Aiming at the problems of insufficient detection accuracy and high false detection rates of traditional pest detection models in the face of small targets and incomplete targets, this study proposes an improved target detection network, I-YOLOv10-SC. The network leverages Space-to-Depth Convolution to enhance its capability in detecting small insect targets. The Convolutional Block Attention Module is employed to improve feature representation and attention focus. Additionally, Shape Weights and Scale Adjustment Factors are introduced to optimize the loss function. The experimental results show that compared with the original YOLOv10, the model generated by the improved algorithm improves the accuracy by 5.88 percentage points, the recall rate by 6.67 percentage points, the balance score by 6.27 percentage points, the mAP value by 4.26 percentage points, the bounding box loss by 18.75%, the classification loss by 27.27%, and the feature point loss by 8%. The model oscillation has also been significantly improved. The enhanced I-YOLOv10-SC network effectively addresses the challenges of detecting small and incomplete insect targets in tea plantations, offering high precision and recall rates, thus providing a solid technical foundation for intelligent pest monitoring and precise prevention in smart tea gardens.

To investigate the flavour evolution mechanism of raw Pu-erh tea (RPT) during storage, the volatile and non-volatile compounds of RPT with different storage years (1–10 years) from the same raw material origin, manufacturer, and storage location in Wenshan Prefecture, Yunnan Province, were systematically analysed by HPLC, HS-SPME-GC-MS, and OAV. The results showed that both cluster analyses based on non-volatile and volatile compounds could classify RPT of different storage years into three ageing cycles, with key turning points in the third and eighth years of storage, which is also accompanied by the colour changing from green to orange or brown, the aroma changing from a faint scent to woody and ageing, the astringency diminishing, and the sweet and mellow increasing. Theophylline was identified as the potential marker of RPT stored 1–3 years, while (−)-catechin gallate, (−)-gallocatechin gallate, quercetin, and rutin as those for a storage of 9–10 years. The volatile compounds indicate a general trend of an initial increase followed by a decrease. Forty-four key aroma compounds (OAV ≥ 1) were identified. Eucalyptol, β-Caryophyllene, 2-Amylfuran, Copaene, Estragole, and α-Terpinene originated as potential markers for RPT stored 1–3 years, while (Z)-Linalool oxide (furanoid), α-Terpineol, Terpinen-4-ol, and cis-Anethol were for RPT stored 8–10 years. This study revealed the flavour characteristics and quality changes of RPT over the course of storage, and constructed a sensory flavour wheel, providing theoretical underpinnings for the quality control and assessment of RPT.

To explore the effects of different withering methods on the quality of Congou black tea, this study focused on five different withering methods: natural withering, warm-air withering, sun–natural combined withering, sun withering, and shaking withering. Gas chromatography‒mass spectrometry (GC‒MS), high-performance liquid chromatography (HPLC), and ion-exchange chromatography techniques were used to analyze the nonvolatile and volatile components and composition of the tea. The results revealed significant differences (p < 0.05) in the contents of nonvolatile constituents including caffeine, polyphenols, soluble sugars, free amino acids and their components, theaflavins, thearubigins, and catechins among the five different withering methods, with varying degrees of correlation between these components. A total of 227 aroma compounds were detected, and significant differences in the contents of alcohols, aldehydes, and ketones were observed. A relative odor activity value (ROVA) analysis of the aroma compounds revealed that 19 compounds had an ROVA > 1. Among them, benzylaldehyde, trans-2-decenal, decanal, benzaldehyde, nonanal, hexanal, trans-linalool, and geraniol from the shaking withering method had significantly higher ROVA values than those from the other withering methods, which may be the reason for the prominent floral and fruity aroma of shaking withering. This study revealed the impact of different withering methods on the quality of Congou black tea, providing a scientific basis for the development of Congou black tea with different flavors and the improvement of Congou black tea processing techniques.

To investigate the variation in flavonoids content in ancient tree sun–dried green tea under abiotic stress environmental conditions, this study determined the flavonoids content in ancient tree sun−dried green tea and analyzed its correlation with corresponding factors such as the age, height, altitude, and soil composition of the tree. This study uses two machine−learning models, Least Absolute Shrinkage and Selection Operator (LASSO) regression and Cox regression, to build a predictive model based on the selection of effective variables. During the process, bootstrap was used to expand the dataset for single−factor and multi−factor comparative analyses, as well as for model validation, and the goodness−of−fit was assessed using the Akaike information criterion (AIC). The results showed that pH, total potassium, nitrate nitrogen, available phosphorus, hydrolytic nitrogen, and ammonium nitrogen have a high accuracy in predicting the flavonoids content of this model and have a synergistic effect on the production of flavonoids in the ancient tree tea. In this prediction model, when the flavonoids content was >6‰, the area under the curve of the training set and validation set were 0.8121 and 0.792 and, when the flavonoids content was >9‰, the area under the curve of the training set and validation set were 0.877 and 0.889, demonstrating good consistency. Compared to modeling with all significantly correlated factors (p < 0.05), the AIC decreased by 32.534%. Simultaneously, a visualization system for predicting flavonoids content in ancient tree sun−dried green tea was developed based on a nomogram model. The model was externally validated using actual measurement data and achieved an accuracy rate of 83.33%. Therefore, this study offers a scientific theoretical foundation for explaining the forecast and interference of the quality of ancient tree sun−dried green tea under abiotic stress.