Bioscience Evidence 2026, Vol.16, No.4, 235-248 http://bioscipublisher.com/index.php/be 244 Figure 4 Process flow diagrams for four tea samples. CK: samples made with traditional white tea processing techniques; YB: sample made by adding shaking to the traditional white tea process; YRB: sample made by adding shaking and rolling in the traditional white tea processing; YLRB: sample made by adding shaking, rolling, and freezing to the traditional white tea process (Adopted from Wu et al., 2025) 6 Future Directions for Season-Based Tea Production 6.1 Precision seasonal harvest management Future tea production will place greater emphasis on the precise use of fresh leaves from different seasons rather than only improving harvesting efficiency. For a long time, tea garden harvesting has mainly depended on growers' experience in judging bud emergence and harvest dates. However, with climate change and rising labor costs, experience-based management alone can no longer fully meet the needs of high-quality tea production. Tea garden management will gradually become more digital and precise. Bud emergence, fresh leaf yield, and optimal harvesting windows will be predicted according to the growth characteristics of tea plants in spring, summer, and autumn, thereby improving the annual utilization efficiency of fresh leaves. Technologies such as unmanned aerial vehicle remote sensing, satellite imagery, machine vision, and artificial intelligence are gradually being applied in tea production. UAV remote sensing combined with machine-learning models can predict spring, summer, autumn, and annual fresh leaf yields with relatively high accuracy. This provides useful information for harvesting plans, processing capacity allocation, and labor arrangements (Liu et al., 2025). Machine-vision systems can also identify the positions of tea buds automatically, allowing pre-harvest yield estimation and post-harvest quality evaluation. These systems provide technical support for precision harvesting. Junagade et al. (2024) showed that UAVs combined with deep-learning technology could identify different seasonal flushes of new shoots, providing a new method for batch harvesting and harvest scheduling.
RkJQdWJsaXNoZXIy MjQ4ODYzNA==