WISE: full-Waveform variational Inference via Subsurface Extensions

Abstract

We introduce a probabilistic technique for full-waveform inversion, employing variational inference and conditional normalizing flows to quantify uncertainty in migration-velocity models and its impact on imaging. Our approach integrates generative artificial intelligence with physics-informed common-image gathers, reducing reliance on accurate initial velocity models. Considered case studies demonstrate its efficacy producing realizations of migration-velocity models conditioned by the data. These models are used to quantify amplitude and positioning effects during subsequent imaging.

References in corpus (7)

• Devito (v3.1.0): an embedded domain-specific language for finite differences and geophysical exploration
• 3D Bayesian Variational Full Waveform Inversion
• An introduction to variational inference in Geophysical inverse problems
• Learned multiphysics inversion with differentiable programming and machine learning
• De-risking geological carbon storage from high resolution time-lapse seismic to explainable leakage detection
• Probabilistic Bayesian optimal experimental design using conditional normalizing flows
• InvertibleNetworks.jl: A Julia package for scalable normalizing flows

Cited by in corpus (4)

• Controllable seismic velocity synthesis using generative diffusion models
• Time-lapse full-waveform permeability inversion: a feasibility study
• Back-Projection Diffusion: Solving the Wideband Inverse Scattering Problem with Diffusion Models
• Power-scaled Bayesian Inference with Score-based Generative Models