Mechanization is the inevitable future of tea harvesting, but its impact on tea chemistry and quality remains uncertain. Our study examines untargeted metabolomic data from 185 oolong tea products (Tieguanyin) made from leaves harvested by hand or machine based on UPLC-QToF-MS analysis. The data revealed a minimum 50% loss for over half of the chemicals in the machine-harvested group, including catechins, theaflavin, gallic acid, chlorogenic acid, and kaempferol-3-gluocside. Integrating sensory evaluation, OPLS-DA identified the six most important metabolites as significant contributors to sensory decline caused by harvesting mechanization. Furthermore, our research validates the possibility of using DD-SIMCA modelling with untargeted metabolomic data for distinguishing handpicked from machine-harvested tea products. The model was able to achieve 93% accuracy. This study provides crucial insights into the chemical and sensory shifts during mechanization, along with tools to manage and monitor these changes.

The impact of seasonality on the aroma quality of tea has been documented in various tea types, but not specifically in oolong tea. This study is the first to explore the complex relationships between seasonality, volatile compounds, and aroma quality in oolong tea. Using Headspace Solid-Phase Microextraction Gas Chromatography–Mass Spectrometry (HS-SPME-GC-MS)-based untargeted metabolomics, we analyzed 266 samples of Tieguanyin oolong tea. The data identified linalool, linalool oxides (trans-linalool oxide (furanoid) and trans-linalool oxide (pyranoid)), and their metabolites (diendiol I; hotrienol) as key seasonal discriminants. Four out of the top ten key differential compounds for distinguishing aroma scores were metabolites from fatty acid degradation, namely trans-3-hexenyl butyrate, trans-2-hexenyl hexanoate, hexyl hexanoate, and hexyl 2-methyl butyrate. Approximately one-fifth of the seasonal discriminant volatile compounds were significant in influencing aroma quality. Overall, the impact of seasonality on the aroma quality of finished Tieguanyin oolong tea is marginal. These findings enhance our understanding of the interplay between seasonal variations, volatile composition, and aroma quality in oolong tea.

Existing reviews on AI in tea production are either agriculture-generic or limited to isolated tasks. This review thoroughly compares vision technologies (RGB, hyperspectral, near-infrared, thermal, Light Detection and Ranging (LiDAR), Unmanned Aerial Vehicle (UAV)) and establishes a task-oriented algorithm selection framework for the tea industry. For small-sample or near-linear problems, traditional machine learning (ML) (support vector machine (SVM); partial least squares regression (PLSR)) remains effective. For unstructured field tasks, deep learning achieves superior performance: pest detection accuracy exceeds 97%, tea bud detection reaches 96.8% with RGB images, and hyperspectral imaging predicts nitrogen content with R² > 0.90 and tea polyphenols with R² up to 0.925. Algorithm choice further differentiates by task granularity: lightweight convolutional neural networks (CNNs) balance speed and accuracy for edge deployment at 16 fps; You Only Look Once (YOLO) series detectors enable real-time localization on mobile platforms at 93.1% accuracy, 24 ms per target. No single algorithm dominates all tea tasks; selection is a trade-off among accuracy, speed, data availability, and computational constraints. These findings outline a structured analysis of the challenges and pathways for transitioning computer vision (CV) from laboratory research toward field-deployable tools.

Authenticating specialty tea products remains a critical challenge in premium food markets, yet current analytical approaches are constrained by limited reproducibility and susceptibility to instrumental variation. Here, we present a deep learning framework that transforms liquid chromatography–mass spectrometry (LC–MS) metabolomic data into image representations, enabling robust authentication of tea products under real-world analytical conditions. Profiling 274 Tieguanyin tea samples across seasonal harvests (spring and autumn) and processing methods (light-scented and strong-scented), our approach achieved 90.9% (95% confidence interval [CI]: 80.4%–96.0%) classification accuracy—substantially outperforming conventional multivariate and machine learning methods (sPLS-DA: 85.5%; random forest: 87.3%). Critically, when subjected to chromatographic drift—a pervasive source of analytical irreproducibility—our model maintained 78.2% accuracy while traditional methods degraded to 69.1%. This framework addresses fundamental limitations in untargeted metabolomics, offering a generalizable solution for food authentication that extends beyond tea to broader applications in agricultural product verification and systems biology.