Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912910883684352 |
|---|---|
| author | Du, Yutong Liu, Zicheng Matkerim, Bazargul Li, Changyou Zong, Yali Qi, Bo Kou, Jingwei |
| author_facet | Du, Yutong Liu, Zicheng Matkerim, Bazargul Li, Changyou Zong, Yali Qi, Bo Kou, Jingwei |
| contents | In recent years, deep learning-based methods have been proposed for solving inverse scattering problems (ISPs), but most of them heavily rely on data and suffer from limited generalization capabilities. In this paper, a new solving scheme is proposed where the solution is iteratively updated following the updating of the physics-driven neural network (PDNN), the hyperparameters of which are optimized by minimizing the loss function which incorporates the constraints from the collected scattered fields and the prior information about scatterers. Unlike data-driven neural network solvers, PDNN is trained only requiring the input of collected scattered fields and the computation of scattered fields corresponding to predicted solutions, thus avoids the generalization problem. Moreover, to accelerate the imaging efficiency, the subregion enclosing the scatterers is identified. Numerical and experimental results demonstrate that the proposed scheme has high reconstruction accuracy and strong stability, even when dealing with composite lossy scatterers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16321 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems Du, Yutong Liu, Zicheng Matkerim, Bazargul Li, Changyou Zong, Yali Qi, Bo Kou, Jingwei Image and Video Processing Machine Learning Computational Physics In recent years, deep learning-based methods have been proposed for solving inverse scattering problems (ISPs), but most of them heavily rely on data and suffer from limited generalization capabilities. In this paper, a new solving scheme is proposed where the solution is iteratively updated following the updating of the physics-driven neural network (PDNN), the hyperparameters of which are optimized by minimizing the loss function which incorporates the constraints from the collected scattered fields and the prior information about scatterers. Unlike data-driven neural network solvers, PDNN is trained only requiring the input of collected scattered fields and the computation of scattered fields corresponding to predicted solutions, thus avoids the generalization problem. Moreover, to accelerate the imaging efficiency, the subregion enclosing the scatterers is identified. Numerical and experimental results demonstrate that the proposed scheme has high reconstruction accuracy and strong stability, even when dealing with composite lossy scatterers. |
| title | Physics-Driven Neural Network for Solving Electromagnetic Inverse Scattering Problems |
| topic | Image and Video Processing Machine Learning Computational Physics |
| url | https://arxiv.org/abs/2507.16321 |