A Neural Network Warm-Start Approach for the Inverse Acoustic Obstacle Scattering Problem
Preprint
Abstract
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.
Keywords
All Related Versions
This publication has 51 references indexed in Scilit:
- Inverse Acoustic and Electromagnetic Scattering Theory2019
- Globally convergent and adaptive finite element methods in imaging of buried objects from experimental backscattering radar measurementsJournal of Computational and Applied Mathematics, 2015
- Geophysical Retrieval, Inverse Problems in Remote Sensing2014
- A direct solver with O(N) complexity for integral equations on one-dimensional domainsFrontiers of Mathematics in China, 2012
- Inverse scattering by a continuation method with initial guesses from a direct imaging algorithmJournal of Computational Physics, 2007
- Qualitative Methods in Inverse Scattering Theory2006
- A fast direct solver for boundary integral equations in two dimensionsJournal of Computational Physics, 2005
- Hierarchical LU Decomposition-based Preconditioners for BEMComputing, 2004
- Linear Integral Equations1999
- Inverse Problems in Medical Imaging and Nondestructive Testing1997