Design of optical meta-structures with applications to beam engineering using deep learning

Abstract

Nanophotonics is a rapidly emerging field in which complex on-chip components are required to manipulate light waves. The design space of on-chip nanophotonic components, such as an optical meta surface which uses sub-wavelength meta-atoms, is often a high dimensional one. As such conventional optimization methods fail to capture the global optimum within the feasible search space. In this manuscript, we explore a Machine Learning (ML)-based method for the inverse design of the meta-optical structure. We present a data-driven approach for modeling a grating meta-structure which performs photonic beam engineering. On-chip planar photonic waveguide-based beam engineering offers the potential to efficiently manipulate photons to create excitation beams (Gaussian, focused and collimated) for lab-on-chip applications of Infrared, Raman and fluorescence spectroscopic analysis. Inverse modeling predicts meta surface design parameters based on a desired electromagnetic field outcome. Starting with the desired diffraction beam profile, we apply an inverse model to evaluate the optimal design parameters of the meta surface. Parameters such as the repetition period (in 2D axis), height and size of scatterers are calculated using a feedforward deep neural network (DNN) and convolutional neural network (CNN) architecture. A qualitative analysis of the trained neural network, working in tandem with the forward model, predicts the diffraction profile with a correlation coefficient as high as 0.996. The developed model allows us to rapidly estimate the desired design parameters, in contrast to conventional (gradient descent based or genetic optimization) time-intensive optimization approaches.

A deep learning method for empirical spectral prediction and inverse design of all-optical nonlinear plasmonic ring resonator switches

“…They also highlighted the utility of inverse design for chemical sensing applications. Brian Anthony et al 51 explored ML methods to predict the design parameters of metasurfaces, considering the desired electromagnetic field outcomes. They also developed a DL framework for mapping the design space of topological states in photonic crystals 52 .…”

On-Chip Integrated Metasystem with Inverse-Design Wavelength Demultiplexing for Augmented Reality

“…Distinct from traditional metasurfaces to operate with free-space light, − on-chip metasurfaces can manipulate guided waves and facilitate arbitrary interfacial conversion between the free-space light and the on-chip guided waves. Imparted the encoding-freedom from traditional metasurfaces, on-chip metasurfaces can enable engineering of light amplitudes, phases, and polarization states at the subwavelength scale and thus create various desired and practical functionalities including beam-steering, optical router, − lensing, − holographic display, − etc.…”

Designing architectured ceramics for transient thermal applications using finite element and deep learning

“…Deep learning and other machine learning (ML) techniques have undergone rapid development over the past few years, and they are being successfully applied to accelerate research in a multitude of areas including materials and structure design in engineering [17][18][19][20][21][22][23]. One of the strengths of deep learning is its capability of expressing strong nonlinear relationships [24,25].…”

“…Fatehi et al [10] introduced a novel methodology that leverages neural networks for designing architectured ceramics. Additionally, Singh et al [19] employed Gaussian process regression and extreme gradient boosting techniques to optimize the architectured ceramics. These combined efforts demonstrate the potential of ML-driven approaches in advancing the performance and properties of architectured ceramic materials.…”