Learned Global Optimization for Inverse Scattering Problems -- Matching Global Search with Computational Efficiency

TL;DR

This paper introduces a novel, efficient global optimization method for nonlinear microwave inverse scattering problems, combining AI-driven search with a digital twin to improve robustness and computational speed.

Contribution

It presents a System-by-Design framework that integrates a customized evolutionary algorithm with a Gaussian Process-based digital twin for the first time in this context.

Findings

Effective and robust inversion demonstrated through numerical tests.

Significant reduction in computational time compared to traditional methods.

Outperforms state-of-the-art inversion techniques in accuracy and efficiency.

Abstract

The computationally-efficient solution of fully non-linear microwave inverse scattering problems (ISPs) is addressed. An innovative System-by-Design (SbD) based method is proposed to enable, for the first time to the best of the authors knowledge, an effective, robust, and time-efficient exploitation of an evolutionary algorithm (EA) to perform the global minimization of the data-mismatch cost function. According to the SbD paradigm as suitably applied to ISPs, the proposed approach founds on (i) a smart re-formulation of the ISP based on the definition of a minimum-dimensionality and representative set of degrees-of-freedom (DoFs) and on (ii) the artificial-intelligence (AI)-driven integration of a customized global search technique with a digital twin (DT) predictor based on the Gaussian Process (GP) theory. Representative numerical and experimental results are provided to assess the effectiveness and the efficiency of the proposed approach also in comparison with competitive state-of-the-art inversion techniques.