Joint Velocity Slope Diffusion Prior for Structurally Constrained Velocity Model Building
2026-07-06 • Artificial Intelligence
Artificial IntelligenceMachine Learning
AI summaryⓘ
The authors developed a new method to improve underground models used for finding oil and gas reservoirs by combining data from wells and surface measurements. Their approach uses information about the layers underground to guide how data from wells spreads through the model, making it more accurate along geological features. They tested their method on real and synthetic data and found it makes the model more consistent and realistic compared to older techniques. The method is also efficient enough to be used in practical scenarios.
velocity modelsreservoir characterizationwell-log dataplane-wave destructionstructural dipdiffusion samplingPDE regularizationViking GrabenDDIM sampling
Authors
Francesco Brandolin, Tariq Alkhalifah
Abstract
High-resolution velocity models are crucial for reservoir characterization and subsurface delineation. However, the band limited nature of our surface recorded data limits resolution. Utilizing well measurements to enhance the resolution of our subsurface models is an important objective. To this end, we present a diffusion-guided framework for structurally preconditioned velocity-model reconstruction from sparse well-log information. The proposed approach combines plane-wave PDE regularization, structurally preconditioned inversion, and measurement-guided diffusion posterior sampling within a unified formulation. Local structural slopes estimated through plane-wave destruction are used both to propagate well information along geological dip directions and to guide the diffusion sampling process through a joint velocity--slope generative prior. Numerical experiments on the Volve synthetic model and the Viking Graben field dataset demonstrate that the proposed framework improves structural continuity, lateral consistency, and geological realism compared with conventional structurally preconditioned inversion approaches while maintaining computationally practical inference through DDIM sampling.