What is it about?
Seismic reflections representing subsurface rock interfaces can be misaligned due to incomplete knowledge of the velocities of the formations. Therefore, we create synthetic seismic data examples with poor alignment and good alignment, and train a machine learning model on thousands of these examples to automatically align reflections. This model is then applied on real data and successfully improves the alignment and resolution.
Featured Image
Photo by Christopher Burns on Unsplash
Why is it important?
The amplitude trends of seismic reflections are often used to locate oil and gas deposits in the subsurface. If these reflections are mislaigned, then this type of analysis becomes difficult.
Read the Original
This page is a summary of: Automatic Conditioning of Marine Seismic Angle Stack Data With a Convolutional Neural Network, Interpretation, November 2024, Society of Exploration Geophysicists,
DOI: 10.1190/int-2024-0034.1.
You can read the full text:
Contributors
The following have contributed to this page
