Nestlé and IBM use deep tech and AI to unleash new packaging

IBM Research and Nestlé R&D are collaborating to create a generative AI tool that can recognise new high-barrier packaging materials.

Nestlé and IBM scientists leveraged AI-based processing techniques to construct a knowledge base of known materials from public and proprietary documents. The team fine-tuned a fit-for-purpose chemical language model on this curated corpus, enabling it to learn the representation of the molecular structures. Using that knowledge, the teams leveraged the recently developed regression transformer by IBM Research to learn the correlation between key structural molecular features and the resulting physical-chemical properties. The resulting model can now propose entirely new high-barrier packaging materials that shield sensitive products from moisture, temperature swings and oxygen.

Nestlé will utilise this novel technology to identify future packaging materials, while considering cost, recyclability, and functionality.

Stefan Palzer, Nestlé chief technology officer: “This novel AI-powered language model, developed in collaboration with IBM Research, illustrates how Nestlé is leading the digital transformation within the food and beverage industry. In the future, such breakthrough technology could be used to optimise the development of more sustainable packaging solutions across product categories.”

Alessandro Curioni, IBM research VP Europe & Africa: “We do believe that Generative AI will continue to disrupt scientific discovery, impacting the core business of all knowledge-based industries, allowing critical differentiation and sustainable growth.”

Nestlé continues to leverage AI, machine learning, data science and automation to support innovation and help manage complexities. For example, Nestlé has developed a recipe optimisation tool that uses advanced algorithms to help product developers better manage trade-offs between ingredients, nutrition, cost and sustainability, while still meeting consumer expectations. The company also uses digital twins of equipment and production lines to optimise manufacturing processes and has developed digital tools to deliver personalised nutrition solutions for people and pets.

Nestlé recently announced the creation of a new R&D centre for deep tech, a first-of-its-kind in the food and nutrition industry. The new centre will screen, test and develop new generations of sensors, robots, coding systems, high-performing AI and virtual/mixed reality solutions to increase efficiency in research, innovation and operations.