Deep Learning Assisted Inverse Design and Functioning of Nanophotonic Devices

A special issue of Micromachines (ISSN 2072-666X). This special issue belongs to the section "A:Physics".

Deadline for manuscript submissions: closed (31 December 2023) | Viewed by 2181

Special Issue Editors


E-Mail Website
Guest Editor
School of Physical Science and Technology, Soochow University, Suzhou 215006, China
Interests: optical force; light scattering; optical manipulation

E-Mail Website
Guest Editor
Physical Department, Belarusian State University, Minsk 220030, Belarus
Interests: metamaterials; light scattering; plasmonics; optical manipulation

Special Issue Information

Dear Colleagues,

Nanoscale photonic devices have received significant attention due to their compactness and remarkable functionality. Restricted by the computational and fabrication costs, prediction of the structural design is a challenge. For a great number of optimization parameters available for a complex nanophotonic device, the inverse design is preferable in comparison to iterative brute-force approaches. The inverse design as a tool for finding an appropriate nanostructure with desired functionality can be realized on different platforms, including topological optimization and machine learning. The latter technique is extremely promising since the training of artificial neuron networks is performed once significantly saving computational resources. This Special Issue welcomes researchers in the fields of computational physics, photonic engineering, and nanoscale optics to contribute research articles of any format, including review papers. The topic of requested research papers is devoted, but not limited to the application of the deep learning and inverse design approaches to improve performance of photonic nanostructures exploited in dispersion and modal coupling engineering, solar energy harvesting and optomechanics, non-Hermitian and topological photonics, etc.

Dr. Dongliang Gao
Prof. Dr. Andrey V. Novitsky
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Micromachines is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • nanophotonics
  • deep learning
  • inverse design
  • structural optimization
  • neuron network

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

13 pages, 4883 KiB  
Article
Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism
by Xiaopeng Xu, Yu Li, Liuge Du and Weiping Huang
Micromachines 2023, 14(3), 634; https://doi.org/10.3390/mi14030634 - 10 Mar 2023
Cited by 1 | Viewed by 1788
Abstract
The inverse design method based on a generative adversarial network (GAN) combined with a simulation neural network (sim-NN) and the self-attention mechanism is proposed in order to improve the efficiency of GAN for designing nanophotonic devices. The sim-NN can guide the model to [...] Read more.
The inverse design method based on a generative adversarial network (GAN) combined with a simulation neural network (sim-NN) and the self-attention mechanism is proposed in order to improve the efficiency of GAN for designing nanophotonic devices. The sim-NN can guide the model to produce more accurate device designs via the spectrum comparison, whereas the self-attention mechanism can help to extract detailed features of the spectrum by exploring their global interconnections. The nanopatterned power splitter with a 2 μm × 2 μm interference region is designed as an example to obtain the average high transmission (>94%) and low back-reflection (<0.5%) over the broad wavelength range of 1200~1650 nm. As compared to other models, this method can produce larger proportions of high figure-of-merit devices with various desired power-splitting ratios. Full article
Show Figures

Figure 1

Back to TopTop