Ellen Kuhl

Eating less meat is associated with a healthier body and planet. Yet, we remain reluctant to switch to a plant-based diet, largely due to the sensory experience of plant-based meat. Our lab integrates mechanical tension, compression, and shear tests with constitutive neural networks to automatically characterize the mechanical signature of plant-based and animal meat. We discover the best models and material parameters for various types of plant-based meat to explore to which extent they succeed in mimicking the behavior of their animal counterparts. For example, we found that the more processed the product–with more additives and ingredients– the more complex the mechanical behavior. Interestingly, animal products generally tend to be stiffer in tension than in compression, while plant-based products tend to behave the opposite way. Our results suggest that probing the mechanics of plant-based and animal meats is critical to understand subtle differences in texture that may result in a different perception of taste. We anticipate that our automated model discovery is a first step towards using generative artificial intelligence to scientifically reverse-engineer formulas for plant-based meat products with customer-friendly tunable properties.