Automatic Differentiation‐Based Full Waveform Inversion With Flexible Workflows

Abstract Full waveform inversion (FWI) is able to construct high‐resolution subsurface models by iteratively minimizing discrepancies between observed and simulated seismic data. However, its implementation can be rather involved for complex wave equations, objective functions, or regularization. Re...

Full description

Saved in:
Bibliographic Details
Main Authors: Feng Liu, Haipeng Li, Guangyuan Zou, Junlun Li
Format: Article
Language:English
Published: Wiley 2025-03-01
Series:Journal of Geophysical Research: Machine Learning and Computation
Subjects:
Online Access:https://doi.org/10.1029/2024JH000542
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850063228059516928
author Feng Liu
Haipeng Li
Guangyuan Zou
Junlun Li
author_facet Feng Liu
Haipeng Li
Guangyuan Zou
Junlun Li
author_sort Feng Liu
collection DOAJ
description Abstract Full waveform inversion (FWI) is able to construct high‐resolution subsurface models by iteratively minimizing discrepancies between observed and simulated seismic data. However, its implementation can be rather involved for complex wave equations, objective functions, or regularization. Recently, automatic differentiation (AD) has proven to be effective in simplifying solutions of various inverse problems, including FWI. In this study, we present an open‐source AD‐based FWI framework (ADFWI), which is designed to simplify the design, development, and evaluation of novel approaches in FWI with flexibility. The AD‐based framework not only includes forword modeling and associated gradient computations for wave equations in various types of media from isotropic acoustic to vertically or horizontally transverse isotropic elastic, but also incorporates a suite of objective functions, regularization techniques, and optimization algorithms. By leveraging state‐of‐the‐art AD, objective functions such as soft dynamic time warping and Wasserstein distance, which are difficult to apply in traditional FWI are also easily integrated into ADFWI. In addition, ADFWI is integrated with deep learning for implicit model reparameterization via neural networks, which not only introduces learned regularization but also allows rapid estimation of uncertainty through dropout. To manage high memory demands in large‐scale inversion associated with AD, the proposed framework adopts strategies such as mini‐batch and checkpointing. Through tests on synthetic and field data, we demonstrate the novelty, practicality and robustness of ADFWI, which can be used to address challenges in FWI and as a workbench for prompt experiments and development of new inversion strategies.
format Article
id doaj-art-2fa488a4803e4d6da048714d4fbbc6cd
institution DOAJ
issn 2993-5210
language English
publishDate 2025-03-01
publisher Wiley
record_format Article
series Journal of Geophysical Research: Machine Learning and Computation
spelling doaj-art-2fa488a4803e4d6da048714d4fbbc6cd2025-08-20T02:49:43ZengWileyJournal of Geophysical Research: Machine Learning and Computation2993-52102025-03-0121n/an/a10.1029/2024JH000542Automatic Differentiation‐Based Full Waveform Inversion With Flexible WorkflowsFeng Liu0Haipeng Li1Guangyuan Zou2Junlun Li3School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai ChinaLaboratory of Seismology and Physics of Earth's Interior, School of Earth and Space Sciences University of Science and Technology of China Hefei ChinaLaboratory of Seismology and Physics of Earth's Interior, School of Earth and Space Sciences University of Science and Technology of China Hefei ChinaLaboratory of Seismology and Physics of Earth's Interior, School of Earth and Space Sciences University of Science and Technology of China Hefei ChinaAbstract Full waveform inversion (FWI) is able to construct high‐resolution subsurface models by iteratively minimizing discrepancies between observed and simulated seismic data. However, its implementation can be rather involved for complex wave equations, objective functions, or regularization. Recently, automatic differentiation (AD) has proven to be effective in simplifying solutions of various inverse problems, including FWI. In this study, we present an open‐source AD‐based FWI framework (ADFWI), which is designed to simplify the design, development, and evaluation of novel approaches in FWI with flexibility. The AD‐based framework not only includes forword modeling and associated gradient computations for wave equations in various types of media from isotropic acoustic to vertically or horizontally transverse isotropic elastic, but also incorporates a suite of objective functions, regularization techniques, and optimization algorithms. By leveraging state‐of‐the‐art AD, objective functions such as soft dynamic time warping and Wasserstein distance, which are difficult to apply in traditional FWI are also easily integrated into ADFWI. In addition, ADFWI is integrated with deep learning for implicit model reparameterization via neural networks, which not only introduces learned regularization but also allows rapid estimation of uncertainty through dropout. To manage high memory demands in large‐scale inversion associated with AD, the proposed framework adopts strategies such as mini‐batch and checkpointing. Through tests on synthetic and field data, we demonstrate the novelty, practicality and robustness of ADFWI, which can be used to address challenges in FWI and as a workbench for prompt experiments and development of new inversion strategies.https://doi.org/10.1029/2024JH000542automatic differentiationfull waveform inversionwave equationdeep prioruncertainty estimation with dropoutflexible workflow
spellingShingle Feng Liu
Haipeng Li
Guangyuan Zou
Junlun Li
Automatic Differentiation‐Based Full Waveform Inversion With Flexible Workflows
Journal of Geophysical Research: Machine Learning and Computation
automatic differentiation
full waveform inversion
wave equation
deep prior
uncertainty estimation with dropout
flexible workflow
title Automatic Differentiation‐Based Full Waveform Inversion With Flexible Workflows
title_full Automatic Differentiation‐Based Full Waveform Inversion With Flexible Workflows
title_fullStr Automatic Differentiation‐Based Full Waveform Inversion With Flexible Workflows
title_full_unstemmed Automatic Differentiation‐Based Full Waveform Inversion With Flexible Workflows
title_short Automatic Differentiation‐Based Full Waveform Inversion With Flexible Workflows
title_sort automatic differentiation based full waveform inversion with flexible workflows
topic automatic differentiation
full waveform inversion
wave equation
deep prior
uncertainty estimation with dropout
flexible workflow
url https://doi.org/10.1029/2024JH000542
work_keys_str_mv AT fengliu automaticdifferentiationbasedfullwaveforminversionwithflexibleworkflows
AT haipengli automaticdifferentiationbasedfullwaveforminversionwithflexibleworkflows
AT guangyuanzou automaticdifferentiationbasedfullwaveforminversionwithflexibleworkflows
AT junlunli automaticdifferentiationbasedfullwaveforminversionwithflexibleworkflows