Prediction Network of Metamaterial with Split Ring Resonator Based on Deep Learning

Abstract

The introduction of "metamaterials" has had a profound impact on several fields, including electromagnetics. Designing a metamaterial's structure on demand, however, is still an extremely time-consuming process. As an efficient machine learning method, deep learning has been widely used for data classification and regression in recent years and in fact shown good generalization performance. We have built a deep neural network for ondemand design. With the required reflectance as input, the parameters of the structure are automatically calculated and then output to achieve the purpose of designing on demand. Our network has achieved low mean square errors (MSE), with MSE of 0.005 on both the training and test sets. The results indicate that using deep learning to train the data, the trained model can more accurately guide the design of the structure, thereby speeding up the design process. Compared with the traditional design process, using deep learning to guide the design of metamaterials can achieve faster, more accurate, and more convenient purposes.

Inverse deep learning methods and benchmarks for artificial electromagnetic material design

“…For our benchmark, we propose to use MSE as the loss function, L, since it is widely used for AEM problems. 21,[27][28][29][30] It is also well-behaved and well-defined for all values of s, unlike the mean-relativeerroranother metric sometimes used in the AEM literature (e.g., Peurifoy et al, 24 Chen et al 1 ). MRE has the limitation that it grows exponentially as the value of s → 0, and becomes infinity when s = 0.…”

Deep Learning the Electromagnetic Properties of Metamaterials—A Comprehensive Review

“…Given the rapid growth of the field in the past several years, there are now many such applications of DL to forward problems throughout the various AEM sub‐disciplines. In metal‐based metamaterials, for example, DNNs have been used to predict the resonant optical behavior in a number of SRR, [ 111 ] cross‐based, [ 108 ] chiral, [ 111–114 ] and coded metasurfaces. [ 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.…”

“…In 2018 Liu et al., first used a tandem model to predict the thicknesses of a multilayer dielectric nanostructure, [ 123 ] with similar works appearing shortly thereafter using more refined networks. [ 107,112,145 ] Since these initial reports, tandem (bidirectional) DNN models have been used extensively in many different inverse design problems in AEM, including in chiral metamaterials, [ 112,144 ] core–shell nanoparticles, [ 148 ] plasmonic nanostructures, [ 106,145,183 ] metasurfaces, [ 111,173 ] topological photonics, [ 107,174,184 ] and dielectric resonators. [ 125,177 ]…”

Plasmonic Metamaterials Absorbers Design Based on XGBoost and LightGBM Algorithms

“…One of the nanophotonics research targets is to get a better understand on optical phenomena at the nanometer scale. Among them, the use of metamaterials to manipulate and control the interaction between light and matter at the micro and nano scale has attracted extensive attention of researchers [1,2]. In recent years, different kinds of devices based on metamaterials have been designed and demonstrated, such as absorbing materials [3][4][5], holographic imaging [6], multiparameter adjustable thermal diodes [7], radome [8].…”