Optimizing Photonic Nanostructures via Multi-fidelity Gaussian Processes
This work addresses optimization challenges in nanophotonics design, offering incremental improvements for researchers and engineers by enhancing computational efficiency in simulating photonic nanostructures.
The paper tackled optimizing transmission properties of plasmonic mirror color filters in a five-dimensional parameter space, using a multi-fidelity Gaussian processes approach, and demonstrated improved optimization efficiency compared to conventional methods like single-fidelity Gaussian processes and Particle Swarm Optimization with fixed computational budgets.
We apply numerical methods in combination with finite-difference-time-domain (FDTD) simulations to optimize transmission properties of plasmonic mirror color filters using a multi-objective figure of merit over a five-dimensional parameter space by utilizing novel multi-fidelity Gaussian processes approach. We compare these results with conventional derivative-free global search algorithms, such as (single-fidelity) Gaussian Processes optimization scheme, and Particle Swarm Optimization---a commonly used method in nanophotonics community, which is implemented in Lumerical commercial photonics software. We demonstrate the performance of various numerical optimization approaches on several pre-collected real-world datasets and show that by properly trading off expensive information sources with cheap simulations, one can more effectively optimize the transmission properties with a fixed budget.