Learned frequency-domain scattered wavefield solutions using neural operators

TL;DR

This paper introduces a neural operator-based method for frequency-domain scattered wavefield modeling in seismic imaging, addressing computational challenges and enabling scalable, accurate solutions across diverse velocities and larger domains.

Contribution

It presents a novel neural operator approach that incorporates source and frequency information, allowing scalable and accurate wavefield solutions in seismic applications.

Findings

Validated on OpenFWI datasets showing high accuracy

Demonstrated scalability to larger domains and higher frequencies

Reduced computational and memory requirements compared to traditional methods

Abstract

Solving the wave equation is essential to seismic imaging and inversion. The numerical solution of the Helmholtz equation, fundamental to this process, often encounters significant computational and memory challenges. We propose an innovative frequency-domain scattered wavefield modeling method employing neural operators adaptable to diverse seismic velocities. The source location and frequency information are embedded within the input background wavefield, enhancing the neural operator's ability to process source configurations effectively. In addition, we utilize a single reference frequency, which enables scaling from larger-domain forward modeling to higher-frequency scenarios, thereby improving our method's accuracy and generalization capabilities for larger-domain applications. Several tests on the OpenFWI datasets and realistic velocity models validate the accuracy and efficacy of our method as a surrogate model, demonstrating its potential to address the computational and memory limitations of numerical methods.