Skip to main content

ORIGINAL RESEARCH article

Front. Earth Sci.
Sec. Solid Earth Geophysics
Volume 12 - 2024 | doi: 10.3389/feart.2024.1472303

Full waveform inversion based on deep learning and the phase-preserving symplectic partitioned Runge-Kutta method

Provisionally accepted
Xianxiang Leng Xianxiang Leng Yanjie Zhou Yanjie Zhou *Xueyuan Huang Xueyuan Huang Xijun He Xijun He Tianming Cao Tianming Cao
  • Beijing Technology and Business University, Beijing, Beijing Municipality, China

The final, formatted version of the article will be published soon.

    To obtain more accurate full waveform inversion results, we present a forward modeling method with minimal phase error, low numerical dispersion, and high computational efficiency. To solve the 2D acoustic wave equation, we utilize a finitedifference (FD) scheme with optimized coefficients for spatial discretization, combined with a phase-preserving symplectic partitioned Runge-Kutta method for temporal discretization. This results in the development of the optimized symplectic partitioned Runge-Kutta (OSPRK) forward modeling method. We further apply the OSPRK method in conjunction with a recurrent neural network (RNN) for full waveform inversion (FWI). Our study explores the impact of various loss functions, Nadam optimizer parameters, and the incorporation of physical information operators on inversion performance. Numerical experiments demonstrate that the OSPRK method significantly reduces numerical dispersion compared to traditional FD methods. The Log-Cosh loss function offers superior stability across different learning rates, while the Nesterov-accelerated Adaptive Moment Estimation (Nadam) optimizer with optimized parameters greatly enhances convergence speed and inversion accuracy.Furthermore, the inclusion of physical information operators markedly improves inversion outcomes.

    Keywords: OSPRK method, FWI, RNN, Nadam optimizer, Log_Cosh loss, the physical information operator

    Received: 29 Jul 2024; Accepted: 04 Nov 2024.

    Copyright: © 2024 Leng, Zhou, Huang, He and Cao. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Yanjie Zhou, Beijing Technology and Business University, Beijing, 102488, Beijing Municipality, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.