Integrating predictive models and sensors to manage food stability in supply chains

• Published in: Food microbiology Vol. 75; pp. 90 - 94
• Main Author: Tamplin, Mark L.
• Format: Journal Article
• Language: English
• Published: England Elsevier Ltd 01.10.2018
• Subjects: Bayes Theorem; Food Contamination - statistics & numerical data; Food safety; Food Storage - statistics & numerical data; Food Supply - statistics & numerical data; Humans; Models, Statistical; Predictive models; Sensors; Spoilage; Supply chains; Temperature; Predictive models; Food safety; Sensors; Spoilage; Supply chains
• ISSN: 0740-0020; 1095-9998
• DOI: 10.1016/j.fm.2017.12.001

Food products move through complex supply chains, which require effective logistics to ensure food safety and to maximize shelf-life. Predictive models offer an efficient means to monitor and manage the safety and quality of perishable foods, however models require environmental data to estimate changes in microbial growth and sensory attributes. Currently, several companies produce Time-Temperature Indicators that react at rates that closely approximate predictive models; these devices are simple and cost-effective for food companies. However, even greater outcomes could be realized using sensors that transfer data to predictive models in real-time. This report describes developments in predictive models designed for supply chain management, as well as advances in environmental sensors. Important innovation can be realized in both supply chain logistics and food safety management by integrating these technologies. •Supply chain performance can be measured with environmental sensors.•Predictive models estimate microbial behaviour based on environmental condition.•Real-time sensors and models can be integrated to manage food safety and quality.