Predictive and generative machine learning models for photonic crystals

Abstract

The prediction and design of photonic features have traditionally been guided by theory-driven computational methods, spanning a wide range of direct solvers and optimization techniques. Motivated by enormous advances in the field of machine learning, there has recently been a growing interest in developing complementary data-driven methods for photonics. Here, we demonstrate several predictive and generative data-driven approaches for the characterization and inverse design of photonic crystals. Concretely, we built a data set of 20,000 two-dimensional photonic crystal unit cells and their associated band structures, enabling the training of supervised learning models. Using these data set, we demonstrate a high-accuracy convolutional neural network for band structure prediction, with orders-of-magnitude speedup compared to conventional theory-driven solvers. Separately, we demonstrate an approach to high-throughput inverse design of photonic crystals via generative adversarial networks, with the design goal of substantial transverse-magnetic band gaps. Our work highlights photonic crystals as a natural application domain and test bed for the development of data-driven tools in photonics and the natural sciences.

Photonic-dispersion neural networks for inverse scattering problems

“…Solving inverse problems in photonic crystals with photonic band structures has been reported by recent works: Wei et al 16 established an inverse-mapping algorithm with a convolutional NN to predict the Zak phase of 1D photonic crystals precisely from input Hamiltonians. Christensen et al 33 trained a convolutional NN and generative adversarial networks to predict and design inverse photonic crystal band structures with orders of-magnitude speedup. In our case, a measured photonic dispersion that contains both abundant band structures features and reflectance information is used to solve ISPs.…”

Deep Learning the Electromagnetic Properties of Metamaterials—A Comprehensive Review

“…[ 115 ] In ADMs, DL has been applied to problems in color generation, [ 116–118 ] efficient metagrating design, [ 119,120 ] and modeling the complex resonant structure of cylindrical meta‐atoms, [ 109,121,122 ] supercells, [ 14 ] and multilayer nanostructures. [ 123–125 ] In photonic crystals, DNNs have been used to optimize the Q‐factor in nanocavities, [ 99 ] waveguide properties in fibers, [ 126 ] compute the band structure in 1D [ 127 ] and 2D [ 128–130 ] PCs, and predict edge states in topological insulators. [ 107 ] Last, several groups have utilized DNNs in the optimization of nanophotonic devices including plasmonic [ 131,132 ] and dielectric [ 102,133–137 ] waveguides, nanoantennas, [ 101,110 ] thermophotovoltaics, [ 138 ] power splitters, [ 133 ] biosensors, [ 139 ] smart windows, [ 140 ] and grating couplers.…”

“…After training with the critic (discriminator) turned on, the authors demonstrated that the network generated patterns that largely resemble the different geometry classes in G when given a target s representative of those shapes. Other GAN models were similarly developed for the inverse design of nanophotonic antennas, [ 179 ] thermal emitters, [ 190 ] photonic crystals, [ 130 ] and free‐form diffractive metagratings. [ 194 ]…”

Machine Learning in Chemical Product Engineering: The State of the Art and a Guide for Newcomers

“…[101] Polymers [102] Thin film nanocomposite membranes [103] Heterogeneous, multicomponent materials [104] Memristors materials [105] Thermal functional materials [106] Mechanical metamaterials [107] Energy materials [108] Photonic crystals [109] Metal-organic nanocapsules [110] Hydrogels [111] Renewable energy materials [112] Alloys [113] Functional materials [114] Polymers [115] Ultraincompressible, superhard materials [116] Materials for clean energy [117] Photo energy conversion systems…”