Applications of deep learning in tea quality monitoring: a review

Abstract Tea is a popular beverage which can offer numerous benefits to human health and support the local economy. There is an increasing demand for accurate and rapid tea quality evaluation methods to ensure that the quality and safety of tea products meet the customers’ expectations. Advanced sensing technologies in combination with deep learning (DL) offer significant opportunities to enhance the efficiency and accuracy for tea quality evaluation. This review aims to summarize the application of DL technologies for tea quality assessment in three stages: cultivation, tea processing, and product evaluation. Various state-of-the-art sensing technologies (e.g., computer vision, spectroscopy, electronic nose and tongue) have been used to collect key data (images, spectral signals, aroma profiles) from tea samples. By utilizing DL models, researchers are able to analyze a wide range of tea quality attributes, including tea variety, geographical origin, quality grade, fermentation stage, adulteration level, and chemical composition. The findings from this review indicate that DL, with its end-to-end analytical capability and strong generalization performance, can serve as a powerful tool to support various sensing technologies for accurate tea quality detection. However, several challenges remain, such as limited sample availability for data training, difficulties for fusing data from multiple sources, and lack of interpretability of DL models. To this end, this review proposes potential solutions and future studies to address these issues, providing practical considerations for tea industry to effectively uptake new technologies and to support the development of the tea industry.