Deep learning modeling approach for metasurfaces with high degrees of freedom

An, Sensong; Zheng, Bowen; Shalaginov, Mikhail Y.; Tang, Hong; Li, Hang; Zhou, Li; Ding, Jun; Agarwal, Anuradha M.; Rivero‐Baleine, Clara; Kang, Myungkoo; Gu, Tian; Hu, Juejun; Fowler, Clayton; Zhang, Hualiang

doi:10.1364/oe.401960

Cited by 90 publications

(55 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After the last transposed convolutional layer, a tan h activation function generates an image ready for evaluation. Finally, a pre‐trained prediction neural network [ 57 ] characterizes these output images and eliminates the unqualified meta‐atom designs.…”

Section: Figurementioning

confidence: 99%

Multifunctional Metasurface Design with a Generative Adversarial Network

Zheng

Tang

et al. 2021

Advanced Optical Materials

Self Cite

105

View full text Add to dashboard Cite

Metasurfaces have enabled precise electromagnetic (EM) wave manipulation with strong potential to obtain unprecedented functionalities and multifunctional behavior in flat optical devices. These advantages in precision and functionality come at the cost of tremendous difficulty in finding individual meta‐atom structures based on specific requirements (commonly formulated in terms of EM responses), which makes the design of multifunctional metasurfaces a key challenge in this field. In this paper, a generative adversarial network that can tackle this problem and generate meta‐atom/metasurface designs to meet multifunctional design goals is presented. Unlike conventional trial‐and‐error or iterative optimization design methods, this new methodology produces on‐demand free‐form structures involving only a single design iteration. More importantly, the network structure and the robust training process are independent of the complexity of design objectives, making this approach ideal for multifunctional device design. Additionally, the ability of the network to generate distinct classes of structures with similar EM responses but different physical features can provide added latitude to accommodate other considerations such as fabrication constraints and tolerances. The network's ability to produce a variety of multifunctional metasurface designs is demonstrated by presenting a bifocal metalens, a polarization‐multiplexed beam deflector, a polarization‐multiplexed metalens, and a polarization‐independent metalens.

show abstract

Section: Figurementioning

confidence: 99%

Multifunctional Metasurface Design with a Generative Adversarial Network

Zheng

Tang

et al. 2021

Advanced Optical Materials

Self Cite

105

View full text Add to dashboard Cite

show abstract

“…The diffraction integral calculations above assume ideal meta-atoms so the metasurface acts as a pure phase mask without imposing intensity modulation and phase error. To make a realistic estimate of the metalens efficiency, next we incorporated actual meta-atom structures and their optical characteristics modeled using full-wave calculations An et al (2020). The all-dielectric, free-form meta-atoms under consideration are made from 1 µm thick PbTe film resting on a BaF 2 substrate Zhang et al (2018); An et al (2019).…”

Section: Performance Evalutionmentioning

confidence: 99%

Wide field-of-view flat lens: an analytical formalism

Yang,

An,

Shalaginov

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Wide field-of-view (FOV) optics are widely used in various imaging, display, and sensing applications. While conventional wide FOV optics rely on cascading multiple elements to suppress coma and other aberrations, it has recently been demonstrated that diffractionlimited, near-180°FOV operation can be achieved with a single-piece flat fisheye lens designed via iterative numerical optimization [Nano Lett. 20, 7429(2020)]. Here we derive an analytical formalism to enable physics-informed and computationally efficient design of wide FOV flat lenses based on metasurfaces or diffractive optical elements (DOEs). Leveraging this analytical approach, we further quantified trade-offs between optical performance and design parameters in wide FOV metalenses.

show abstract

“…Metamaterials, along with their 2D versions, metasurfaces, have attracted wide attentions in recent years due to their unique low profile and lightweight properties as compared to their conventional bulk optics counterparts. Meta-atoms, the building blocks addition to these methods, recently numerous optimization algorithms, [22][23][24][25][26] deep neural networks (DNN), [27][28][29][30][31][32][33] and DNNoptimization adjoint methods [34][35][36] have also been proposed recently for the fast inverse design of meta-atoms with complex shapes or multiple objectives. [37] In these meta-atom design approaches mentioned above, unit cell boundary conditions were adopted during full wave simulations, which assumes that each meta-atom structure under consideration is part of an infinite 2D array of identical structures.…”

Section: Introductionmentioning

confidence: 99%

Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces

Zheng

Shalaginov

et al. 2021

Advanced Optical Materials

Self Cite

View full text Add to dashboard Cite

of metasurfaces, constructed with either all-dielectric [1][2][3] or plasmonic [4][5][6] nanoresonators, are capable of achieving engineered phase and amplitude control at the element level and thus enable accurate wave front control with subwavelength resolution. The most widely adopted metasurface design approach includes two steps: 1) calculate the amplitude and phase masks necessary for desired functionalities, fitted to square or hexagonal grids, and 2) find meta-atoms with performance closest to the target of each grid for the final design. Accurate and efficient meta-atom on-demand design approaches remain the main challenge with metasurface designs.To design meta-atoms with maximum efficiency and accurate phase gradients, a common method is to consider structures with simple geometric shapes (such as circles, [7,8] rectangles, [9,10] H-shapes, [11,12] and plasmonic thin layers [13,14] ) and perform a parameter sweep over all dimensions to assemble a library covering the full design space. Then best-fit metaatoms are selected from the library to approximate the ideal amplitude/phase map. Beyond this brute-force approach, previous literatures have also reported metasurface designs that based on solid physical considerations, such as waveguiding analysis, [15,16] Huygens surface, [11,17] surface integral equations, [18][19][20] and Pancharatnam-Berry (PB) phase. [4,21] In Metasurfaces have provided a novel and promising platform for realizing compact and high-performance optical devices. The conventional metasurface design approach assumes periodic boundary conditions for each element, which is inaccurate in most cases since near-field coupling effects between elements will change when the element is surrounded by nonidentical structures. In this paper, a deep learning approach is proposed to predict the actual electromagnetic (EM) responses of each target meta-atom placed in a large array with near-field coupling effects taken into account. The predicting neural network takes the physical specifications of the target metaatom and its neighbors as input, and calculates its actual phase and amplitude in milliseconds. This approach can be used to optimize metasurfaces' efficiencies when combined with optimization algorithms. To demonstrate the efficacy of this methodology, large improvements in efficiency for a beam deflector and a metalens over the conventional design approach are obtained. Moreover, it is shown that the correlations between a metasurface's performance and its design errors caused by mutual coupling are not bound to certain specifications (materials, shapes, etc.). As such, it is envisioned that this approach can be readily applied to explore the mutual coupling effects and improve the performance of various metasurface designs.

show abstract

Deep learning modeling approach for metasurfaces with high degrees of freedom

Cited by 90 publications

References 22 publications

Multifunctional Metasurface Design with a Generative Adversarial Network

Multifunctional Metasurface Design with a Generative Adversarial Network

Wide field-of-view flat lens: an analytical formalism

Deep Convolutional Neural Networks to Predict Mutual Coupling Effects in Metasurfaces

Contact Info

Product

Resources

About