We support innovation and research by providing multi-scale models of complex systems, from molecules to nanotechnology to the continuum scale, and developing advanced models in the context of application domains, from digital twins for manufacturing to the simulation of biomedical devices and several others. Our approach to multi-scale integration relies on the definition of the interrelationships connecting hierarchically different time and scale domains, assisted by data-driven links. In each domain, realistic models are defined through state-of-the-art computational techniques and supported by high-performance computing. The integration of data, information and knowledge across scales and domains is enabled by the development of data-driven integration frameworks and supported by semantic technologies. We apply this approach to understand and develop innovative platforms for the application of advanced materials, processes and technology. In the research news, applications of our approach in fields ranging from energy, health, to manufacturing and smart mobility, are showcased.

We integrate recent advancements in Artificial Intelligence and data science with high-performance computing to create data-driven frameworks that drive scientific and technological progress across various fields. Using state-of-the-art AI tools and methods, from machine learning to large language models, we leverage domain-specific knowledge to apply predictive AI frameworks effectively. Our approach includes high-throughput simulations to generate synthetic data for models, enhancing their accuracy and applicability. We also automate research processes by defining data-driven workflows. Managing vast amounts of modeling data requires precise information representation, so we develop and implement integration frameworks for AI support, utilizing semantic technologies, ontologies, and knowledge graphs. This foundational work enables the creation of robust simulation frameworks across multiple application domains.