Rapid Bayesian Seismic Tomography using Graph Mixture Density Networks

TL;DR

This paper introduces graph mixture density networks (GMDNs) that leverage graph neural networks to efficiently estimate Bayesian posterior distributions in seismic tomography, handling variable data sizes more flexibly than traditional methods.

Contribution

The study presents a novel combination of GNNs with MDNs to improve seismic tomography uncertainty quantification, especially for variable data scenarios.

Findings

GMDNs produce posterior PDFs comparable to MCMC.

GMDNs operate at significantly lower computational cost.

Applicable to both synthetic and real seismic data.

Abstract

Seismic tomography is a methodology to image subsurface properties of the Earth. In order to better interpret the resulting images, it is important to assess uncertainty in the results. Mixture density networks (MDNs) provide an efficient way to estimate Bayesian posterior probability density functions (pdfs) that describe the uncertainty of tomographic images. However, the method can only be applied in cases where the number of data is fixed, and consequently a large number of practical applications that have variable data sizes cannot be solved. To resolve this issue, we introduce graph neural networks (GNNs) to solve seismic tomographic problems. Graphs are data structure which provides flexible representation of complex, variable systems. GNNs are neural networks that manipulates graph data, and can be combined with MDNs (called graph MDNs) to provide efficient estimates of posterior pdfs for graph data. In this study we apply graph MDNs to seismic tomography by representing travel time data with a graph. We demonstrate the method using both synthetic and real data, and compare the results with those obtained using Markov chain Monte Carlo (McMC). The results show that graph MDNs can provide comparable posterior pdfs to those obtained using McMC at significantly lower cost. We thus conclude that graph MDNs can be used in a range of practical applications that require many similar seismic tomographic problems with different number of data to be solved.