Machine learning based data retrieval for inverse scattering problems with incomplete data

TL;DR

This paper introduces a machine learning approach using CNNs to improve data retrieval in inverse scattering problems with incomplete data, enhancing reconstruction quality in limited data scenarios.

Contribution

It presents a novel CNN-based scheme for inverse scattering with incomplete data, addressing practical limitations like limited aperture and phaseless measurements.

Findings

Effective reconstruction with limited-aperture data

Robustness to phaseless far-field data

Numerical experiments confirm promising results

Abstract

We are concerned with the inverse scattering problems associated with incomplete measurement data. It is a challenging topic of increasing importance in many practical applications. Based on a prototypical working model, we propose a machine learning based inverse scattering scheme, which integrates a CNN (convolution neural network) for the data retrieval. The proposed method can effectively cope with the reconstruction under limited-aperture and/or phaseless far-field data. Numerical experiments verify the promising features of our new scheme.