Over the past decades, the field of computational electromagnetics (CEM) has led to many simulation-driven scientific and engineering discoveries. One long-standing challenge in CEM research is to perform rapid, high-fidelity design and optimization for large-scale applications. The CEM-based high-fidelity design goes beyond just performing individual simulations, encompassing object-oriented interference analysis, design optimization, and uncertainty quantification. The typical scenarios require a much more rapid turnaround in order to navigate highly complex design spaces.

The purpose of this session is to discuss and explore recent advances in harnessing machine learning and artificial intelligence, model order reduction and domain decomposition, and quantum computing algorithms in the context of computer-aided electromagnetic design and optimization. This session serves as a platform to foster insightful discussions, share innovative approaches, and inspire collaboration within the CEM community.