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

Abstract

.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.

Fast crystallization of InSe thin films via pulsed laser welding technique and effect of crystallinity on the optical and dielectric properties

“…Compared to the data published in [40], although the increase in the drift mobility values is not much pronounced, for the first three oscillators eV, the plasmon frequency and free electron concentration are highly increased 12.2 and 150, 4.1 and 17.5 and 1.3 and 1.6 times, respectively. These features which are reached via pulsed laser assisted crystallinity of the films within one second make the material more effective in optoelectronic technology [55][56][57].…”

Recent developments in Chalcogenide phase change material-based nanophotonics

“…They considered a vast design space consisting of four commonly used phase change materials and an arbitrarily specifiable polygonal meta-atom They found that a deep neural network can accurately predict optical spectra in this design space and can be used in a surrogate-optimization setup to achieve the inverse design of active metasurfaces. Overall, the study demonstrated the potential of DL-assisted approaches in designing complex nanophotonic structures [157]. There are a few more papers [158,159] that discuss the application of deep learning (DL) for the inverse design of PCM-based metasurfaces.…”