Diffusion probabilistic model based accurate and high-degree-of-freedom metasurface inverse design

Conventional meta-atom designs rely heavily on researchers’ prior knowledge and trial-and-error searches using full-wave simulations, resulting in time-consuming and inefficient processes. Inverse design methods based on optimization algorithms, such as evolutionary algorithms, and topological optim...

Full description

Saved in:
Bibliographic Details
Published in:Nanophotonics (Berlin, Germany) Germany), 2023-10, Vol.12 (20), p.3871-3881
Main Authors: Zhang, Zezhou, Yang, Chuanchuan, Qin, Yifeng, Feng, Hao, Feng, Jiqiang, Li, Hongbin
Format: Article
Language:English
Subjects:
Algorithms
Deep learning
Degrees of freedom
Design optimization
diffusion probabilistic model
Evolutionary algorithms
Generative adversarial networks
Inverse design
Machine learning
Markov processes
Metamaterials
metasurfaces
Normal distribution
Parameters
Probabilistic models
Probability theory
Statistical analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Conventional meta-atom designs rely heavily on researchers’ prior knowledge and trial-and-error searches using full-wave simulations, resulting in time-consuming and inefficient processes. Inverse design methods based on optimization algorithms, such as evolutionary algorithms, and topological optimizations, have been introduced to design metamaterials. However, none of these algorithms are general enough to fulfill multi-objective tasks. Recently, deep learning methods represented by generative adversarial networks (GANs) have been applied to inverse design of metamaterials, which can directly generate high-degree-of-freedom meta-atoms based on S-parameters requirements. However, the adversarial training process of GANs makes the network unstable and results in high modeling costs. This paper proposes a novel metamaterial inverse design method based on the diffusion probability theory. By learning the Markov process that transforms the original structure into a Gaussian distribution, the proposed method can gradually remove the noise starting from the Gaussian distribution and generate new high-degree-of-freedom meta-atoms that meet S-parameters conditions, which avoids the model instability introduced by the adversarial training process of GANs and ensures more accurate and high-quality generation results. Experiments have proven that our method is superior to representative methods of GANs in terms of model convergence speed, generation accuracy, and quality.
ISSN:2192-8614
2192-8606
2192-8614
DOI:10.1515/nanoph-2023-0292