Kyushu University develops AI-powered packaging to cut food waste

JAPAN – Researchers at Kyushu University have developed a future-ready food packaging framework combining intelligent sensors, self-healing materials and artificial intelligence to detect spoilage in real time and inform producers and consumers.

The framework, published in Trends in Food Science and Technology, is built around a closed loop of recognition, judgment, actuation and feedback. 

It merges three research areas that had previously developed in isolation: intelligent sensing, self-healing materials and AI-driven prediction. 

Fumihiko Tanaka, professor at Kyushu University’s Faculty of Agriculture, noted that roughly one-third of all food produced globally is wasted, carrying a climate cost, as food loss accounts for approximately 8 percent of global greenhouse gas emissions, approaching the roughly 10 percent attributed to road transport.

Natural Pigments Provide Readable Spoilage Signals

After a systematic review, the researchers placed sensors within packaging to detect pH shifts, gases and microbial byproducts signalling spoilage. 

Natural pigments such as anthocyanins, found in foods like purple sweet potatoes, shift colour as pH changes, offering a readable signal at every stage of deterioration. 

In spoiling meat, for example, alkaline gases accumulate and the material shifts continuously from purple-red to yellow-green. 

Fanze Meng, the paper’s first author and a postdoctoral researcher, said future-ready packaging required a different mindset, with the film designed to communicate with the food itself, converting optical or gas signals into electrical data that AI could interpret.

Self-Healing Capacity Addresses Reliability Concerns

Xirui Yan, a researcher for the Japan Society for the Promotion of Science at Kyushu University, explained that surviving real-world distribution required more than sensing ability, since light and heat could cause false readings and bumps or scratches could interrupt signals. 

One approach involved anchoring pigments with metal-organic frameworks and carbon quantum dots while adding self-healing capacity so the film kept working after damage. 

The AI-enabled system then converts spoilage signals into responses such as releasing antimicrobials, sending alerts or optimising logistics.

Commercial Pathways and Future Research Directions

The team plans to update its recommendation system to reflect how differently foods spoil, tracking compounds each food releases so AI can learn distinct patterns. 

Tanaka observed that deeper understanding of produce deterioration could inform sales and consumption strategy. 

The researchers are collaborating with local governments and logistics partners to grade produce based on storage and transport resilience, directing short-shelf-life items to local markets and hardier varieties to export. 

Consumer-facing applications could deliver instant product information through connective packaging. 

Future studies must address long-term safety and stability of food-contact materials, particularly certain nanomaterials, alongside consistent quality control at industrial scale.

Subscribe to our email newsletters that provide busy executives like you with the latest news insights and trends from Africa and the World. SUBSCRIBE HERE