A Direct Sampling-Based Deep Learning Approach for Inverse Medium Scattering Problems

TL;DR

This paper introduces a novel deep learning approach based on direct sampling methods for solving inverse medium scattering problems, enhancing reconstruction quality and robustness to noise.

Contribution

It combines deep learning with the direct sampling method using U-Net to improve scatterer reconstruction in IMSP, which is computationally efficient and noise-robust.

Findings

High-quality reconstructions with multiple data inputs

Robust performance under various noise levels

Efficient and easy-to-implement method

Abstract

In this work, we focus on the inverse medium scattering problem (IMSP), which aims to recover unknown scatterers based on measured scattered data. Motivated by the efficient direct sampling method (DSM) introduced in [23], we propose a novel direct sampling-based deep learning approach (DSM-DL)for reconstructing inhomogeneous scatterers. In particular, we use the U-Net neural network to learn the relation between the index functions and the true contrasts. Our proposed DSM-DL is computationally efficient, robust to noise, easy to implement, and able to naturally incorporate multiple measured data to achieve high-quality reconstructions. Some representative tests are carried out with varying numbers of incident waves and different noise levels to evaluate the performance of the proposed method. The results demonstrate the promising benefits of combining deep learning techniques with the DSM for IMSP.