English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Solving inverse problems involving measurement noise and modeling errorsrequires regularization in order to avoid data overfit. Geophysical inverseproblems, in which the Earth's highly heterogeneous structure is unknown,present a challenge in encoding prior knowledge through analytical expressions.Our main contribution is a generative-model-based regularization approach,robust to out-of-distribution data, which exploits the prior knowledge embeddedin existing data and model pairs. Utilizing an amortized variational inferenceobjective, a conditional normalizing flow (NF) is pretrained on pairs of low-and high-fidelity migrated images in order to achieve a low-fidelityapproximation to the seismic imaging posterior distribution for previouslyunseen data. The NF is used after pretraining to reparameterize the unknownseismic image in an inversion scheme involving physics-guided data misfit and aGaussian prior on the NF latent variable. Solving this optimization problemwith respect to the latent variable enables us to leverage the benefits ofdata-driven conditional priors whilst being informed by physics and data. Thenumerical experiments demonstrate that the proposed inversion scheme producesseismic images with limited artifacts when dealing with noisy andout-of-distribution data.

Wave-equation-based inversion with amortized variational Bayesian inference