Learned iterative solvers for the Helmholtz equation

TitleLearned iterative solvers for the Helmholtz equation
Publication TypeSubmitted
Year of Publication2019
AuthorsGabrio Rizzuti, Ali Siahkoohi, Felix J. Herrmann
KeywordsHelmholtz, Iterative, machine learning, private
Abstract

We propose a ‘learned’ iterative solver for the Helmholtz equation, by combining traditional Krylov-based solvers with machine learning. The method is, in principle, able to circumvent the shortcomings of classical iterative solvers, and has clear advantages over purely data-driven ap- proaches. We demonstrate the effectiveness of this approach under a 1.5-D assumption, when ade- quate a priori information about the velocity distribution is known.

Notes

Submitted to EAGE on January 15, 2019

URLhttps://www.slim.eos.ubc.ca/Publications/Private/Submitted/2019/rizzuti2019EAGElis/rizzuti2019EAGElis.pdf
Citation Keyrizzuti2019EAGElis