A machine learning-guided modeling approach to the kinetics of α-tocopherol and myricetin synergism in bulk oil oxidation

Date

2024-09-01

Author

Parra-Escudero, Carlos
Bayram, İpek
Decker, Eric A.
Singh, Shyamyanshikumar
Corvalan, Carlos
Lu, Jiakai

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

27
views

0
downloads

Cite This

The shelf-life and quality of food products depend heavily on antioxidants, which protect lipids from free radical degradation. α-Tocopherol and myricetin, two potent antioxidants, synergistically enhance the prevention of oxidative rancidity in bulk oil systems. Understanding their degradation kinetics is essential for deepening our knowledge of their mechanisms and developing strategies to predict shelf-life before expiration. This paper introduces a generalized mathematical model to describe the degradation kinetics of α-tocopherol in the presence of myricetin. Using direct differential methods guided by a machine learning approach based on neural differential equations, we uncover two distinct phases of α-tocopherol degradation when coexisting with myricetin at varying concentration ratios. These findings inform the development of a mixed Weibull model that accurately captures the degradation process. Our study enhances the understanding of antioxidant interactions and provides a reliable method for predicting food system stability, offering valuable insights for optimizing natural antioxidants in food preservation.

URI

https://hdl.handle.net/11511/112074

Collections

Department of Food Engineering, Article