Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism
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 accur...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-03-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/14/3/634 |
| _version_ | 1797610075923152896 |
|---|---|
| author | Xiaopeng Xu Yu Li Liuge Du Weiping Huang |
| author_facet | Xiaopeng Xu Yu Li Liuge Du Weiping Huang |
| author_sort | Xiaopeng Xu |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-11T06:09:24Z |
| format | Article |
| id | doaj.art-8bafba457e0c4e46afddea570b98336c |
| institution | Directory Open Access Journal |
| issn | 2072-666X |
| language | English |
| last_indexed | 2024-03-11T06:09:24Z |
| publishDate | 2023-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj.art-8bafba457e0c4e46afddea570b98336c2023-11-17T12:43:33ZengMDPI AGMicromachines2072-666X2023-03-0114363410.3390/mi14030634Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention MechanismXiaopeng Xu0Yu Li1Liuge Du2Weiping Huang3School of Information Science and Engineering, Shandong University, 72 Binhai Road, Qingdao 266237, ChinaSchool of Information Science and Engineering, Shandong University, 72 Binhai Road, Qingdao 266237, ChinaSchool of Information Science and Engineering, Shandong University, 72 Binhai Road, Qingdao 266237, ChinaSchool of Information Science and Engineering, Shandong University, 72 Binhai Road, Qingdao 266237, ChinaThe 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.https://www.mdpi.com/2072-666X/14/3/634inverse designnanophotonicsneural networkgenerative adversarial network |
| spellingShingle | Xiaopeng Xu Yu Li Liuge Du Weiping Huang Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism Micromachines inverse design nanophotonics neural network generative adversarial network |
| title | Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism |
| title_full | Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism |
| title_fullStr | Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism |
| title_full_unstemmed | Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism |
| title_short | Inverse Design of Nanophotonic Devices Using Generative Adversarial Networks with the Sim-NN Model and Self-Attention Mechanism |
| title_sort | inverse design of nanophotonic devices using generative adversarial networks with the sim nn model and self attention mechanism |
| topic | inverse design nanophotonics neural network generative adversarial network |
| url | https://www.mdpi.com/2072-666X/14/3/634 |
| work_keys_str_mv | AT xiaopengxu inversedesignofnanophotonicdevicesusinggenerativeadversarialnetworkswiththesimnnmodelandselfattentionmechanism AT yuli inversedesignofnanophotonicdevicesusinggenerativeadversarialnetworkswiththesimnnmodelandselfattentionmechanism AT liugedu inversedesignofnanophotonicdevicesusinggenerativeadversarialnetworkswiththesimnnmodelandselfattentionmechanism AT weipinghuang inversedesignofnanophotonicdevicesusinggenerativeadversarialnetworkswiththesimnnmodelandselfattentionmechanism |