Multi-frequency progressive refinement for learned inverse scattering

Journal Article · 03 February 2025 · Journal of Computational Physics

DOI: https://doi.org/10.1016/j.jcp.2025.113809 · OSTI ID:2510906

Melia, Owen  ^[1]; Tsang, Olivia  ^[1]; Charisopoulos, Vasileios  ^[1]; Khoo, Yuehaw  ^[1]; Hoskins, Jeremy  ^[1]; Willett, Rebecca  ^[1]

---

1. University of Chicago, IL (United States)

Interpreting scattered acoustic and electromagnetic wave patterns is a computational task that enables remote imaging in a number of important applications, including medical imaging, geophysical exploration, sonar and radar detection, and nondestructive testing of materials. However, accurately and stably recovering an inhomogeneous medium from far-field scattered wave measurements is a computationally difficult problem, due to the nonlinear and non-local nature of the forward scattering process. We design a neural network, called Multi-Frequency Inverse Scattering Network (MFISNet), and a training method to approximate the inverse map from far-field scattered wave measurements at multiple frequencies. We consider three variants of MFISNet, with the strongest performing variant inspired by the recursive linearization method — a commonly used technique for stably inverting scattered wavefield data — that progressively refines the estimate with higher frequency content. MFISNet outperforms past methods in regimes with high-contrast, heterogeneous large objects, and inhomogeneous unknown backgrounds.

• Research Organization: University of Chicago, IL (United States)
• Sponsoring Organization: USDOE
• Grant/Contract Number: SC0022232
• OSTI ID: 2510906
• Journal Information: Journal of Computational Physics, Journal Name: Journal of Computational Physics Vol. 527; ISSN 0021-9991
• Publisher: ElsevierCopyright Statement
• Country of Publication: United States
• Language: English