Industrial food quality and consumer choice: Artificial intelligence-based tools in the chemistry of sensory notes in comfort foods (coffee, cocoa and tea)

Background Food quality is a multifaceted, evolving concept encompassing various aspects throughout the production chain. The shift from traditional analytics to comprehensive strategies is driven by the need to meet this extended quality definition. Scope and approach Foodomics, specifically focusing on connecting chemical composition to sensory properties, is vital for comfort foods like coffee, cocoa, and tea, chosen for enjoyment rather than nutrition. In foodomics, larger and more complex datasets demand Artificial intelligence-based tools for decoding encrypted information. Key findings and conclusions Global coffee, cocoa, and tea supply involve numerous small farms affected by socio-political instability and climate change. Financial motives drive fraudulent practices, leading to unfair competition, loss of consumer confidence, and safety issues. AI-based tools enhance data understanding for knowledge gain, but challenges include the misalignment between academia and industry, limited industrial samples for AI application, academic training gaps, algorithm complexity, and decision-making misinterpretation.