Periodic Reporting for period 1 - FOODGUARD (Microbiome applications and technological hubs as solutions to minimize food loss and waste - FOODGUARD)
Periodo di rendicontazione: 2024-01-01 al 2025-06-30
In a world grappling with escalating food waste, a silent crisis threatens the very foundation of our global food systems. Mountains of perishable goods are discarded, contributing to environmental degradation and economic losses. The urgency to find sustainable solutions is evident as we confront the dual challenges of meeting food demand and minimising waste. In this context, the EU-funded FOODGUARD project addresses the nexus of health, economics, and the environment. Specifically, its solutions aim to extend food shelf life, enhance safety monitoring, and accurately predict shelf life using cutting-edge tools. With pilot demonstrations in four countries, the project promises to minimise food loss, improve preservation methods, and foster transparency across the entire food value chain.
The main objective of FOODGUARD is to develop and demonstrate co-created innovations and applicable sustainable solutions in food processing and packaging based on microbiome (microbial networks and their interactions within the developed niche) in combination with advanced digital technologies to fight food loss/waste.FOODGUARD envisages the industrial application of certain microbiota and their theatre of activity, i.e. MICROBIOME, as well as tools to create the optimal conditions for the microbiome in food processing and food packaging configurations that (i) prevent microbial growth and thereby extend the shelf-life of high-value perishable foods like meat, fish, vegetables, and cheese; (ii) allow monitoring of food quality/safety/spoilage; and (iii) predict the microbial effect on the selected food systems, i.e. quality, safety, shelf-life.
These tools include (a) novel packaging with use of protective cultures and/or natural antimicrobials in the form of films (b) smart packaging with time temperature indicators and printed tags based on microbial activities/molecular biomarkers; and (c) Predictive Modelling, Data Science (ML, AI and advanced analytics), digital twins, deep learning, and distributed ledger technology (DLT) from data derived from microbial kinetics and spectral fingerprint acquired by sensors. At the same time, safety and sustainability assessments of tools, as well as validation, will be employed to ensure their uptake by relevant stakeholders for improved decision-making and policy.
The main objective of FOODGUARD is to develop and demonstrate co-created innovations and applicable sustainable solutions in food processing and packaging based on microbiome (microbial networks and their interactions within the developed niche) in combination with advanced digital technologies to fight food loss/waste.FOODGUARD envisages the industrial application of certain microbiota and their theatre of activity, i.e. MICROBIOME, as well as tools to create the optimal conditions for the microbiome in food processing and food packaging configurations that (i) prevent microbial growth and thereby extend the shelf-life of high-value perishable foods like meat, fish, vegetables, and cheese; (ii) allow monitoring of food quality/safety/spoilage; and (iii) predict the microbial effect on the selected food systems, i.e. quality, safety, shelf-life.
These tools include (a) novel packaging with use of protective cultures and/or natural antimicrobials in the form of films (b) smart packaging with time temperature indicators and printed tags based on microbial activities/molecular biomarkers; and (c) Predictive Modelling, Data Science (ML, AI and advanced analytics), digital twins, deep learning, and distributed ledger technology (DLT) from data derived from microbial kinetics and spectral fingerprint acquired by sensors. At the same time, safety and sustainability assessments of tools, as well as validation, will be employed to ensure their uptake by relevant stakeholders for improved decision-making and policy.
– (a) Mapped stakeholder expectations via literature review and 40 interviews; identified key food waste drivers (ii) Analyzed microbiome innovations and smart packaging; conducted a GAP analysis (iii) Developed sustainable packaging for pilot cases; surveyed 5,000 consumers on freshness indicators (iv) Designed the Intelligent FOODGUARD Management System (iFGMS) architecture for traceability and monitoring.
– (b) Tested 20 protective cultures; identified promising strains for fish, meat, lettuce, and feta (ii) Developed smart packaging tags (TTIs, freshness sensors); early seafood trials showed success (iii) Used non-invasive sensors (NIR, FTIR, MSI) to monitor spoilage; early predictive models developed, (iv) Machine learning models (Elastic Net most effective) used for freshness prediction; data quality challenges noted.
– (c) Investigated microbial indicators (metabolites, biomarkers) across the food chain (ii) Explored microbial pathways to reduce spoilage and food loss. – (i) Designed a blockchain-based data management system (ii) Integrated IoT for real-time tracking and traceability (iii) Developed AI/ML models for quality prediction (iv) Built a food risk assessment module using sensor data (v) Created user interfaces for stakeholder engagement.
–(d) Pilots launched for vegetables, meat, fish, and dairy (ii) Installed systems and adapted packaging; integrated smart tools (RFID, NIR, protective cultures) (iii) Initiated AI-based shelf-life prediction and blockchain traceability (iv) Developed training materials and the foodpackCulture app (v) Set up evaluation frameworks for sustainability and usability.
– (b) Tested 20 protective cultures; identified promising strains for fish, meat, lettuce, and feta (ii) Developed smart packaging tags (TTIs, freshness sensors); early seafood trials showed success (iii) Used non-invasive sensors (NIR, FTIR, MSI) to monitor spoilage; early predictive models developed, (iv) Machine learning models (Elastic Net most effective) used for freshness prediction; data quality challenges noted.
– (c) Investigated microbial indicators (metabolites, biomarkers) across the food chain (ii) Explored microbial pathways to reduce spoilage and food loss. – (i) Designed a blockchain-based data management system (ii) Integrated IoT for real-time tracking and traceability (iii) Developed AI/ML models for quality prediction (iv) Built a food risk assessment module using sensor data (v) Created user interfaces for stakeholder engagement.
–(d) Pilots launched for vegetables, meat, fish, and dairy (ii) Installed systems and adapted packaging; integrated smart tools (RFID, NIR, protective cultures) (iii) Initiated AI-based shelf-life prediction and blockchain traceability (iv) Developed training materials and the foodpackCulture app (v) Set up evaluation frameworks for sustainability and usability.
Beyond the state of the art;
(i) A microbiome signature specific to each product is also groundbreaking, although it is a bottleneck for industrial application (ii) Clear indications that there are potential avenues for performance improvements in real-world, minimally invasive food monitoring scenarios. In conclusion, the approaches demonstrated in this project may serve as an indicator of the potential utility of all three general types of sensor fusion in real-world food analysis scenarios. (iii) The application of “multi-omics” in food supply chain can provide insightful information about food’ quality and safety compared to the methodologies followed in current quality and safety management systems (iv) The applied bioprotective strain (L. pentosus) can elongate the shelf-life of the RTE salads without an effect on pathogen growth (v) The developed tool (Skandamis,Growth Predictor) is intended for multiple users from the scientific community, the authorities and the food industry for growth simulations and high-resolution risk assessments.
(i) A microbiome signature specific to each product is also groundbreaking, although it is a bottleneck for industrial application (ii) Clear indications that there are potential avenues for performance improvements in real-world, minimally invasive food monitoring scenarios. In conclusion, the approaches demonstrated in this project may serve as an indicator of the potential utility of all three general types of sensor fusion in real-world food analysis scenarios. (iii) The application of “multi-omics” in food supply chain can provide insightful information about food’ quality and safety compared to the methodologies followed in current quality and safety management systems (iv) The applied bioprotective strain (L. pentosus) can elongate the shelf-life of the RTE salads without an effect on pathogen growth (v) The developed tool (Skandamis,Growth Predictor) is intended for multiple users from the scientific community, the authorities and the food industry for growth simulations and high-resolution risk assessments.