This symposium focuses on the key methodologies and technologies that support the development of digital twins. It will highlight how artificial intelligence, big data analytics, and advanced numerical simulations contribute to creating reliable, dynamic, and predictive virtual models of physical systems.
Special attention will be given to data-driven approaches, where machine learning and AI techniques are used to extract insights, anticipate system behavior, and improve decision-making through the analysis of large and complex datasets. The importance of big data infrastructures and real-time data processing will be addressed as essential components to ensure continuous synchronization between the physical system and its digital counterpart.
In parallel, the symposium will explore the role of physics-based numerical simulations, such as finite element and multi-physics modeling, which remain fundamental for building accurate and interpretable digital twins—especially in contexts where empirical data is limited or uncertain. The integration of model-based and data-driven approaches will be presented as a key strategy to enhance the flexibility and precision of digital representations.
The session will include real-world case studies from both industrial applications and cultural heritage. In the industrial domain, examples will demonstrate how AI-supported digital twins are applied to predictive maintenance, process control, and system optimization. In the field of cultural heritage, projects will illustrate how digital replicas of artworks and historical structures are created through 3D scanning, data fusion, and simulation, enabling digital preservation, virtual exploration, and informed restoration strategies.