An Empirical Study of Large-Scale Data-Driven Full Waveform Inversion

TL;DR

This study empirically evaluates how large-scale data influences deep learning models for full waveform inversion, showing significant performance improvements and the importance of model capacity scaling.

Contribution

It provides the first empirical validation of big data benefits in FWI, demonstrating improved accuracy and generalization with large synthetic datasets.

Findings

Training on combined datasets improves MAE, MSE, SSIM metrics.

Model capacity must scale with data size for best results.

Largest model outperforms smaller ones significantly.

Abstract

This paper investigates the impact of big data on deep learning models to help solve the full waveform inversion (FWI) problem. While it is well known that big data can boost the performance of deep learning models in many tasks, its effectiveness has not been validated for FWI. To address this gap, we present an empirical study that investigates how deep learning models in FWI behave when trained on OpenFWI, a collection of large-scale, multi-structural, synthetic datasets published recently. In particular, we train and evaluate the FWI models on a combination of 10 2D subsets in OpenFWI that contain 470K pairs of seismic data and velocity maps in total. Our experiments demonstrate that training on the combined dataset yields an average improvement of 13.03% in MAE, 7.19% in MSE and 1.87% in SSIM compared to each split dataset, and an average improvement of 28.60%, 21.55% and 8.22% in the leave-one-out generalization test. We further demonstrate that model capacity needs to scale in accordance with data size for optimal improvement, where our largest model yields an average improvement of 20.06%, 13.39% and 0.72% compared to the smallest one.