Shape reconstruction of acoustic obstacle with linear sampling method and neural network

Abstract

We consider the inverse scattering problem of reconstructing the boundary of an obstacle by using far-field data. With the plane wave as the incident wave, a priori information of the impenetrable obstacle can be obtained via the linear sampling method. We have constructed the shape parameter inversion model based on a neural network to reconstruct the obstacle. Numerical experimental results demonstrate that the model proposed in this paper is robust and performs well with a small number of observation directions.

Keywords

• inverse acoustic scattering problems
• linear sampling method
• neural network
• shape reconstruction of obstacles