A Beam-Splitting Bianisotropic Metasurface Designed by Optimization and Machine Learning

Article Engineering, Electrical & Electronic

The Design of Dual Band Stacked Metasurfaces Using Integral Equations

Jordan Budhu et al.

Summary: An integral equation-based approach is presented for designing dual-band stacked metasurfaces that are invariant in 1-D. The approach involves three phases of design and can generate collimated beams at desired angles in each band.

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Optimization of Electromagnetic Metasurface Parameters Satisfying Far-Field Criteria

Stewart Pearson et al.

Summary: This article introduces a new optimization scheme for determining surface parameters to satisfy far-field constraints such as beam level, sidelobe level, and null locations. Through this optimization scheme, multicriteria pattern forming, extreme angle small surface refraction, and Chebyshev-like beamforming can be achieved.

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION (2022)

Add to Collection

Article Engineering, Electrical & Electronic

Gradient-Based Electromagnetic Inversion for Metasurface Design Using Circuit Models

Chaitanya Narendra et al.

Summary: The algorithm presented in the text is capable of designing metasurfaces directly at the circuit parameter level to achieve desired field patterns or power patterns. By assuming a three-layer admittance model, the inversion algorithm designs microwave admittance profiles of subwavelength elements of the metasurface. It minimizes the data misfit cost functional over unknown admittance profiles using analytically derived gradients and step lengths, allowing for the design of metasurfaces capable of beam forming in the far-field zone.

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION (2022)

Add to Collection

Article Engineering, Electrical & Electronic

A Combined Machine-Learning/Optimization-Based Approach for Inverse Design of Nonuniform Bianisotropic Metasurfaces

Parinaz Naseri et al.

Summary: This article proposes an efficient approach for the design of electromagnetic metasurfaces based on far-field constraints. The approach allows the designer to input high-level constraints and returns a design that satisfies these constraints. The method utilizes optimization and machine-learning techniques to determine the required surface parameters. Two examples are provided to demonstrate the effectiveness of the approach.

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION (2022)

Add to Collection

Article Materials Science, Multidisciplinary

Multifunctional Metasurface Design with a Generative Adversarial Network

Sensong An et al.

Summary: This paper presents a generative adversarial network that can generate meta-atom/metasurface designs to meet multifunctional design goals. This new methodology is efficient and flexible, suitable for multifunctional device design, and able to produce different classes of structures to accommodate other considerations.

ADVANCED OPTICAL MATERIALS (2021)

Add to Collection

Article Nanoscience & Nanotechnology

Multiplexed supercell metasurface design and optimization with tandem residual networks

Christopher Yeung et al.

Summary: Complex nanophotonic structures can be efficiently designed using deep learning models to explore structure-property relationships and generate a wide range of complex designs. This approach overcomes the challenges of vast design possibilities in a high-dimensional design space, demonstrating the feasibility of using deep neural networks for inverse design of nanophotonic structures.

NANOPHOTONICS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

Arbitrary Wave Transformations With Huygens' Metasurfaces Through Surface-Wave Optimization

Vasileios G. Ataloglou et al.

Summary: Huygens' metasurfaces have shown the ability to tailor electromagnetic wavefronts with passive low-profile structures by conserving real power locally along the metasurface. In this letter, a method using auxiliary surface waves to design HMS for wave transformations is examined, achieving high aperture illumination efficiency. The effects of evanescent spectrum on losses and bandwidth are also discussed.

IEEE ANTENNAS AND WIRELESS PROPAGATION LETTERS (2021)

Add to Collection

Article Engineering, Electrical & Electronic

A Generative Machine Learning-Based Approach for Inverse Design of Multilayer Metasurfaces

Parinaz Naseri et al.

Summary: This article introduces a machine learning-based approach to automate the design of dual- and triple-layer metasurfaces, solving the difficulties encountered in traditional synthesis methods. This method allows for the synthesis of thin structures with specific scattering properties, applied in various metasurface applications.

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION (2021)

Add to Collection

Article Engineering, Electrical & Electronic