Enhanced PML Based on the Long Short Term Memory Network for the FDTD Method
This paper proposes a new absorbing boundary condition (ABC) computation approach based on the deep learning technique. Benefited from the sequence dependence feature, the Long Short-Term Memory (LSTM) network is employed to replace the conventional perfectly matched layer (PML) ABC for the Finite-D...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8970334/ |
| _version_ | 1818620874525245440 |
|---|---|
| author | He Ming Yao Lijun Jiang |
| author_facet | He Ming Yao Lijun Jiang |
| author_sort | He Ming Yao |
| collection | DOAJ |
| description | This paper proposes a new absorbing boundary condition (ABC) computation approach based on the deep learning technique. Benefited from the sequence dependence feature, the Long Short-Term Memory (LSTM) network is employed to replace the conventional perfectly matched layer (PML) ABC for the Finite-Difference Time-Domain (FDTD) solving process. The newly proposed LSTM based PML model is trained by the electromagnetic field data on the interface of the conventional PML. Different from the conventional PML, the newly proposed model only needs one cell layer as the boundary. Hence, the newly proposed method conveniently reduces both the algorithm's complexity and the area of computation domain of FDTD. Additionally, the newly proposed LSTM based PML model can achieve higher accuracy than the conventional artificial neural network (ANN) based PML, thanks to the sequence dependence feature of the LSTM networks. Numerical examples have illustrated the capability and the accuracy of the proposed LSTM model. The results illustrate that the new method can be compatibly embedded into the FDTD solving process with the high accuracy. |
| first_indexed | 2024-12-16T18:00:19Z |
| format | Article |
| id | doaj.art-71e0eee0a299446bb662568a5e5bca97 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T18:00:19Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-71e0eee0a299446bb662568a5e5bca972022-12-21T22:22:04ZengIEEEIEEE Access2169-35362020-01-018210282103510.1109/ACCESS.2020.29695698970334Enhanced PML Based on the Long Short Term Memory Network for the FDTD MethodHe Ming Yao0https://orcid.org/0000-0003-2814-9539Lijun Jiang1https://orcid.org/0000-0002-7391-6322Department of Electrical and Electronic Engineering, The University of Hong Kong, Hong KongDepartment of Electrical and Electronic Engineering, The University of Hong Kong, Hong KongThis paper proposes a new absorbing boundary condition (ABC) computation approach based on the deep learning technique. Benefited from the sequence dependence feature, the Long Short-Term Memory (LSTM) network is employed to replace the conventional perfectly matched layer (PML) ABC for the Finite-Difference Time-Domain (FDTD) solving process. The newly proposed LSTM based PML model is trained by the electromagnetic field data on the interface of the conventional PML. Different from the conventional PML, the newly proposed model only needs one cell layer as the boundary. Hence, the newly proposed method conveniently reduces both the algorithm's complexity and the area of computation domain of FDTD. Additionally, the newly proposed LSTM based PML model can achieve higher accuracy than the conventional artificial neural network (ANN) based PML, thanks to the sequence dependence feature of the LSTM networks. Numerical examples have illustrated the capability and the accuracy of the proposed LSTM model. The results illustrate that the new method can be compatibly embedded into the FDTD solving process with the high accuracy.https://ieeexplore.ieee.org/document/8970334/LSTM networkPMLdeep learningFDTD |
| spellingShingle | He Ming Yao Lijun Jiang Enhanced PML Based on the Long Short Term Memory Network for the FDTD Method IEEE Access LSTM network PML deep learning FDTD |
| title | Enhanced PML Based on the Long Short Term Memory Network for the FDTD Method |
| title_full | Enhanced PML Based on the Long Short Term Memory Network for the FDTD Method |
| title_fullStr | Enhanced PML Based on the Long Short Term Memory Network for the FDTD Method |
| title_full_unstemmed | Enhanced PML Based on the Long Short Term Memory Network for the FDTD Method |
| title_short | Enhanced PML Based on the Long Short Term Memory Network for the FDTD Method |
| title_sort | enhanced pml based on the long short term memory network for the fdtd method |
| topic | LSTM network PML deep learning FDTD |
| url | https://ieeexplore.ieee.org/document/8970334/ |
| work_keys_str_mv | AT hemingyao enhancedpmlbasedonthelongshorttermmemorynetworkforthefdtdmethod AT lijunjiang enhancedpmlbasedonthelongshorttermmemorynetworkforthefdtdmethod |