Stanford Engineers Develop 3D Texture Tests to Make Plant-Based Meat with “Precisely Desired” Properties

Stanford engineers have developed a new AI model for food texture testing to improve the sensory experience of plant-based meat and encourage wider acceptance. Using mechanical testing and machine learning, they were able to measure and replicate the texture of both plant-based and animal meats, similar to human taste testers. The study found that some plant-based meats already mimic the texture of animal meats well, with plant-based hotdogs and sausages ranking similarly to their animal counterparts.

The researchers discovered that the mechanical properties of plant-based meat depend heavily on the source of the plants and processing technique, with successful combinations featuring wheat, pea, or potato proteins. By sharing their data online and promoting collaboration in the field of plant-based meat development, the team hopes to use generative artificial intelligence to reverse-engineer formulas for plant-based meat products with precisely desired properties. This approach could lead to more appealing vegan alternatives and accelerate the development of plant-based meats that meet consumer expectations.