The growing complexity of global food supply chains, coupled with stringent demands for safety, authenticity, and regulatory compliance, necessitates innovative approaches leveraging advanced technologies. METROFOOD-IT addresses these challenges by integrating cutting edge analytical techniques such as NIR/IR spectroscopy, GC-MS, and microbiome sequencing with a dedicated High-Performance Computing (HPC) infrastructure (Urania), optimized for machine learning (ML) and big data analytics. Practical applications demonstrate the system's effectiveness, from detecting olive oil adulteration using deep learning to verifying PDO products through interpretable AI techniques. The implementation of Explainable AI methods ensures transparency in predictive models, addressing both scientific rigor and consumer trust requirements. The METROFOODIT approach not only enhances current quality control measures but also provides a scalable model for future applications in the agri-food sector, setting new standards for data-driven food analysis and regulatory compliance. The findings underscore the project's potential to reshape industry practices while maintaining scientific accountability and operational efficiency. © 2025 Elsevier B.V., All rights reserved.

Cited by: 0; Conference name: 8th IEEE International Workshop on Metrology for Industry 4.0 and IoT, MetroInd4.0 and IoT 2025; Conference sponsors: ; Conference location: Castelldefels; Conference code: 211621