Skip to main content
Journal cover image

Learning the Physics of All-Dielectric Metamaterials with Deep Lorentz Neural Networks

Publication ,  Journal Article
Khatib, O; Ren, S; Malof, J; Padilla, WJ
Published in: Advanced Optical Materials
July 1, 2022

Deep neural networks (DNNs) have shown marked achievements across numerous research and commercial settings. Part of their success is due to their ability to “learn” internal representations of the input (x) that are ideal to attain an accurate approximation ((Formula presented.)) of some unknown function (f) that is, y = f(x). Despite their universal approximation capability, a drawback of DNNs is that they are black boxes, and it is unknown how or why they work. Thus, the physics discovered by the DNN remains hidden. Here, the condition of causality is enforced through a Lorentz layer incorporated within a deep neural network. This Lorentz NN (LNN) takes in the geometry of an all-dielectric metasurface, and outputs the causal frequency-dependent permittivity (Formula presented.) and permeability (Formula presented.). Additionally, this LNN gives the spatial dispersion (k) inherent in the effective material parameters, as well as the Lorentz terms, which constitute both (Formula presented.) and (Formula presented.). The ability of the LNN to learn metasurface physics is demonstrated through several examples, and the results are compared to theory and simulations.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Advanced Optical Materials

DOI

EISSN

2195-1071

Publication Date

July 1, 2022

Volume

10

Issue

13

Related Subject Headings

  • 5104 Condensed matter physics
  • 4016 Materials engineering
  • 3403 Macromolecular and materials chemistry
  • 0912 Materials Engineering
  • 0906 Electrical and Electronic Engineering
  • 0205 Optical Physics
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Khatib, O., Ren, S., Malof, J., & Padilla, W. J. (2022). Learning the Physics of All-Dielectric Metamaterials with Deep Lorentz Neural Networks. Advanced Optical Materials, 10(13). https://doi.org/10.1002/adom.202200097
Khatib, O., S. Ren, J. Malof, and W. J. Padilla. “Learning the Physics of All-Dielectric Metamaterials with Deep Lorentz Neural Networks.” Advanced Optical Materials 10, no. 13 (July 1, 2022). https://doi.org/10.1002/adom.202200097.
Khatib O, Ren S, Malof J, Padilla WJ. Learning the Physics of All-Dielectric Metamaterials with Deep Lorentz Neural Networks. Advanced Optical Materials. 2022 Jul 1;10(13).
Khatib, O., et al. “Learning the Physics of All-Dielectric Metamaterials with Deep Lorentz Neural Networks.” Advanced Optical Materials, vol. 10, no. 13, July 2022. Scopus, doi:10.1002/adom.202200097.
Khatib O, Ren S, Malof J, Padilla WJ. Learning the Physics of All-Dielectric Metamaterials with Deep Lorentz Neural Networks. Advanced Optical Materials. 2022 Jul 1;10(13).
Journal cover image

Published In

Advanced Optical Materials

DOI

EISSN

2195-1071

Publication Date

July 1, 2022

Volume

10

Issue

13

Related Subject Headings

  • 5104 Condensed matter physics
  • 4016 Materials engineering
  • 3403 Macromolecular and materials chemistry
  • 0912 Materials Engineering
  • 0906 Electrical and Electronic Engineering
  • 0205 Optical Physics