Improved Physics-Driven Neural Network for Solving Inverse Scattering Problems
- 10 April 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Antennas and Propagation
- Vol. 74 (7) , 6944-6953
Abstract
This paper presents an improved physics-driven neural network (IPDNN) framework for solving electromagnetic inverse scattering problems (ISPs). Unlike data-driven solvers that require large labeled datasets and often suffer from limited generalization, the proposed method performs instance-wise optimization under electromagnetic governing equations and measured scattered-field constraints. Three improvements over the original PDNN framework are introduced. First, a Gaussian-localized oscillation-suppressing window (GLOW) activation function is designed to stabilize convergence and enable a lightweight yet accurate network architecture. Second, a dynamic scatter subregion identification strategy is further developed to adaptively refine the computational domain, preventing missed detections and reducing computational cost. Third, transfer learning is incorporated to extend the solver’s applicability to practical scenarios, integrating the physical interpretability of iterative algorithms with the approximation capability of neural networks. Numerical and experimental results on representative Fresnel datasets show that the proposed IPDNN achieves up to a 57% reduction in reconstruction error while maintaining robust performance under noise levels up to 50%. Under the current implementation, the proposed FCN-based realization also requires substantially less training memory than the original PDNN. These results demonstrate that IPDNN provides a more accurate and practically extensible physics-driven framework for electromagnetic inverse scattering.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62201469)
- National Natural Science Foundation of China (62305379)
This publication has 46 references indexed in Scilit:
- Physics-infused deep neural network for solution of non-associative Drucker–Prager elastoplastic constitutive modelJournal of the Mechanics and Physics of Solids, 2024
- Invariance embedded physics-infused deep neural network-based sub-grid scale models for turbulent flowsEngineering Applications of Artificial Intelligence, 2023
- Deep learning-accelerated computational framework based on Physics Informed Neural Network for the solution of linear elasticityNeural Networks, 2023
- A data-driven physics-constrained deep learning computational framework for solving von Mises plasticityEngineering Applications of Artificial Intelligence, 2023
- Computational Methods for Electromagnetic Inverse Scattering2018
- Convergence analyses of the born iterative method and the distorted born iterative methodNumerical Functional Analysis and Optimization, 1999
- A contrast source inversion methodInverse Problems, 1997
- Beyond the Born and Rytov approximations: A nonlinear approach to electromagnetic scatteringJournal of Geophysical Research, 1993
- Nonlinear total variation based noise removal algorithmsPhysica D: Nonlinear Phenomena, 1992
- An iterative solution of the two‐dimensional electromagnetic inverse scattering problemInternational Journal of Imaging Systems and Technology, 1989