Exploiting deep learning network in optical chirality tuning and manipulation of diffractive chiral metamaterials

Abstract

<jats:title>Abstract</jats:title><jats:p>Deep-learning (DL) network has emerged as an important prototyping technology for the advancements of big data analytics, intelligent systems, biochemistry, physics, and nanoscience. Here, we used a DL model whose key algorithm relies on deep neural network to efficiently predict circular dichroism (CD) response in higher-order diffracted beams of two-dimensional chiral metamaterials with different parameters. To facilitate the training process of DL network in predicting chiroptical response, the traditional rigorous coupled wave analysis (RCWA) method is utilized. Notably, these T-like shaped chiral metamaterials all exhibit the strongest CD response in the third-order diffracted beams whose intensities are the smallest, when comparing up to four diffraction orders. Our comprehensive results reveal that by means of DL network, the complex and nonintuitive relations between T-like metamaterials with different chiral parameters (i. e., unit period, width, bridge length, and separation length) and their CD performances are acquired, which owns an ultrafast computational speed that is four orders of magnitude faster than RCWA and a high accuracy. The insights gained from this study may be of assistance to the applications of DL network in investigating different optical chirality in low-dimensional metamaterials and expediting the design and optimization processes for hyper-sensitive ultrathin devices and systems.</jats:p>

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.…”

Inverse Design for Silicon Photonics: From Iterative Optimization Algorithms to Deep Neural Networks

“…In this section, we will focus on multi-layer perceptron (MLP) and convolutional neural network (CNN) for this kind of discriminable problem. Many advanced DNNs have already been considered for the design of metasurface [94][95][96][97][98][99][100][101][102][103] since many similar components with different diffraction angles are needed in this case. Advanced DNN architectures may also enable the design of integrated silicon photonic devices.…”

Expedited circular dichroism prediction and engineering in two-dimensional diffractive chiral metamaterials leveraging a powerful model-agnostic data enhancement algorithm

“…In addition, the source domain datasets are also needed for the MADE training process. In this work, we use the data from two published works [41,42] that employ deep neural networks in CD response analysis for the source domain. Particularly, the data in work 1 contain chiroptical responses from nine different structures [41], while work 2 provides the different optical responses from a T-like array with four key graphic parameters [42].…”

“…In order to verify the model-agnostic feature of MADE, two more ML models in addition to the ANN, namely the random forest regression (RFR) [56] and support vector regression (SVR) [57], are implemented in the MADE framework, accompanied by two target domain datasets (D T1 and D T2 ) and two source datasets (nine-structure dataset [41] and T-like structure dataset [42]). For each target domain dataset, we use two above source domain datasets to train these three ML models.…”

“…Deep learning networks or machine learning (ML) methods are significant for a wide range of scientific and industrial processes, covering the aspects of finance [26,27], medicine [28][29][30], transportation [31][32][33], communication [34,35], nanoscience [36][37][38][39], and sensors [40]. Particularly, these learning-based algorithms have emerged as one of the most successful research routes for computational physics and photonic device design [41][42][43][44][45][46]. In general, the training dataset created by either numerical simulations or experimental measurements is usually required in order to facilitate a predesigned artificial neural network (ANN) or other ML model to learn the underlying rules, followed by the trained model solving a target problem.…”