AI models for predicting and extending product shelf life

Overview

• Industry-academic collaboration opportunity in food product innovation
• Focus on transforming shelf-life determination through AI/machine learning models
• Potential to significantly reduce time, labor, and costs associated with traditional stability testing
• Opportunity to improve innovation timelines and market success of food products

Priority Areas

• Predictive Models: Machine learning models trained on degradation and stability datasets
• Simulation Tools: Systems combining formulation data and packaging specifications
• Degradation Modeling: Tools for predicting oxidation, vitamin loss, and moisture migration
• Sensory Stability: Models predicting flavor and aroma stability over time

Eligibility & Requirements

Must Have:

• Ability to predict product shelf life based on formulation and processing data
• Capacity to recommend formulation adjustments that may improve shelf life
• Potential to reduce reliance on repeated stability testing through virtual modeling approaches

Nice to Have:

• Simulation of key degradation pathways (oxidation, vitamin loss, microbial growth)
• Integration of packaging barrier data into shelf-life prediction models
• End-to-end modeling across formulation, processing, packaging, and storage conditions
• Accounting for variability in supply chain conditions (temperature spikes, humidity fluctuations)

Please note: Full RFP is attached in the "More Information" section of this page. Faculty and researchers interested in applying for these opportunities based on technologies developed or disclosed at Vanderbilt must submit their proposals through the CTTC.