Neural-adjoint method for the inverse design of all-dielectric metasurfaces

Abstract

All-dielectric metasurfaces exhibit exotic electromagnetic responses, similar to those obtained with metal-based metamaterials. Research in all-dielectric metasurfaces currently uses relatively simple unit-cell designs, but increased geometrical complexity may yield even greater scattering states. Although machine learning has recently been applied to the design of metasurfaces with impressive results, the much more challenging task of finding a geometry that yields the desired spectra remains largely unsolved. We explore and adapt a recent deep learning approach -- termed neural-adjoint -- and find it is capable of accurately and efficiently estimating complex geometry needed to yield a targeted frequency-dependent scattering. We also show how the neural-adjoint method can intelligently grow the design search space to include designs that increasingly and accurately approximate the desired scattering response. The neural-adjoint method is not restricted to the case demonstrated and may be applied to plasmonics, photonic bandgap, and other structured material systems.

References in corpus (6)

• UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction
• Training deep neural networks for the inverse design of nanophotonic structures
• A Generative Model for Inverse Design of Metamaterials
• Global optimization of dielectric metasurfaces using a physics-driven neural network
• Wide-angle infrared absorber based on negative index plasmonic metamaterial
• Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks

Cited by in corpus (1)

• Mixture Manifold Networks: A Computationally Efficient Baseline for Inverse Modeling