Potential of spectroscopic analyses for non-destructive estimation of tea quality-related metabolites in fresh new leaves

Abstract

Spectroscopic sensing provides physical and chemical information in a non-destructive and rapid manner. To develop non-destructive estimation methods of tea quality-related metabolites in fresh leaves, we estimated the contents of free amino acids, catechins, and caffeine in fresh tea leaves using visible to short-wave infrared hyperspectral reflectance data and machine learning algorithms. We acquired these data from approximately 200 new leaves with various status and then constructed the regression model in the combination of six spectral patterns with pre-processing and five algorithms. In most phenotypes, the combination of de-trending pre-processing and Cubist algorithms was robustly selected as the best combination in each round over 100 repetitions that were evaluated based on the ratio of performance to deviation (RPD) values. The mean RPD values were ranged from 1.1 to 2.7 and most of them were above the acceptable or accurate threshold (RPD = 1.4 or 2.0, respectively). Data-based sensitivity analysis identified the important hyperspectral regions around 1500 and 2000 nm. Present spectroscopic approaches indicate that most tea quality-related metabolites can be estimated non-destructively, and pre-processing techniques help to improve its accuracy.

Spectroscopic assessment of flavor-related chemical compounds in fresh tea shoots using deep learning

“…We employed the two-stage training approach to determine whether the additional training stage would enhance model performance by referring to metrics losses. Furthermore, we also selected an advanced multivariate statistical (PLS) approach [31] and other commonly used machine-/deep-learning methods, including cubist [32] with de-trend pre-processing [6],…”

“…Plant metabolism collectively produces many metabolites, crucial in resisting biotic stress and adapting to abiotic pressure. These metabolites also serve as invaluable resources for human health and survival [1][2][3][4][5][6]. Tea plants are predominantly cultivated in Asia, producing some of the most popular non-alcoholic beverages in the world [7,8].…”

“…However, these linear models may not be suitable for the prediction due to the complex nature of TFCC. Yamashita et al [6] uses machine learning, including random forests (RF) and cubist, to analyze leaf reflectance and quantify TFCC in fresh tea shoots. However, information may be lost solely relying on leaf reflectance during optimization.…”

A Combination of Near-Infrared Hyperspectral Imaging with Two-Dimensional Correlation Analysis for Monitoring the Content of Alanine in Beef

“…Therefore, the rapid detection requirements in the beef mass production process cannot be met. In previous investigations, the combination of several nondestructive rapid measurement methods and chemometric methods have been applied in the assessment of amino acid content, including visible near–infrared spectroscopy, near–infrared (NIR) spectroscopy, Fourier infrared spectroscopy, and nondestructive magnetic resonance imaging [ 11 , 12 , 13 , 14 ]. However, these studies mainly focused on the evaluation of research objectives concerning soybean, daqu, tea, potato, and ham [ 11 , 12 , 13 , 14 , 15 ], and detection indicators such as amino acid nitrogen [ 12 ], total amino acid [ 15 ], and total volatile basic nitrogen (TVB-N) have been emphatically discussed [ 16 ].…”

“…In previous investigations, the combination of several nondestructive rapid measurement methods and chemometric methods have been applied in the assessment of amino acid content, including visible near–infrared spectroscopy, near–infrared (NIR) spectroscopy, Fourier infrared spectroscopy, and nondestructive magnetic resonance imaging [ 11 , 12 , 13 , 14 ]. However, these studies mainly focused on the evaluation of research objectives concerning soybean, daqu, tea, potato, and ham [ 11 , 12 , 13 , 14 , 15 ], and detection indicators such as amino acid nitrogen [ 12 ], total amino acid [ 15 ], and total volatile basic nitrogen (TVB-N) have been emphatically discussed [ 16 ]. In addition, hyperspectral imaging (HSI) technology is more widely focused in predicting other meat-related quality attributes, especially nutritional attributes (fatty acid, protein, and intramuscular fat), technical attributes (pH and water holding capacity), sensory attributes (tenderness, color, hardness, gumminess, and chewiness), freshness attributes (thiobarbituric acid reactive substances (TBARS), total biogenic amines (TBA), and myoglobin), and microbial attributes (total viable count) of meat in different parts, types, and places of origin [ 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 , 25 ].…”