Physics-Consistent Data-driven Waveform Inversion with Adaptive Data Augmentation

TL;DR

This paper introduces a hybrid seismic waveform inversion method that combines physics-based models with data-driven data augmentation to improve accuracy and generalization in subsurface imaging.

Contribution

A novel physics-consistent data-driven waveform inversion approach that integrates data augmentation with physics-based modeling for enhanced seismic imaging.

Findings

Higher inversion accuracy compared to traditional methods

Improved generalization ability on synthetic seismic data

Effective incorporation of physics into data-driven training

Abstract

Seismic full-waveform inversion (FWI) is a nonlinear computational imaging technique that can provide detailed estimates of subsurface geophysical properties. Solving the FWI problem can be challenging due to its ill-posedness and high computational cost. In this work, we develop a new hybrid computational approach to solve FWI that combines physics-based models with data-driven methodologies. In particular, we develop a data augmentation strategy that can not only improve the representativity of the training set but also incorporate important governing physics into the training process and therefore improve the inversion accuracy. To validate the performance, we apply our method to synthetic elastic seismic waveform data generated from a subsurface geologic model built on a carbon sequestration site at Kimberlina, California. We compare our physics-consistent data-driven inversion method to both purely physics-based and purely data-driven approaches and observe that our method yields higher accuracy and greater generalization ability.