Supermarkets and wholesalers may soon be able to keep food fresh and safe for longer while cutting waste, with a new artificial intelligence model developed by Nanyang Technological University, Singapore (NTU Singapore). The system can predict bacterial growth in different foods, giving retailers better guidance on shelf life, storage and stock management.
The technology is being developed at the Future Ready Food Safety Hub (FRESH@NTU), a joint research centre involving NTU, the Singapore Food Agency and A*STAR. Researchers there are studying how bacteria such as Salmonella behave over time in different food conditions, so the AI can learn to make more accurate predictions.
At the hub, scientists track how Salmonella grows or is inactivated under different factors such as temperature, acidity, salt levels and preservatives. This allows the model to estimate how quickly food may spoil and when it may no longer be safe to sell.
Dr Youssef Ezzaky, Research Fellow at FRESH@NTU, said the work helps train the AI to better reflect how bacteria behave in real food systems. This could give food businesses a more precise way to monitor freshness and support day-to-day decisions on storage, handling and stock turnover.
Professor William Chen, Executive Director of FRESH@NTU, said experiments have shown strong alignment between the AI's predictions and actual bacterial behaviour, demonstrating its potential to monitor bacteria in real food samples. He added that the technology could complement existing food safety guidelines by helping businesses better manage spoilage risks while maintaining safety standards.
Supermarket chain Sheng Siong is in talks with NTU to test the technology. If adopted, the model could help retailers and wholesalers decide when food is no longer safe to sell, reduce the risk of food poisoning, and optimise refrigeration use. This could improve food security by reducing waste across the supply chain while lowering energy use.
