to have limited accuracy for component estimation because the spectra are affected by moisture in the samples. In this study, external parameter orthogonalization (EPO) was introduced to filter out the effect of moisture in fresh tea leaves on NIR spectra. Then, a feature selection algorithm was applied to determine the optimal NC wavelength to improve the prediction precision. Finally, a partial least squares (PLS) prediction model was established. The PLS model based on EPO and VCPA-IRIV achieved satisfactory prediction results, with an increase in Rp 2 to 0.9371 from 0.5846 for the full spectral PLS model without treatment. Overall, this study found that eliminating the effect of moisture on spectra could improve detection accuracy of the model significantly.