Acoustic field estimation with differentiable physics

Samuel Arturo Verburg Riezu, Efren Fernandez Grande, Peter Gerstoft

Keywords: differentiable physics, sparsity-promoting constraint, acoustic field

TL;DR: Differentiable physics is used to estimate acoustic fields from a limited number of spatially distributed observations with sparsity-promoting constraints.

Abstract: This work introduces a differentiable physics approach to estimate acoustic fields from a limited number of spatially distributed observations. The initial conditions of the wave equation are approximated with a neural network, and the differential operator is computed with a differentiable numerical solver. We introduce an additional sparsity-promoting constraint to achieve meaningful solutions even under severe undersampling conditions. Numerical experiments demonstrate that the proposed approach can reconstruct sound fields under extreme data scarcity.

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 4