DeepNIS: Deep Neural Network for Nonlinear Electromagnetic Inverse Scattering

TL;DR

DeepNIS introduces a novel deep neural network approach that significantly improves the quality and speed of nonlinear electromagnetic inverse scattering imaging, addressing challenges of nonlinearity and computational expense.

Contribution

This paper pioneers the connection between DNN architecture and iterative nonlinear EM inverse scattering methods, creating a new effective deep learning-based methodology.

Findings

Outperforms conventional methods in image quality

Reduces computational time significantly

Learns a general model for EM inverse scattering

Abstract

Nonlinear electromagnetic (EM) inverse scattering is a quantitative and super-resolution imaging technique, in which more realistic interactions between the internal structure of scene and EM wavefield are taken into account in the imaging procedure, in contrast to conventional tomography. However, it poses important challenges arising from its intrinsic strong nonlinearity, ill-posedness, and expensive computation costs. To tackle these difficulties, we, for the first time to our best knowledge, exploit a connection between the deep neural network (DNN) architecture and the iterative method of nonlinear EM inverse scattering. This enables the development of a novel DNN-based methodology for nonlinear EM inverse problems (termed here DeepNIS). The proposed DeepNIS consists of a cascade of multi-layer complexvalued residual convolutional neural network (CNN) modules. We numerically and experimentally demonstrate that the DeepNIS outperforms remarkably conventional nonlinear inverse scattering methods in terms of both the image quality and computational time. We show that DeepNIS can learn a general model approximating the underlying EM inverse scattering system. It is expected that the DeepNIS will serve as powerful tool in treating highly nonlinear EM inverse scattering problems over different frequency bands, involving large-scale and high-contrast objects, which are extremely hard and impractical to solve using conventional inverse scattering methods.