Artificial Intelligence and the Generative Science of Food Formulation

Abstract

Food formulation requires balancing taste, nutrition, sustainability, and cost. Traditionally, new foods have emerged through empirical experimentation, expert intuition, and iterative refinement. Now, artificial intelligence offers the opportunity to accelerate this process. Yet despite rapid advances across food science, most AI applications remain isolated prediction and optimization tasks rather than parts of a broader scientific approach. Here we integrate these emerging technologies into a unified framework--the generative science of food formulation--in which digital food representations enable artificial intelligence to predict, discover, generate, organize, simulate, and optimize. We illustrate this approach through sustainability and nutrition, where generative artificial intelligence transforms environmental and nutritional metrics from post hoc evaluation criteria into explicit design objectives. Finally, we identify the data, models, benchmarks, and automation that will establish computational food design as a rigorous scientific discipline. Together, these advances have the potential to transform food formulation from an empirical discipline into a generative science.

20 pages, 5 figures, 1 table