Optical metasurfaces enable compact and ultrafast analog optical computing functions such as spatial and temporal differentiation, which are critical for edge detection, motion sensing, and real-time signal processing. However, traditional metasurface design relies heavily on iterative full-wave simulations and manual parameter tuning, making the process slow, computation-heavy, and difficult to scale. To address these limitations, this project aims to integrate machine learning into the metasurface design workflow, ultimately enabling rapid inverse design for analog optical computation.
Year
Student Trainees