Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2402.16920 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929257724248064 |
|---|---|
| author | Sun, Ming-Yan Xu, Peng Zhang, Jun-Jie Du, Tai-Jiao Wang, Jian-Guo |
| author_facet | Sun, Ming-Yan Xu, Peng Zhang, Jun-Jie Du, Tai-Jiao Wang, Jian-Guo |
| contents | We present JefiAtten, a novel neural network model employing the attention mechanism to solve Maxwell's equations efficiently. JefiAtten uses self-attention and cross-attention modules to understand the interplay between charge density, current density, and electromagnetic fields. Our results indicate that JefiAtten can generalize well to a range of scenarios, maintaining accuracy across various spatial distribution and handling amplitude variations. The model showcases an improvement in computation speed after training, compared to traditional integral methods. The adaptability of the model suggests potential for broader applications in computational physics, with further refinements to enhance its predictive capabilities and computational efficiency. Our work is a testament to the efficacy of integrating attention mechanisms with numerical simulations, marking a step forward in the quest for data-driven solutions to physical phenomena. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_16920 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | JefiAtten: An Attention Based Neural Network Model for Solving Maxwell's Equations with Charge and Current Sources Sun, Ming-Yan Xu, Peng Zhang, Jun-Jie Du, Tai-Jiao Wang, Jian-Guo Computational Physics We present JefiAtten, a novel neural network model employing the attention mechanism to solve Maxwell's equations efficiently. JefiAtten uses self-attention and cross-attention modules to understand the interplay between charge density, current density, and electromagnetic fields. Our results indicate that JefiAtten can generalize well to a range of scenarios, maintaining accuracy across various spatial distribution and handling amplitude variations. The model showcases an improvement in computation speed after training, compared to traditional integral methods. The adaptability of the model suggests potential for broader applications in computational physics, with further refinements to enhance its predictive capabilities and computational efficiency. Our work is a testament to the efficacy of integrating attention mechanisms with numerical simulations, marking a step forward in the quest for data-driven solutions to physical phenomena. |
| title | JefiAtten: An Attention Based Neural Network Model for Solving Maxwell's Equations with Charge and Current Sources |
| topic | Computational Physics |
| url | https://arxiv.org/abs/2402.16920 |