A deep neural network for general scattering matrix
The scattering matrix is the mathematical representation of the scattering characteristics of any scatterer. Nevertheless, except for scatterers with high symmetry like spheres or cylinders, the scattering matrix does not have any analytical forms and thus can only be calculated numerically, which r...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
De Gruyter
2023-04-01
|
| Series: | Nanophotonics |
| Subjects: | |
| Online Access: | https://doi.org/10.1515/nanoph-2022-0770 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832570422840786944 |
|---|---|
| author | Jing Yongxin Chu Hongchen Huang Bo Luo Jie Wang Wei Lai Yun |
| author_facet | Jing Yongxin Chu Hongchen Huang Bo Luo Jie Wang Wei Lai Yun |
| author_sort | Jing Yongxin |
| collection | DOAJ |
| description | The scattering matrix is the mathematical representation of the scattering characteristics of any scatterer. Nevertheless, except for scatterers with high symmetry like spheres or cylinders, the scattering matrix does not have any analytical forms and thus can only be calculated numerically, which requires heavy computation. Here, we have developed a well-trained deep neural network (DNN) that can calculate the scattering matrix of scatterers without symmetry at a speed thousands of times faster than that of finite element solvers. Interestingly, the scattering matrix obtained from the DNN inherently satisfies the fundamental physical principles, including energy conservation, time reversal and reciprocity. Moreover, inverse design based on the DNN is made possible by applying the gradient descent algorithm. Finally, we demonstrate an application of the DNN, which is to design scatterers with desired scattering properties under special conditions. Our work proposes a convenient solution of deep learning for scattering problems. |
| format | Article |
| id | doaj-art-431619ea3c4141b58e7b4cbba1013ceb |
| institution | Kabale University |
| issn | 2192-8614 |
| language | English |
| publishDate | 2023-04-01 |
| publisher | De Gruyter |
| record_format | Article |
| series | Nanophotonics |
| spelling | doaj-art-431619ea3c4141b58e7b4cbba1013ceb2025-02-02T15:46:12ZengDe GruyterNanophotonics2192-86142023-04-0112132583259110.1515/nanoph-2022-0770A deep neural network for general scattering matrixJing Yongxin0Chu Hongchen1Huang Bo2Luo Jie3Wang Wei4Lai Yun5National Laboratory of Solid State Microstructures, School of Physics, and Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing210093, ChinaNational Laboratory of Solid State Microstructures, School of Physics, and Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing210093, ChinaInformation Hub, Hong Kong University of Science and Technology (Guangzhou), Guangzhou511458, ChinaSchool of Physical Science and Technology, Soochow University, Suzhou215006, ChinaInformation Hub, Hong Kong University of Science and Technology (Guangzhou), Guangzhou511458, ChinaNational Laboratory of Solid State Microstructures, School of Physics, and Collaborative Innovation Center of Advanced Microstructures, Nanjing University, Nanjing210093, ChinaThe scattering matrix is the mathematical representation of the scattering characteristics of any scatterer. Nevertheless, except for scatterers with high symmetry like spheres or cylinders, the scattering matrix does not have any analytical forms and thus can only be calculated numerically, which requires heavy computation. Here, we have developed a well-trained deep neural network (DNN) that can calculate the scattering matrix of scatterers without symmetry at a speed thousands of times faster than that of finite element solvers. Interestingly, the scattering matrix obtained from the DNN inherently satisfies the fundamental physical principles, including energy conservation, time reversal and reciprocity. Moreover, inverse design based on the DNN is made possible by applying the gradient descent algorithm. Finally, we demonstrate an application of the DNN, which is to design scatterers with desired scattering properties under special conditions. Our work proposes a convenient solution of deep learning for scattering problems.https://doi.org/10.1515/nanoph-2022-0770deep neural networkinverse problemscattering matrix |
| spellingShingle | Jing Yongxin Chu Hongchen Huang Bo Luo Jie Wang Wei Lai Yun A deep neural network for general scattering matrix Nanophotonics deep neural network inverse problem scattering matrix |
| title | A deep neural network for general scattering matrix |
| title_full | A deep neural network for general scattering matrix |
| title_fullStr | A deep neural network for general scattering matrix |
| title_full_unstemmed | A deep neural network for general scattering matrix |
| title_short | A deep neural network for general scattering matrix |
| title_sort | deep neural network for general scattering matrix |
| topic | deep neural network inverse problem scattering matrix |
| url | https://doi.org/10.1515/nanoph-2022-0770 |
| work_keys_str_mv | AT jingyongxin adeepneuralnetworkforgeneralscatteringmatrix AT chuhongchen adeepneuralnetworkforgeneralscatteringmatrix AT huangbo adeepneuralnetworkforgeneralscatteringmatrix AT luojie adeepneuralnetworkforgeneralscatteringmatrix AT wangwei adeepneuralnetworkforgeneralscatteringmatrix AT laiyun adeepneuralnetworkforgeneralscatteringmatrix AT jingyongxin deepneuralnetworkforgeneralscatteringmatrix AT chuhongchen deepneuralnetworkforgeneralscatteringmatrix AT huangbo deepneuralnetworkforgeneralscatteringmatrix AT luojie deepneuralnetworkforgeneralscatteringmatrix AT wangwei deepneuralnetworkforgeneralscatteringmatrix AT laiyun deepneuralnetworkforgeneralscatteringmatrix |