• Corpus ID: 209532128

A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks

  title={A Freeform Dielectric Metasurface Modeling Approach Based on Deep Neural Networks},
  author={Sensong An and Bowen Zheng and Mikhail Y. Shalaginov and Hong Tang and Hang Li and Li Zhou and Jun Ding and Anuradha Murthy Agarwal and Clara Rivero‐Baleine and Myungkoo Kang and Kathleen A. Richardson and Tian Gu and Juejun Hu and Clayton Fowler and Hualiang Zhang},
Metasurfaces have shown promising potentials in shaping optical wavefronts while remaining compact compared to bulky geometric optics devices. Design of meta-atoms, the fundamental building blocks of metasurfaces, relies on trial-and-error method to achieve target electromagnetic responses. This process includes the characterization of an enormous amount of different meta-atom designs with different physical and geometric parameters, which normally demands huge computational resources. In this… 

Figures from this paper

A cyclical deep learning based framework for simultaneous inverse and forward design of nanophotonic metasurfaces
This work introduces a framework for inverse design of nanophotonic metasurfaces based on cyclical deep learning (DL) and performs inverse design and optimization mechanism for the generation of meta-atoms and meta-molecules as meetasurface units based on DL models and genetic algorithm.
Reconfigurable all-dielectric metalens for diffraction-limited imaging
Optical metasurfaces, planar sub-wavelength nano-antenna arrays with the singular ability to sculpt wave front in almost arbitrary manners, are poised to become a powerful tool enabling compact and
Successive training of a generative adversarial network for the design of an optical cloak
An optimization algorithm based on a deep convolution generative adversarial network (DCGAN) to design a 2-Dimensional optical cloak that uses a feedback loop from the solutions of the DCGAN to successively retrain it and improve its ability to predict and find optimal geometries.
Machine learning for the design of nanomaterials
In this article the authors review some machine learning methods for the design of nanomaterials and how to use neural network to build a predictive model of the optical properties of a certain material or structure using generative networks.
Artificial intelligence for photonics and photonic materials.
Research is summarized, future opportunities for AI in the domains of photonics, nanophotonics, plasmonics and photonic materials discovery, including metamaterials are discussed.
Multiplexed supercell metasurface design and optimization with tandem residual networks
This study demonstrates the feasibility of high-dimensional supercell inverse design with deep neural networks, which is applicable to complex nanophotonic structures composed of multiple subunit elements that exhibit coupling.
Meta-optics for spatial optical analog computing
This review discusses state-of-the-art developments, as well as emerging trends, in computational metastructures as disruptive platforms for spatial optical analog computation and discusses two fundamental approaches based on general concepts of spatial Fourier transformation and Green’s function.


A Novel Modeling Approach for All-Dielectric Metasurfaces Using Deep Neural Networks
A deep neural network approach is introduced that significantly improves on both speed and accuracy compared to techniques currently used to assemble metasurface-based devices.
Simulator-based training of generative neural networks for the inverse design of metasurfaces
This work presents a new type of population-based global optimization algorithm for metasurfaces that is enabled by the training of a generative neural network and observes that the distribution of devices generated by the network continuously shifts towards high performance design space regions over the course of optimization.
Plasmonic nanostructure design and characterization via Deep Learning
Rising to the challenge, Haim Suchowski and colleagues from Tel Aviv University in Israel have developed an innovative technique that uses Deep Neural Networks to model the complex relationships between light-matter interactions, allowing them to characterise nanostructures based on their far-field optical responses.
Generative Model for the Inverse Design of Metasurfaces
This work identifies a solution to circumvent this conventional design procedure by means of a deep learning architecture to expedite the discovery and design of metasurfaces for tailored optical responses in a systematic, inverse-design manner.
Global optimization of dielectric metasurfaces using a physics-driven neural network
We present a global optimizer, based on a conditional generative neural network, which can output ensembles of highly efficient topology-optimized metasurfaces operating across a range of parameters.
Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials.
A deep-learning-based model is reported, comprising two bidirectional neural networks assembled by a partial stacking strategy, to automatically design and optimize three-dimensional chiral metamaterials with strong chiroptical responses at predesignated wavelengths.
Compounding Meta‐Atoms into Metamolecules with Hybrid Artificial Intelligence Techniques
A hybrid artificial-intelligence-based framework consolidating compositional pattern-producing networks and cooperative coevolution to resolve the inverse design of metamolecules in metasurfaces is proposed, revealing a promising candidate approach to expedite the design of large-scale metAsurfaces in a labor-saving, systematic manner.
Deep learning meets nanophotonics: A generalized accurate predictor for near fields and far fields of arbitrary 3D nanostructures.
It is demonstrated how a deep neural network can be used as a fast, general purpose predictor of the full near-field and far-field response of plasmonic and dielectric nanostructures.
Probabilistic Representation and Inverse Design of Metamaterials Based on a Deep Generative Model with Semi‐Supervised Learning Strategy
This work proposes to represent metamaterials and model the inverse design problem in a probabilistically generative manner, enabling to elegantly investigate the complex structure–performance relationship in an interpretable way, and solve the one‐to‐many mapping issue that is intractable in a deterministic model.
A Hybrid Strategy for the Discovery and Design of Photonic Structures
This work represents an efficient, on-demand, and automated approach for the inverse design of photonic structures with subwavelength features and requires no prior knowledge of the geometry of thePhotonic structures, and allows joint optimization of the dimensional parameters.