Advanced Modeling and AI for Food Quality Degradation and Shelf-Life Prediction

The increasing complexity of modern food systems, coupled with globalized supply chains and sustainability pressures, demands integrative, evidence-based data approaches with proven predictive ability to understand, manage, and reduce food quality losses and consequent food waste. Traditional empirical methods used to estimate shelf-life and spoilage are often limited in their ability to capture the nonlinear, multiscale interactions among food structure, composition, environmental conditions, and biological activity that govern quality degradation.Recent advances in data-driven, physics-based and hybrid modeling offer transformative opportunities to integrate heterogeneous datasets, ranging from molecular composition and microstructure to environmental conditions and microbial dynamics, into robust predictive frameworks. These approaches enable improved forecasting of shelf-life, mechanistic understanding of degradation pathways, and optimization of product quality over time. Ultimately, such tools support product innovation, reduction of food waste, improved inventory and cold-chain management, and more consistent consumer experiences.This topic seeks contributions that advance predictive and mechanistic understanding of food quality degradation and shelf-life evolution under realistic storage and distribution conditions. Emphasis is placed on modeling approaches that connect food structure, physicochemical transformations, microbial activity, and environmental variability to quality outcomes, while safety assessment remains an important complementary consideration.Submissions may include, but are not limited to: Predictive modeling of quality degradation and shelf life o Kinetics of physicochemical changes (e.g., oxidation, moisture migration, texture loss)o Structure–function–degradation relationships in complex food matriceso Multiscale modeling driving quality attributeso Digital twins and simulation platforms for shelf-life forecastingo Modeling consumer-perceived quality and acceptability over time Food microstructure, transport phenomena, and degradation mechanisms o Coupling of food structure with moisture, oxygen, and heat transporto Modeling of physical instability and structural collapse during storageo Relationships between microstructure and spoilage progressiono Packaging–product interactions influencing shelf-life Spoilage microorganism community modeling o Predictive microbiology and growth/inactivation modelso AI-driven microbiota assessmentsArtificial intelligence and data-driven approaches o Machine learning, deep learning, and hybrid (mechanistic–ML) modelso Explainable AI for food quality decision-makingo Transfer learning and generalizable models across food systemso Real-time predictive systems integrating sensors and process data Data integration and infrastructure o Fusion of omics, compositional, environmental, and process datao Development of curated databases for model training and validationo Reproducible modeling workflows Applications and case studies o Fresh, minimally processed, and shelf-stable foodso Cold chain management and logistics optimizationo Food waste reduction strategies informed by predictive analytics Topic editors: Maria G. Corradini, Daniel Onwude Source: https://www.frontiersin.org/research-topics/81625/advanced-modeling-and-ai-for-food-quality-degradation-and-shelf-life-prediction