InversionNet: A Real-Time and Accurate Full Waveform Inversion with CNNs and continuous CRFs

TL;DR

This paper introduces InversionNet, a CNN-based method combined with CRFs for real-time, high-resolution full waveform inversion that overcomes computational costs and resolution issues of traditional techniques.

Contribution

The paper presents a novel CNN-CRF framework that directly learns the inversion operator, enabling faster and more accurate velocity structure recovery without explicit forward modeling.

Findings

Significantly improved inversion accuracy

Reduced computational time

Effective structural predictions with CNN-CRF

Abstract

Full-waveform inversion problems are usually formulated as optimization problems, where the forward-wave propagation operator $f$ maps the subsurface velocity structures to seismic signals. The existing computational methods for solving full-waveform inversion are not only computationally expensive, but also yields low-resolution results because of the ill-posedness and cycle skipping issues of full-waveform inversion. To resolve those issues, we employ machine-learning techniques to solve the full-waveform inversion. Specifically, we focus on applying the convolutional neural network~(CNN) to directly derive the inversion operator $f^{-1}$ so that the velocity structure can be obtained without knowing the forward operator $f$. We build a convolutional neural network with an encoder-decoder structure to model the correspondence from seismic data to subsurface velocity structures. Furthermore, we employ the conditional random field~(CRF) on top of the CNN to generate structural predictions by modeling the interactions between different locations on the velocity model. Our numerical examples using synthetic seismic reflection data show that the propose CNN-CRF model significantly improve the accuracy of the velocity inversion while the computational time is reduced.