Saved in:
Bibliographic Details
Main Authors: Du, Yutong, Liu, Zicheng, Wu, Bo, Kou, Jingwei, Li, Hang, Li, Changyou, Zong, Yali, Qi, Bo
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.09333
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915930863304704
author Du, Yutong
Liu, Zicheng
Wu, Bo
Kou, Jingwei
Li, Hang
Li, Changyou
Zong, Yali
Qi, Bo
author_facet Du, Yutong
Liu, Zicheng
Wu, Bo
Kou, Jingwei
Li, Hang
Li, Changyou
Zong, Yali
Qi, Bo
contents This paper presents an improved physics-driven neural network (IPDNN) framework for solving electromagnetic inverse scattering problems (ISPs). A new Gaussian-localized oscillation-suppressing window (GLOW) activation function is introduced to stabilize convergence and enable a lightweight yet accurate network architecture. A dynamic scatter subregion identification strategy is further developed to adaptively refine the computational domain, preventing missed detections and reducing computational cost. Moreover, transfer learning is incorporated to extend the solver's applicability to practical scenarios, integrating the physical interpretability of iterative algorithms with the real-time inference capability of neural networks. Numerical simulations and experimental results demonstrate that the proposed solver achieves superior reconstruction accuracy, robustness, and efficiency compared with existing state-of-the-art methods.
format Preprint
id arxiv_https___arxiv_org_abs_2512_09333
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Improved Physics-Driven Neural Network to Solve Inverse Scattering Problems
Du, Yutong
Liu, Zicheng
Wu, Bo
Kou, Jingwei
Li, Hang
Li, Changyou
Zong, Yali
Qi, Bo
Machine Learning
This paper presents an improved physics-driven neural network (IPDNN) framework for solving electromagnetic inverse scattering problems (ISPs). A new Gaussian-localized oscillation-suppressing window (GLOW) activation function is introduced to stabilize convergence and enable a lightweight yet accurate network architecture. A dynamic scatter subregion identification strategy is further developed to adaptively refine the computational domain, preventing missed detections and reducing computational cost. Moreover, transfer learning is incorporated to extend the solver's applicability to practical scenarios, integrating the physical interpretability of iterative algorithms with the real-time inference capability of neural networks. Numerical simulations and experimental results demonstrate that the proposed solver achieves superior reconstruction accuracy, robustness, and efficiency compared with existing state-of-the-art methods.
title Improved Physics-Driven Neural Network to Solve Inverse Scattering Problems
topic Machine Learning
url https://arxiv.org/abs/2512.09333