Global Optimization of Dielectric Metasurfaces Using a Physics-Driven Neural Network

Jiang, Jiaqi; Fan, Jonathan A.

doi:10.1021/acs.nanolett.9b01857

Cited by 331 publications

(250 citation statements)

References 36 publications

Supporting

Mentioning

250

Contrasting

Order By: Relevance

“…[ 296 ] Machine learning methods provide new opportunities for model development and data fitting in conventional X‐ray and CTR scattering. [ 297,298 ] Building on recent work in image reconstruction [ 299 ] and inverse optical design methods, [ 300 ] deep learning neural networks could be applied in the future to perform phase retrieval from measured CTRs.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

High‐Resolution Crystal Truncation Rod Scattering: Application to Ultrathin Layers and Buried Interfaces

Disa

Walker

Ahn

2020

Adv Materials Inter

View full text Add to dashboard Cite

In crystalline materials, the presence of surfaces or interfaces gives rise to crystal truncation rods (CTRs) in their X‐ray diffraction patterns. While structural properties related to the bulk of a crystal are contained in the intensity and position of Bragg peaks in X‐ray diffraction, CTRs carry detailed information about the atomic structure at the interface. Developments in synchrotron X‐ray sources, instrumentation, and analysis procedures have made CTR measurements into extremely powerful tools to study atomic reconstructions and relaxations occurring in a wide variety of interfacial systems, with relevance to chemical and electronic functionalities. In this review, an overview of the use of CTRs in the study of atomic structure at interfaces is provided. The basic theory, measurement, and analysis of CTRs are covered and applications from the literature are highlighted. Illustrative examples include studies of complex oxide thin films and multilayers.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: (A) (B) (C)mentioning

confidence: 99%

High‐Resolution Crystal Truncation Rod Scattering: Application to Ultrathin Layers and Buried Interfaces

Disa

Walker

Ahn

2020

Adv Materials Inter

View full text Add to dashboard Cite

show abstract

“…40 Recently, deep learning approaches, based on the artificial neural networks (ANNs), have emerged as a revolutionary and robust methodology in nanophotonics. [41][42][43][44][45][46][47][48][49][50][51][52][53][54][55] Indeed, applying the deep learning algorithms to the nanophotonic inverse design can introduce remarkable design flexibility that can go far beyond that of the conventional methods. The inverse design approach works based one the training process, that enables fast prediction of complex optical properties of nanostructures with intricate architectures.…”

Section: Introductionmentioning

confidence: 99%

Enhanced light–matter interactions in dielectric nanostructures via machine-learning approach

Rahmani

et al. 2020

Adv. Photon.

114

View full text Add to dashboard Cite

A key concept underlying the specific functionalities of metasurfaces, i.e. arrays of subwavelength nanoparticles, is the use of constituent components to shape the wavefront of the light, on-demand. Metasurfaces are versatile and novel platforms to manipulate the scattering, colour, phase or the intensity of the light. Currently, one of the typical approaches for designing a metasurface is to optimize one or two variables, among a vast number of fixed parameters, such as various materials' properties and coupling effects, as well as the geometrical parameters. Ideally, it would require a multi-dimensional space optimization through direct numerical simulations. Recently, an alternative approach became quite popular allowing to reduce the computational cost significantly based on a deeplearning-assisted method. In this paper, we utilize a deep-learning approach for obtaining high-quality factor (high-Q) resonances with desired characteristics, such as linewidth, amplitude and spectral position. We exploit such high-Q resonances for the enhanced light-matter interaction in nonlinear optical metasurfaces and optomechanical vibrations, simultaneously. We demonstrate that optimized metasurfaces lead up to 400+ folds enhancement of the third harmonic generation (THG); at the same time, they also contribute to 100+ folds enhancement in optomechanical vibrations. This approach can be further used to realize structures with unconventional scattering responses.

show abstract

“…The stochastic nature of the generative models enables the exploration of the solution space in a global way. Consolidating with traditional optimization techniques, GAN and VAE are able to discover the topology of nanostructures with improved efficiency and robustness [29][30][31] .In the problems of inverse design of photonic structures, optimizing the topology of a photonic structure with arbitrary shape is a long-sought-after goal. Typically, the topology of photonic structures is represented in binary images.…”

mentioning

confidence: 99%

mentioning

confidence: 99%

Topological encoding method for data-driven photonics inverse design

Liu¹,

Zhu²,

Cai³

2020

Opt. Express

View full text Add to dashboard Cite

Data-driven approaches have been proposed as effective strategies for the inverse design and optimization of photonic structures in recent years. In order to assist data-driven methods for the design of topology of photonic devices, we propose a topological encoding method that transforms photonic structures represented by binary images to a continuous sparse representation. This sparse representation can be utilized for dimensionality reduction and dataset generation, enabling effective analysis and optimization of photonic topologies with data-driven approaches. As a proof of principle, we leverage our encoding method for the design of two dimensional non-paraxial diffractive optical elements with various diffraction intensity distributions. We proved that our encoding method is able to assist machine-learning-based inverse design approach for accurate and global optimization.With the fast evolution of machine learning (ML) and deep learning (DL) techniques 12 , data-driven methods are emerging as an alternative way to discover and design photonic structures and devices 13 . Feedforward neural networks are leveraged for the approximation of the photonics systems with tens to hundreds of parameters, and have been utilized to successfully optimize photonic structures such as photonic crystals 14,15 , waveguide 16,17 , chiral metamaterials 18 , and metasurfaces 19 . When the degree of freedom (DOF) of the photonic system grows to thousands and more, convolutional neural networks (CNN) are adopted for the accurate prediction of the physical responses with much lower computational complexity 20,21 . Photonic structures represented in pixelated images, for example, are usually processed by CNNs to reduce the DOF for further optimization. Additionally, generative models, such as variational autoencoder (VAE) 22 and generative adversarial network (GAN) 23,24 , are utilized for the design of high DOF metasurface nanostructures in an expeditious way [25][26][27][28] . The stochastic nature of the generative models enables the exploration of the solution space in a global way. Consolidating with traditional optimization techniques, GAN and VAE are able to discover the topology of nanostructures with improved efficiency and robustness [29][30][31] .In the problems of inverse design of photonic structures, optimizing the topology of a photonic structure with arbitrary shape is a long-sought-after goal. Typically, the topology of photonic structures is represented in binary images. Because of the discretization and the high DOF of binary images, optimization is likely stuck in local minima. Although generative models are able to discover new topologies so as to approach global minimum, the bias of the training dataset and the limited capacity of the network cause incompleteness of the solution space, i.e., the global minimum may not be included in the space defined by the training dataset. Here, we propose an encoding method that is able to transform the binary image to a continuous sparse representation. This encoding appro...

show abstract

Global Optimization of Dielectric Metasurfaces Using a Physics-Driven Neural Network

Cited by 331 publications

References 36 publications

High‐Resolution Crystal Truncation Rod Scattering: Application to Ultrathin Layers and Buried Interfaces

High‐Resolution Crystal Truncation Rod Scattering: Application to Ultrathin Layers and Buried Interfaces

Enhanced light–matter interactions in dielectric nanostructures via machine-learning approach

Topological encoding method for data-driven photonics inverse design

Contact Info

Product

Resources

About