The complexity of metasurface behavior across spatial and temporal scales presents a significant challenge for accurate modeling and efficient design --- especially in the context of biophotonics and biochemical sensing. As metasurfaces evolve into multifunctional platforms for real-time diagnostics, label-free sensing, and controlled light-matter interaction, there is a growing need for advanced computational frameworks that can capture their multiscale nature.
This session aims to bring together researchers and practitioners exploring next-generation modeling techniques that blend physics-based approaches with data-driven methods. Emphasis will be placed on inverse design, machine learning, and optimization strategies tailored to the development of metasurfaces operating in optical and microwave regimes for biochemical and biomedical applications.