Absorption and Diffusion Enabled Ultrathin Broadband Metamaterial Absorber Designed by Deep Neural Network and PSO

Chen, Jian; Ding, Wei; Li, Ximing; Xi, Xiang; Ye, Kang-Ping; Wu, Huabing; Wu, Rui‐Xin

doi:10.1109/lawp.2021.3101703

Cited by 44 publications

(17 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Based on the DL model and genetic model, inverse design and optimized generation of structural units in metamaterials can be realized [133]. This can also be achieved through the combination of the DL model and PSO algorithm [134]. Combining the combined pattern generation network (CPPN) and the co-evolution algorithm can solve the problem of supramolecular inverse design in metamaterials.…”

Section: Hybrid Models With Other Algorithmsmentioning

confidence: 99%

Deep learning modeling strategy for material science: from natural materials to metamaterials

Chen

Xiong

et al. 2022

J. Phys. Mater.

View full text Add to dashboard Cite

Computational modeling is a crucial approach in material-related research for discovering new materials with superior properties. However, the high design flexibility in materials, especially in the realm of metamaterials where the sub-wavelength structure provides an additional degree of freedom in design, poses a formidable computational cost in various real-world applications. With the advent of big data, deep learning brings revolutionary breakthroughs in many conventional machine learning and pattern recognition tasks such as image classification. The accompanied data-driven modeling paradigm also provides transformative methodology shift in materials science, from trial-and-error routine to intelligent material discovery and analysis. This review systematically summarize the application of deep learning in material science, based on a model selection perspective for both natural materials and metamaterials. The review aims to uncover the logic behind data-model relation with emphasis on suitable data structures for different scenarios in the material study and the corresponding problem-solving deep learning model architectures.

show abstract

Section: Hybrid Models With Other Algorithmsmentioning

confidence: 99%

Deep learning modeling strategy for material science: from natural materials to metamaterials

Chen

Xiong

et al. 2022

J. Phys. Mater.

View full text Add to dashboard Cite

show abstract

“…[ 11,23 ] Assuming that the MSA consists of n different subarrays and each is composed of one building block, and the period building blocks are the same. Then, the RL of the absorber is written as: [ 11,12 ]

\begin{array}{*{20}{c}}{{\rm{RL}} = 20\ {{\log }_{10}}\left| {\sum\nolimits_{i = 1}^n {{c_i}{\Gamma _i}\left( {z,R,h} \right)} } \right|}\end{array}

where c i and Γ i is the filling ratio and reflection coefficient of the i ‐th subarray; z and R is the latent variable and surface resistance, respectively; h is thickness of the dielectric.…”

Section: Design Metasurface Absorber By Generative Meta‐atom Model An...mentioning

confidence: 99%

A Generative Meta‐Atom Model for Metasurface‐Based Absorber Designs

Ding

Chen

2022

Advanced Optical Materials

Self Cite

View full text Add to dashboard Cite

dielectric loss, [5] ohmic loss, [13][14][15][16] loading tunable lumped elements, [17][18][19][20] or multilayered metasurface. [15] Furthermore, polarization conversion and interference cancellation are introduced to the designs to achieve even better absorption and wider bandwidth. [21][22][23] Though the metasurface increases the design freedom of absorbers, it also causes complexity in design. Firstly, the increased dimensionality of the design freedom rapidly raises the cost of optimizations since the acquisition of EM response of MSA usually involves complex and time-consuming numerical simulations. [24] Next, the pattern of meta-atoms is usually given by physics-inspired considerations, which leads to regular patterns or their geometric transformations, such as split rings, [25] patches, [26] cross, [27] V-shapes, [28,29] and so on. These regular patterns are in a very small subspace of whole patterns, and thus the absorbers implemented by such patterns may not achieve the best absorbing performances.To meet the complexity caused by meta-atoms, one trend is using the deep learning (DL) method to model the meta-atoms, which have been extensively studied in computer science and engineering. [30] The unique feature of DL is that it can discover useful information from large amounts of data and establish data-driven models for the design. [24] For example, deep neural network (DNN) can capture data features with higher levels of abstraction in lower-level features and fit complex input-output relationships. Using this capability of the DL, one can construct a model to characterize the complex relationship between geometric topology and EM response for MS, and then timeconsuming numerical modeling is avoided in the design process. [31] This surrogate model will greatly improve design efficiency. However, it can only apply to the optimal design of MS with given topologies because of the one-to-one correspondence between the topologies and topological parameters. To overcome this shortcoming, the generative networks model attracts much attention. The generative model can not only effectively capture the essential features of complex input datasets, but uses the feature knowledge to generate new data. For example, researchers build generative adversarial networks (GANs) to implement the inverse design of metasurface patterns. [32][33][34] However, the inverse design model meets the convergence difficulty because of the existence of multiple candidate solutions.In this work, we propose a generative meta-atom model for the generation and optimization of MS toward absorbing Metasurfaces (MS) are widely accepted in the devices, such as absorbers, to improve their performances. MS provide new design freedoms, however, they also result in complexity in designs because of the high-dimensional topological space of meta-atoms, and high computational costs in the optimization procedure. To alleviate this challenge, a generative meta-atom model that generates the pattern and corresponding electromagnetic (EM) responses of m...

show abstract

“…Computational optimization techniques, such as genetic algorithms (GAs) and particle swarm optimization (PSO), were proposed to optimize the metamaterials and obtain the desired behavior [135], [136]. GA is an artificial intelligence algorithm often utilized to optimize electromagnetic devices in a global sense [137].…”

Section: Metamaterials Loss Reduction Based On Computational Optimiza...mentioning

confidence: 99%

Overview of Approaches for Compensating Inherent Metamaterials Losses

et al. 2022

View full text Add to dashboard Cite

Metamaterials are synthetic composite structures with extraordinary electromagnetic properties not readily accessible in ordinary materials. These media attracted massive attention due to their exotic characteristics. However, several issues have been encountered, such as the narrow bandwidth and inherent losses that restrict the spectrum and the variety of their applications. The losses have become the principal limiting factor when employing metamaterials in real-world applications. Consequently, overcoming them is crucially important and of practical necessity. This paper discusses the practical applications of metamaterials in constructing functional devices and the effects of the losses on such devices. In more depth, it reviews the available approaches for reducing the metamaterial losses developed over the last two decades in the light of available literature. These approaches include the utilization of the principles of electromagnetically induced transparency (EIT), geometric tailoring of the metamaterial structures, and embedding gain materials. Further, computational optimization techniques, such as particle swarm optimization (PSO) and genetic algorithm (GA), are also discussed to design low-loss metamaterials. The EIT-like metamaterial and the including of gain materials are systematic and universal approaches exhibiting low loss approaching zero. In contrast, the other two are not systematic and universal approaches.

show abstract

Absorption and Diffusion Enabled Ultrathin Broadband Metamaterial Absorber Designed by Deep Neural Network and PSO

Cited by 44 publications

References 32 publications

Deep learning modeling strategy for material science: from natural materials to metamaterials

Deep learning modeling strategy for material science: from natural materials to metamaterials

A Generative Meta‐Atom Model for Metasurface‐Based Absorber Designs

Overview of Approaches for Compensating Inherent Metamaterials Losses

Contact Info

Product

Resources

About