Leveraging multi-omics and machine learning approaches in malting barley research: From farm cultivation to the final products

Abstract

This study focuses on the potential of multi-omics and machine learning approaches in improving our understanding of the malting processes and cultivation systems in barley. The omics approach has been used to explore biomarkers associated with desired sensory characteristics in malting barley, enabling potential applications in specific treatments to modify diastatic power, enzyme activity, color, and aroma compounds. Moreover, the integration of machine learning and multi-omics in malting barley researches has significantly enhanced our knowledge in physiology, cultivation, and processing for more efficient and sustainable production systems in malting barley industry. The integration of cutting-edge machine vision and high-throughput phenotyping technologies has additionally the potential to revolutionize the assessment of physical and biochemical traits in malting barley. In addition, the harnessing of integrative approach to predict consumer acceptability, and assess physicochemical and colorimetric properties of malt extracts has been discussed. Current survey showed that the ML-driven predictive maintenance is revolutionizing the barley malting industry by not only enhancing equipment performance but also minimizing operational costs and reducing unplanned downtime. This knowledge not only promises advancements but also opens avenues for future researches in malting barley industry.

Keywords

• Phenotyping
• Multi-omics
• Machine learning
• Predictive maintenance
• Malting
• Process