ABSTRACT
Aging is a time-consuming step in the manufacturing of fermented alcoholic beverages. Natural-aging huangjiu sealed in pottery jars was taken as an example to investigate the changes of physiochemical indexes during aging and to quantify intercorrelations between aging-related factors and metabolites through machine learning methods. Machine learning models provided significant predictions for 86% of metabolites. Physiochemical indexes well reflected the metabolic profile, and total acid was the most important index that needed to be controlled. For aging-related factors, several aging biomarkers of huangjiu were also well predicted. Feature attribution analysis showed aging year was the most powerful predictive factor, and several microbial species were significantly associated with aging biomarkers. Some of the correlations, mostly connected to environmental microorganisms, were newly found, showing considerable microbial influence on aging. Overall, our results reveal the potential determinants that affect the metabolic profile of aged huangjiu, paving the way for a systematical understanding of changes in metabolites of fermented alcoholic beverages.
ABSTRACT
Traditional fermented alcoholic beverages (TFABs) have gained widespread acceptance and enjoyed great popularity for centuries. COVID-19 pandemics lead to the surge in health demand for diet, thus TFABs once again attract increased focus for the health benefits. Though the production technology is quite mature, food companies and research institutions are looking for transformative innovation in TFABs to make healthy, nutritious offerings that give a competitive advantage in current beverage market. The implementation of intelligent platforms enables companies and researchers to gather, store and analyze data in a more convenient way. The development of data collection methods contributed to the big data environment of TFABs, providing a fresh perspective that helps brewers to observe and improve the production steps. Among data analytical tools, Artificial Intelligence (AI) is considered to be one of the most promising methodological approaches for big data analytics and decision-making of automated production, and machine learning (ML) is an important method to fulfill the goal. This review describes the development trends and challenges of TFABs in big data era and summarize the application of AI-based methods in TFABs. Finally, we provide perspectives on the potential research directions of new frontiers in application of AI approaches in the supply chain of TFABs.