Options
Approximate Bayesian Geophysical Inversion using Generative Modeling and Subset Simulation
Editeur(s)
David Ginsbourger
Niklas Linde
Date de parution
2020
Résumé
We present preliminary work on solving geophysical inverse problems by exploring
the latent space of a joint Generative Neural Network (GNN) model by Approximate Bayesian Computation (ABC) based on Subset Simulation (SuS). Given
pre-generated subsurface domains and their corresponding solver outputs, the GNN
surrogates the forward solver during inversion to quickly explore the input space
through SuS and locate regions of credible solutions. Akin to ABC methods, our
methodology allows to tune the similarity threshold between observed and candidate outputs. We explore how tuning this threshold influences the uncertainty
in the solutions, allowing to sample solutions with a selected diversity level. Our
initial tests were carried out with data from straight-ray (linear) tomography with
Gaussian priors on slowness fields and Gaussian versus Gumbel observation noise
distributions. We are presently testing the methodology on non-linear physics to
demonstrate its applicability in more general inversion settings.
the latent space of a joint Generative Neural Network (GNN) model by Approximate Bayesian Computation (ABC) based on Subset Simulation (SuS). Given
pre-generated subsurface domains and their corresponding solver outputs, the GNN
surrogates the forward solver during inversion to quickly explore the input space
through SuS and locate regions of credible solutions. Akin to ABC methods, our
methodology allows to tune the similarity threshold between observed and candidate outputs. We explore how tuning this threshold influences the uncertainty
in the solutions, allowing to sample solutions with a selected diversity level. Our
initial tests were carried out with data from straight-ray (linear) tomography with
Gaussian priors on slowness fields and Gaussian versus Gumbel observation noise
distributions. We are presently testing the methodology on non-linear physics to
demonstrate its applicability in more general inversion settings.
Nom de l'événement
Workshop Machine Learning and the Physical Sciences , NeurIPS2020
Lieu
https://ml4physicalsciences.github.io/2020/
Identifiants
Type de publication
Resource Types::text::conference output::conference proceedings::conference poster
Dossier(s) à télécharger
