Multiscale Data-driven Seismic Full-waveform Inversion with Field Data Study

TL;DR

This paper introduces a multiscale data-driven seismic FWI method using convolutional neural networks, significantly reducing computation time and improving accuracy over traditional physics-based approaches, validated on synthetic and field data.

Contribution

The paper develops a novel multiscale neural network approach for seismic FWI, utilizing synthetic training data generated from natural images to enhance inversion efficiency and accuracy.

Findings

Reduces computation time compared to traditional FWI

Achieves more accurate subsurface models

Validated on both synthetic and field data

Abstract

Seismic full-waveform inversion (FWI), which uses iterative methods to estimate high-resolution subsurface models from seismograms, is a powerful imaging technique in exploration geophysics. In recent years, the computational cost of FWI has grown exponentially due to the increasing size and resolution of seismic data. Moreover, it is a non-convex problem and can encounter local minima due to the limited accuracy of the initial velocity models or the absence of low frequencies in the measurements. To overcome these computational issues, we develop a multiscale data-driven FWI method based on fully convolutional networks (FCN). In preparing the training data, we first develop a real-time style transform method to create a large set of synthetic subsurface velocity models from natural images. We then develop two convolutional neural networks with encoder-decoder structure to reconstruct the low- and high-frequency components of the subsurface velocity models, separately. To validate the performance of our data-driven inversion method and the effectiveness of the synthesized training set, we compare it with conventional physics-based waveform inversion approaches using both synthetic and field data. These numerical results demonstrate that, once our model is fully trained, it can significantly reduce the computation time, and yield more accurate subsurface velocity models in comparison with conventional FWI.