Neural Born Iteration Method For Solving Inverse Scattering Problems: 2D Cases
This is an incremental improvement for computational physics and imaging applications, offering a neural network-based approach to solve inverse scattering problems.
The paper tackled 2D inverse scattering problems by proposing NeuralBIM, a method that uses convolutional neural networks to emulate the traditional Born iterative method, with supervised and unsupervised schemes; numerical and experimental results validated its efficacy, though no concrete numbers were provided.
In this paper, we propose the neural Born iterative method (NeuralBIM) for solving 2D inverse scattering problems (ISPs) by drawing on the scheme of physics-informed supervised residual learning (PhiSRL) to emulate the computing process of the traditional Born iterative method (TBIM). NeuralBIM employs independent convolutional neural networks (CNNs) to learn the alternate update rules of two different candidate solutions regarding the residuals. Two different schemes are presented in this paper, including the supervised and unsupervised learning schemes. With the data set generated by the method of moments (MoM), supervised NeuralBIM are trained with the knowledge of total fields and contrasts. Unsupervised NeuralBIM is guided by the physics-embedded objective function founding on the governing equations of ISPs, which results in no requirement of total fields and contrasts for training. Numerical and experimental results further validate the efficacy of NeuralBIM.