Generalizable Neural Electromagnetic Inverse Scattering

2025-06-26

AI Summary

Electromagnetic inverse scattering problems (EISPs) suffer from poor generalization under sparse illumination (e.g., single-source excitation), and existing methods rely on case-specific optimization, limiting broad applicability. This paper proposes the first end-to-end, optimization-free, physics-driven two-stage neural framework. In Stage I, induced current is introduced as a universal intermediate physical representation to decouple the nonlinear scattering forward process from the ill-posed inversion. In Stage II, the relative permittivity is robustly reconstructed from the estimated current. To our knowledge, this is the first work to explicitly incorporate induced current into a deep learning architecture, synergistically integrating electromagnetic modeling, implicit geometric representation, and data-driven joint training. The method surpasses state-of-the-art approaches across diverse scenarios—achieving over 18% improvement in reconstruction accuracy—while maintaining high robustness to unseen targets and extreme sparsity (e.g., single transmitter) and enabling real-time, feedforward inference.

Technology Category

• Search and Optimization: Learning to Search
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Learning & Optimization for CV

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Solving Electromagnetic Inverse Scattering Problems (EISP) is fundamental in applications such as medical imaging, where the goal is to reconstruct the relative permittivity from scattered electromagnetic field. This inverse process is inherently ill-posed and highly nonlinear, making it particularly challenging. A recent machine learning-based approach, Img-Interiors, shows promising results by leveraging continuous implicit functions. However, it requires case-specific optimization, lacks generalization to unseen data, and fails under sparse transmitter setups (e.g., with only one transmitter). To address these limitations, we revisit EISP from a physics-informed perspective, reformulating it as a two stage inverse transmission-scattering process. This formulation reveals the induced current as a generalizable intermediate representation, effectively decoupling the nonlinear scattering process from the ill-posed inverse problem. Built on this insight, we propose the first generalizable physics-driven framework for EISP, comprising a current estimator and a permittivity solver, working in an end-to-end manner. The current estimator explicitly learns the induced current as a physical bridge between the incident and scattered field, while the permittivity solver computes the relative permittivity directly from the estimated induced current. This design enables data-driven training and generalizable feed-forward prediction of relative permittivity on unseen data while maintaining strong robustness to transmitter sparsity. Extensive experiments show that our method outperforms state-of-the-art approaches in reconstruction accuracy, generalization, and robustness. This work offers a fundamentally new perspective on electromagnetic inverse scattering and represents a major step toward cost-effective practical solutions for electromagnetic imaging.

Problem

• Reconstruct relative permittivity from scattered electromagnetic fields
• Address ill-posed and nonlinear challenges in inverse scattering
• Improve generalization and robustness in sparse transmitter setups

Innovation

• Two-stage inverse transmission-scattering process reformulation
• Generalizable physics-driven framework for EISP
• Current estimator and permittivity solver end-to-end