VBIM-Net: Variational Born Iterative Network for Inverse Scattering Problems
- 20 January 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-16
Abstract
Recently, studies have shown the potential of integrating field-type iterative methods with deep learning (DL) techniques in solving inverse scattering problems (ISPs). In this article, we propose a novel Variational Born Iterative Network, namely, VBIM-Net, to solve the full-wave ISPs with significantly improved structural rationality and inversion quality. The proposed VBIM-Net emulates the alternating updates of the total electric field and the contrast in the variational Born iterative method (VBIM) by multiple layers of subnetworks. We embed the analytical calculation of the contrast variation into each subnetwork, converting the scattered field residual into an approximate contrast variation and then enhancing it by a U-Net, thus avoiding the requirement of matched measurement dimension and grid resolution as in existing approaches. The total field and contrast of each layer’s output is supervised in the loss function of VBIM-Net, imposing soft physical constraints on the variables in the subnetworks, which benefits the model’s performance. In addition, we design a training scheme with extra noise to enhance the model’s stability. Extensive numerical results on synthetic and experimental data both verify the inversion quality, generalization ability, and robustness of the proposed VBIM-Net. This work may provide some new inspiration for the design of efficient field-type DL schemes.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62394292, U20A20158)
- Zhejiang Provincial Key Research and Development Program (2023C01021)
- Ministry of Industry and Information Technology (TC220H07E)
- Fundamental Research Funds for the Central Universities (226-2024-00069)
This publication has 42 references indexed in Scilit:
- Multifrequency electromagnetic geophysical tools for evaluating the hydrologic conditions and performance of evapotranspiration barriersJournal of Environmental Management, 2022
- Computational Methods for Electromagnetic Inverse Scattering2018
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Introduction to Ground Penetrating Radar2014
- Twofold subspace-based optimization method for solving inverse scattering problemsInverse Problems, 2009
- Free space experimental scattering database continuation: experimental set-up and measurement precisionInverse Problems, 2005
- A contrast source inversion methodInverse Problems, 1997
- A total variation enhanced modified gradient algorithm for profile reconstructionInverse Problems, 1995
- Associate memories for system identification: Inverse problems in remote sensingMathematical and Computer Modelling, 1990
- An iterative solution of the two‐dimensional electromagnetic inverse scattering problemInternational Journal of Imaging Systems and Technology, 1989