Long short-term memory neural network for directly inverse design of nanofin metasurface

Posted on 23.06.2022 - 16:47
In this study, the neural network long short-term memory (LSTM) is used to quickly and accurately predict the polarization sensitivity of a nanofin metasurface, including forward prediction and reverse design. In the forward prediction, we construct a DNN with the same structure for comparison with LSTM. The test results show that LSTM has a higher accuracy and better robustness than DNN in similar cases. In the reverse design, we directly build an LSTM to reverse the design similar to the forward prediction network. By inputting the extinction ratio value in 8 ~ 12 μm, the reverse network can directly provide the unit cell geometry of the nanofin metasurface. Compared with other methods used to reverse design photonic structures using deep learning, our method is more direct because no other networks are introduced.

CITE THIS COLLECTION

Deng, Wenqiang; XU, Zhengji; Wang, Jinhao; Lv, Jinwen (2022): Long short-term memory neural network for directly inverse design of nanofin metasurface. Optica Publishing Group. Collection. https://doi.org/10.6084/m9.figshare.c.6032900.v2
or
Select your citation style and then place your mouse over the citation text to select it.

SHARE

email

Usage metrics

Optics Letters

AUTHORS (4)

Wenqiang Deng
Zhengji XU
Jinhao Wang
Jinwen Lv

CATEGORIES

need help?