Machine learning in tea industry: data-driven approaches for quality and sustainability
Beverage Plant Research · 2025 · 5 (1) · 0-0
DOI: 10.48130/bpr-0025-0016 ↗Kurz gefasst
Fachartikel in der Zeitschrift Beverage Plant Research, 2025. Verfasst von Fuquan Gao und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 144 Literaturangaben.
Abstract (Originalsprache)
Tea holds significant cultural, economic, and nutritional value globally, yet the industry faces persistent challenges including quality inconsistency, climate change impacts, labor shortages, and inefficient conventional production methods. Machine learning (ML) has emerged as a powerful solution to address these challenges through data-driven decision-making, automation, and resource optimization across the entire production chain. This review systematically examines ML applications throughout tea industry, from cultivation and harvesting to processing and quality assessment. We analyze the development of comprehensive ML pipelines encompassing data acquisition, feature engineering, model development, optimization, evaluation, and deployment. Key technological advancements include automated monitoring systems for enhanced productivity, non-destructive spectroscopic and imaging techniques for improved quality assessment, and precision resource management for sustainable production. Despite its transformative potential, widespread ML adoption faces implementation barriers, including limited data availability, scalability issues, and integration with established practices. To overcome these barriers, we highlight strategic approaches such as advanced preprocessing techniques and domain-specific feature engineering to mitigate data limitations, resource-efficient ML architectures tailored for constrained environments, and user-centered interfaces that effectively bridge computational insights with traditional expertise. By synthesizing theoretical frameworks with practical implementation strategies, this review provides researchers, industry stakeholders, and practitioners with essential knowledge to advance sustainable and efficient tea industry through targeted ML integration.
Zitieren
APA
Gao, F., Wang, S., & Yu, X. (2025). Machine learning in tea industry: data-driven approaches for quality and sustainability. Beverage Plant Research, 5(1), 0-0. https://doi.org/10.48130/bpr-0025-0016
Vancouver
Gao F, Wang S, Yu X. Machine learning in tea industry: data-driven approaches for quality and sustainability. Beverage Plant Research. 2025;5(1):0-0. doi:10.48130/bpr-0025-0016
BibTeX
@article{Gao2025,
author = {Gao, Fuquan and Wang, Shuyan and Yu, Xiaomin},
title = {Machine learning in tea industry: data-driven approaches for quality and sustainability},
journal = {Beverage Plant Research},
year = {2025},
volume = {5},
number = {1},
pages = {0--0},
doi = {10.48130/bpr-0025-0016}
}
EUVIMED