South SFV Today

Stanford engineers are exploring a new approach to improve the texture of plant-based meats, potentially making them more appealing to meat lovers. The team has developed a method combining mechanical testing and machine learning to assess food texture, as detailed in their recent paper published in Science of Food.

"We were surprised to find that today’s plant-based products can reproduce the whole texture spectrum of animal meats," said Ellen Kuhl, professor of mechanical engineering and senior author of the study. This innovation could accelerate the development of plant-based alternatives that closely mimic animal meat textures.

The research highlights the environmental benefits of plant-based diets, noting that industrial animal agriculture contributes significantly to climate change and other ecological issues. A previous study cited by the researchers suggests that plant-based meats generally have half the environmental impact compared to traditional animal meats.

Skyler St. Pierre, a PhD student in mechanical engineering and lead author of the paper, emphasized the importance of convincing consumers: "People love meat. If we want to convince hardcore meat eaters that alternatives are worth trying, the closer we can mimic animal meat with plant-based products, the more likely people might be open to trying something new."

Traditional food testing methods lack standardization and transparency, posing challenges for scientific collaboration. To address this, St. Pierre's class project evolved into a comprehensive study involving both animal and plant-based products tested through mechanical means.

Using machine learning algorithms, they processed data from tests on various products including hot dogs and sausages. These tests revealed similarities between some plant-based options and their animal counterparts in terms of texture properties like stiffness.

"What’s really cool is that the ranking of the people was almost identical to the ranking of the machine," Kuhl remarked about human testers' perceptions aligning with mechanical test results.

The findings suggest potential for artificial intelligence (AI) in developing recipes for plant-based meats with desired textures more efficiently than traditional trial-and-error methods. However, AI requires substantial data input; thus, Stanford researchers are making their data publicly available for further innovation.

The team plans ongoing tests on various foods and aims to expand their public database. They also intend to examine engineered fungi as part of future research endeavors.

Additional contributors from Stanford include Marc Levenston, associate professor; postdoctoral researcher Kevin Linka; graduate students Ethan C. Darwin, Divya Adil, Valerie A. Perez Medina; visiting researcher María Parra Vallecillo; undergraduate researchers Magaly C. Aviles, Archer Date, Reese A. Dunne, Yanav Lall.

This project received funding from several organizations including the National Science Foundation and European Research Council.

For further information or media inquiries contact Jill Wu at jillwu@stanford.edu