EUVIMEDEUVIMED entdecken
Crossref

A neural network warm-start approach for the inverse acoustic obstacle scattering problem

Mo Zhou, Jiequn Han, Manas Rachh, Carlos Borges

Journal of Computational Physics · 2023-10 · 490 · 112341

DOI: 10.1016/j.jcp.2023.112341 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Computational Physics, 2023-10. Verfasst von Mo Zhou und 3 weiteren Autor:innen. Die Arbeit wurde bisher 27-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Office of Naval Research.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We consider the inverse acoustic obstacle problem for sound-soft star-shaped obstacles in two dimensions wherein the boundary of the obstacle is determined from measurements of the scattered field at a collection of receivers outside the object. One of the standard approaches for solving this problem is to reformulate it as an optimization problem: finding the boundary of the domain that minimizes the $L^2$ distance between computed values of the scattered field and the given measurement data. The optimization problem is computationally challenging since the local set of convexity shrinks with increasing frequency and results in an increasing number of local minima in the vicinity of the true solution. In many practical experimental settings, low frequency measurements are unavailable due to limitations of the experimental setup or the sensors used for measurement. Thus, obtaining a good initial guess for the optimization problem plays a vital role in this environment. We present a neural network warm-start approach for solving the inverse scattering problem, where an initial guess for the optimization problem is obtained using a trained neural network. We demonstrate the effectiveness of our method with several numerical examples. For high frequency problems, this approach outperforms traditional iterative methods such as Gauss-Newton initialized without any prior (i.e., initialized using a unit circle), or initialized using the solution of a direct method such as the linear sampling method. The algorithm remains robust to noise in the scattered field measurements and also converges to the true solution for limited aperture data. However, the number of training samples required to train the neural network scales exponentially in frequency and the complexity of the obstacles considered. We conclude with a discussion of this phenomenon and potential directions for future research.

Förderung

  • Office of Naval Research

Zitieren

APA

Zhou, M., Han, J., Rachh, M., & Borges, C. (2023). A neural network warm-start approach for the inverse acoustic obstacle scattering problem. Journal of Computational Physics, 490, 112341. https://doi.org/10.1016/j.jcp.2023.112341

Vancouver

Zhou M, Han J, Rachh M, Borges C. A neural network warm-start approach for the inverse acoustic obstacle scattering problem. Journal of Computational Physics. 2023;490:112341. doi:10.1016/j.jcp.2023.112341

BibTeX
@article{Zhou2023,
  author = {Zhou, Mo and Han, Jiequn and Rachh, Manas and Borges, Carlos},
  title = {A neural network warm-start approach for the inverse acoustic obstacle scattering problem},
  journal = {Journal of Computational Physics},
  year = {2023},
  volume = {490},
  pages = {112341},
  doi = {10.1016/j.jcp.2023.112341}
}
Kostenlos starten →