Publication | Closed Access
Machine‐Learning Designs of Anisotropic Digital Coding Metasurfaces
174
Citations
32
References
2018
Year
EngineeringPhysicsMaterials FabricationNanotechnologyNeural NetworkApplied PhysicsMetasurfacesMetamaterialsCircular PolarizationMaterial SimulationSurface ModelingComputational Nanostructure ModelingAbstract DigitalNanophotonicsQuantum Metamaterials
Digital coding representations of meta‑atoms enable intelligent metasurface designs via machine learning. The paper proposes a machine‑learning method to design anisotropic digital coding metasurfaces capable of achieving arbitrary absolute phase values across positions and polarizations. A deep‑learning neural network trained on 70,000 coding patterns and validated on 10,000 patterns predicts phase responses with 90.05 % accuracy and 2° error. The trained network identifies the correct coding pattern among 18 billion possibilities within a second, enabling the rapid creation of three functional 1‑bit anisotropic metasurfaces that support dual‑beam and triple‑beam scattering with specified polarizations.
Abstract Digital coding representations of meta‐atoms make it possible to realize intelligent designs of metasurfaces by means of machine learning algorithms. Here, a machine‐learning method to design anisotropic digital coding metasurfaces is proposed, and meta‐atoms may require any absolute phase values at different positions and under different polarizations. A deep‐learning neural network to predict the vast and complex system is proposed, in which only 70 000 training coding patterns are used to train the network. Another 10 000 randomly chosen coding patterns are employed to validate the neural network, showing an accuracy of 90.05% of phase responses with 2° error in the 360° phase. Using the learned network, the correct coding pattern among 18 billion of billions of choices for the required phase can be readily found in a second, finishing automatic design of anisotropic meta‐atoms. Three functional 1‐bit anisotropic coding metasurfaces are intelligently achieved by the learned network. It is convenient to realize dual‐beam scattering with left‐handed circular polarization (LHCP) for one beam while right‐handed circular polarization (RHCP) for the others, dual‐beam scattering with circular polarization for one beam while linear polarization (LP) for the others, and triple‐beam scattering with LHCP and RHCP for two beams while LP for the third one.
| Year | Citations | |
|---|---|---|
Page 1
Page 1