A deep-learning based Bayesian approach to seismic imaging and uncertainty quantification

TitleA deep-learning based Bayesian approach to seismic imaging and uncertainty quantification
Publication TypePresentation
Year of Publication2020
AuthorsAli Siahkoohi, Gabrio Rizzuti, Felix J. Herrmann
Keywordsdeep learning, seismic imaging, stochastic gradient Langevin dynamics, Uncertainty quantification

Uncertainty quantification is essential when dealing with ill-conditioned inverse problems due to the inherent nonuniqueness of the solution. Bayesian approaches allow us to determine how likely an estimation of the unknown parameters is via formulating the posterior distribution. Unfortunately, it is often not possible to formulate a prior distribution that precisely encodes our prior knowledge about the unknown. Furthermore, adherence to handcrafted priors may greatly bias the outcome of the Bayesian analysis. To address this issue, we propose to use the functional form of a randomly initialized convolutional neural network as an implicit structured prior, which is shown to promote natural images and excludes images with unnatural noise. In order to incorporate the model uncertainty into the final estimate, we sample the posterior distribution using stochastic gradient Langevin dynamics and perform Bayesian model averaging on the obtained samples. Our synthetic numerical experiment verifies that deep priors combined with Bayesian model averaging are able to partially circumvent imaging artifacts and reduce the risk of overfitting in the presence of extreme noise. Finally, we present pointwise variance of the estimates as a measure of uncertainty, which coincides with regions that are more difficult to image.


(SEG Student Chapter)

Citation Keysiahkoohi2020SEGCHAPTERGTdlbuq