SUTD-PRCM Dataset and Neural Architecture Search Approach for Complex Metasurface Design

Zhang, Tianning; Ang, Yee Sin; Li, Er‐Ping; Kee, Chun Yun; Ang, L. K.

doi:10.48550/arxiv.2203.00002

Cited by 1 publication

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We consider the polygonal encoding of the meta-atom, which enables the multi-variable parameterized representation of a large number of symmetric and asymmetric shapes; the asymmetry forces a polarization sensitivity. Unlike a pixel-based representation, [57][58][59] polygon-encoding can design lithographically realizable designs with a simple tuning of parameter values and is easy to implement compared with generative and latent space representations. [60][61][62] Four PCMs (GST, GeTe, VO 2 , and AIST) with their amorphous and crystalline phases are considered in the material front, and the wide-band transmittance and reflectance in the NIR wavelength range for s-and p-polarized incident waves are evaluated.…”

Section: Introductionmentioning

confidence: 99%

Deep learning aids simultaneous structure–material design discovery: a case study on designing phase change material metasurfaces

et al. 2023

View full text Add to dashboard Cite

.The capabilities of modern precision nanofabrication and the wide choice of materials [plasmonic metals, high-index dielectrics, phase change materials (PCM), and 2D materials] make the inverse design of nanophotonic structures such as metasurfaces increasingly difficult. Deep learning is becoming increasingly relevant for nanophotonics inverse design. Although deep learning design methodologies are becoming increasingly sophisticated, the problem of the simultaneous inverse design of structure and material has not received much attention. In this contribution, we propose a deep learning-based inverse design methodology for simultaneous material choice and device geometry optimization. To demonstrate the utility of the proposed method, we consider the topical problem of active metasurface design using PCMs. We consider a set of four commonly used PCMs in both fully amorphous and crystalline material phases for the material choice and an arbitrarily specifiable polygonal meta-atom shape for the geometry part, which leads to a vast structure/material design space. We find that a suitably designed deep neural network can achieve good optical spectrum prediction capability in an ample design space. Furthermore, we show that this forward model has a sufficiently high predictive ability to be used in a surrogate-optimization setup resulting in the inverse design of active metasurfaces of switchable functionality.

show abstract