AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
PDF (5.3 MB)
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Publishing Language: Chinese

Rapid Prediction of Tea Leaf Catechins via Hyperspectral Multi-Task Synergistic Sensing Fusing Plant Physiological Priors

ZhiChao CHAI, XiaoNa QIAN, YongChen YU, XiWang LI, XiaoLing SUN( )
Tea Research Institute, Chinese Academy of Agricultural Sciences/National Center for Tea Plant Improvement/State Key Laboratory of Tea Plant Germplasm Innovation and Resource Utilization, Key Laboratory of Biology/Genetics and Breeding of Special Economic Animals and Plants, Ministry of Agriculture and Rural Affairs, Hangzhou 310008
Show Author Information

Abstract

Objective

To meet the demand for in situ, real-time, and non-destructive monitoring of tea leaf quality in smart teagardens, this study proposed a multi-component quantitative prediction method based on visible-near infrared hyperspectral imaging (400-1000 nm) integrated with plant physiological priors, so as to realize rapid assessment of secondary metabolites, such as catechins.

Method

Twelve tea cultivars were used as experiment materials. Leaves were classed as young (2nd-3rd), mature (4th-5th), and old (6th-7th) to represent physiological gradients, giving 429 independent samples in total. For each leaf, hyperspectral reflectance was recorded, and the contents of catechin (C), epicatechin (EC), epigallocatechin (EGC), epicatechin gallate (ECG), epigallocatechin gallate (EGCG), gallocatechin (GC), gallocatechin gallate (GCG), caffeine (CAF), and gallic acid (GA) were quantified by high-performance liquid chromatography. Spectra were preprocessed using Savitzky-Golay (SG) smoothing, standard normal variate (SNV), and first derivative. The generalization performance of partial least squares regression (PLSR), support vector regression (SVR), XGBoost, multilayer perceptron (MLP), and 1D-CNN-SE was compared. Based on the best single-task model, a multi-task XGBoost framework was then developed to simultaneously predict the nine components. Additionally, the successive projections algorithm (SPA) was used to select key wavelengths from the full spectrum (557 bands) to assess the feasibility of simplified modeling.

Result

When leaf maturity was ignored, EGCG and GCG showed a spurious negative correlation due to confounding by maturity, which was a clear instance of Simpson's paradox. This meant that maturity needed to be accounted for, either by stratifying the data or by explicit adjustment, so that models would not learn false correlations. Among the tested models, XGBoost combined with SG+SNV+first-derivative preprocessing achieved the best performance on the small-sample with high-dimensional spectral dataset. The R2 values for EGCG and GCG were approximately 0.60 and 0.59, respectively. In contrast, 1D-CNN-SE achieved calibration set R2 value above 0.90 but dropped to about 0.40-0.50 on the prediction set, showing clear overfitting. The multi-task XGBoost model predicted all nine components in a single run; the R2 value for EGCG remained about 0.57, and the RPD values for EGCG, GCG, and CAF were about 1.48-1.52, with only a slight loss in single-component accuracy but a substantial gain in throughput. After SPA reduced the full spectrum from 557 bands to 18 key wavelengths, the R2 for EGCG remained about 0.54. These key wavelengths fell mainly in the visible region and the near-infrared overtone absorption bands, supporting the design of portable quality sensors based on discrete wavelengths.

Conclusion

The spectral modeling that integrated physiological priors, such as leaf maturity, could enhance the model’s explanatory power and improve its generalization across cultivars and leaf ages. The single- and multi-task XGBoost frameworks, combined with wavelength selection, provided a theoretical basis and practical support for rapid multi-index tea quality assessment in tea plantations.

References

【1】
【1】
 
 
Scientia Agricultura Sinica
Pages 4149-4162

{{item.num}}

Comments on this article

Go to comment

< Back to all reports

Review Status: {{reviewData.commendedNum}} Commended , {{reviewData.revisionRequiredNum}} Revision Required , {{reviewData.notCommendedNum}} Not Commended Under Peer Review

Review Comment

Close
Close
Cite this article:
CHAI Z, QIAN X, YU Y, et al. Rapid Prediction of Tea Leaf Catechins via Hyperspectral Multi-Task Synergistic Sensing Fusing Plant Physiological Priors. Scientia Agricultura Sinica, 2026, 59(18): 4149-4162. https://doi.org/10.3864/j.issn.0578-1752.2026.18.015

7

Views

0

Downloads

0

Crossref

0

Scopus

0

CSCD

Received: 28 January 2026
Accepted: 28 April 2026
Published: 16 September 2026
© 2026 The Journal of Scientia Agricultura Sinica