Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative Model
This study proposes an inverse design framework for metasurfaces based on a neural network capable of generating infinite and continuous latent representations to fully span the electromagnetic metasurfaces (EMMS) property space. The inverse design of EMMS inherently poses the one-to-many mapping pr...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Korean Institute of Electromagnetic Engineering and Science
2024-03-01
|
| Series: | Journal of Electromagnetic Engineering and Science |
| Subjects: | |
| Online Access: | https://www.jees.kr/upload/pdf/jees-2024-2-r-218.pdf |
| _version_ | 1827287465593929728 |
|---|---|
| author | Jong-Hoon Kim Ic-Pyo Hong |
| author_facet | Jong-Hoon Kim Ic-Pyo Hong |
| author_sort | Jong-Hoon Kim |
| collection | DOAJ |
| description | This study proposes an inverse design framework for metasurfaces based on a neural network capable of generating infinite and continuous latent representations to fully span the electromagnetic metasurfaces (EMMS) property space. The inverse design of EMMS inherently poses the one-to-many mapping problem, since one set of electromagnetic properties can be provided by many different shapes of scatterers. Previous studies have addressed this issue by introducing machine learning-based generative models and regularization strategies. However, most of these approaches require highly complex operating configurations or external modules for preprocessing datasets. In contrast, this study aimed to construct a more streamlined and end-to-end solver by building a network to process multimodal datasets and then incorporating a classification scheme into the network. The validity of the idea was confirmed by comparing the accuracy of the results predicted by the proposed approach and the outcomes simulated using PSSFSS. |
| first_indexed | 2024-04-24T10:59:55Z |
| format | Article |
| id | doaj.art-9942abf9e83844f2a98724b57913a362 |
| institution | Directory Open Access Journal |
| issn | 2671-7255 2671-7263 |
| language | English |
| last_indexed | 2024-04-24T10:59:55Z |
| publishDate | 2024-03-01 |
| publisher | The Korean Institute of Electromagnetic Engineering and Science |
| record_format | Article |
| series | Journal of Electromagnetic Engineering and Science |
| spelling | doaj.art-9942abf9e83844f2a98724b57913a3622024-04-12T04:10:31ZengThe Korean Institute of Electromagnetic Engineering and ScienceJournal of Electromagnetic Engineering and Science2671-72552671-72632024-03-0124217819010.26866/jees.2024.2.r.2183656Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative ModelJong-Hoon Kim0Ic-Pyo Hong1 Smart Natural Space Research Center, Kongju National University, Cheonan, Korea Department of Information and Communication Engineering, Kongju National University, Cheonan, KoreaThis study proposes an inverse design framework for metasurfaces based on a neural network capable of generating infinite and continuous latent representations to fully span the electromagnetic metasurfaces (EMMS) property space. The inverse design of EMMS inherently poses the one-to-many mapping problem, since one set of electromagnetic properties can be provided by many different shapes of scatterers. Previous studies have addressed this issue by introducing machine learning-based generative models and regularization strategies. However, most of these approaches require highly complex operating configurations or external modules for preprocessing datasets. In contrast, this study aimed to construct a more streamlined and end-to-end solver by building a network to process multimodal datasets and then incorporating a classification scheme into the network. The validity of the idea was confirmed by comparing the accuracy of the results predicted by the proposed approach and the outcomes simulated using PSSFSS.https://www.jees.kr/upload/pdf/jees-2024-2-r-218.pdfemms propertygenerative modelinverse designlatent spacesmetasurfaces |
| spellingShingle | Jong-Hoon Kim Ic-Pyo Hong Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative Model Journal of Electromagnetic Engineering and Science emms property generative model inverse design latent spaces metasurfaces |
| title | Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative Model |
| title_full | Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative Model |
| title_fullStr | Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative Model |
| title_full_unstemmed | Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative Model |
| title_short | Inverse Design of Electromagnetic Metasurfaces Utilizing Infinite and Separate Latent Space Yielded by a Machine Learning-Based Generative Model |
| title_sort | inverse design of electromagnetic metasurfaces utilizing infinite and separate latent space yielded by a machine learning based generative model |
| topic | emms property generative model inverse design latent spaces metasurfaces |
| url | https://www.jees.kr/upload/pdf/jees-2024-2-r-218.pdf |
| work_keys_str_mv | AT jonghoonkim inversedesignofelectromagneticmetasurfacesutilizinginfiniteandseparatelatentspaceyieldedbyamachinelearningbasedgenerativemodel AT icpyohong inversedesignofelectromagneticmetasurfacesutilizinginfiniteandseparatelatentspaceyieldedbyamachinelearningbasedgenerativemodel |