According to the seminal NAE (National Academy of Engineering) report on digital twins, "a digital twin is a set of virtual information constructs that mimics the structure, context, and behavior of a physical system, is dynamically updated with data, possesses predictive capabilities, and informs decisions that realize value,” enabling critical needs for optimization and operation of complex systems. Advances in AI and the HPC Continuum, which integrates distributed data sources with pervasive computing resources spanning HPC/Cloud to the edge, can enable digital-twin workflows for complex natural, engineered, and human systems. The invited talks in this session will explore digital twin workflows, their requirements and challenges, and technical and infrastructural solutions to address them.
