Chalcogenide phase change materials (PCMs) are uniquely suited for spectral tuning applications due to their contrasting dielectric material properties. Recent headway has been made towards realizing tunable photonic devices using twodimensional, sub-wavelength resonators by carefully designing geometries that optimize optical, electrical, and thermal performances using multi-physics analyses and machine learning. In this paper, we tackle two other essential aspects for creating application-specific, tunable PCM devices: (1) scalability of the device size and (2) high-throughput fabrication techniques. We employ a deep ultraviolet (DUV) stepper projection lithography to manufacture over 100 densely packed GST metasurfaces, each with a sample size of 5×7 mm2, all on a 4-inch Al2O3 wafer. These metasurface structures were discovered using artificial neural network (ANN) techniques and confirmed by finite-difference-time domain calculations. The primary structures under investigation were nanobar configurations enabling amplitude modulation at short-wave infrared wavelengths to realize efficient optical switches for free space optical multiplexing. The DUV fabrication technique can easily be extended to other metasurface geometries to demonstrate multi-functional, non-volatile photonic devices.
The next generation of multi-functional optical materials will customize electric field responses via a careful arrangement of micro- and nano- scale scatterers to achieve targeted optical performance otherwise unattainable in traditional bulk media. Macroscopically, such designed materials collectively respond to radiation based on the geometric shape, distribution, and inherent material properties of these sub-wavelength structures. The core challenge is in prescribing a configuration which results in a desired property. It becomes immediately clear these metamaterial systems pose significant challenges because of the near-infinite design space one needs to consider. Recently, artificial neural networks (ANNs) have been used to successfully approach this intractable problem. In the specific context of designing an all-dielectric metasurface reflector, we showed that joining two properly trained ANNs can both emulate Maxwell equations as well as inversely correlate reflection and transmission spectra.1 Though highly accurate ANNs were trained, the ANNs employed were never optimized in terms of architecture (e.g. number of layers, number of nodes, shape of the network) or hyperparameters (e.g. batch sizes, activation functions, loss functions). In this manuscript, we apply Bayesian optimization with Gaussian processes to first optimize the architecture and then the hyperparameters of the spectra predicting networks described in Ref. 1. The goal is not only to improve upon the previously implemented ANNs but to analyze the effect of different ANN architectures and convergence settings on overall spectra predictive performance.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.