Automatic Differentiation-based Full Waveform Inversion with Flexible Workflows

TL;DR

This paper introduces an open-source automatic differentiation-based framework for full waveform inversion (FWI) that simplifies complex implementations, integrates advanced objective functions, and combines deep learning techniques for improved seismic imaging.

Contribution

The paper presents ADFWI, a flexible, open-source AD-based FWI framework that supports various wave equations, objective functions, regularizations, and deep learning integration, enhancing ease of development and experimentation.

Findings

Demonstrates robustness and practicality of ADFWI in seismic inversion.

Enables easy integration of complex objective functions like Wasserstein distance.

Supports large-scale inversion with memory management strategies.

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 comprehensive evaluations, 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 the development of new inversion strategies.