Westerngeco L.l.p.

Bp Corporation North America Inc.

Madhav Vyas

David Nichols

Everett C Mobley

Arvind Sharma

Qingqing Liao

A method includes receiving modelled seismic data that is to be recognized by the at least one classification and/or segmentation processor. The modelled seismic data can be represented within a transform domain. The method includes generating an output via the at least one processor based on the received modelled seismic data. The method also includes comparing the output of the at least one processor with a desired output. The method also includes modifying the at least one processor so that the output of the processor corresponds to the desired output.

Method and apparatus for performing de-aliasing using deep learning

Systems and methods include seismic data stacking derived from a set of image volumes. Stacking includes finding a sub-set of seismic image volumes (and in some implementations their respective stacking weights) or multiple realizations of sub-set of seismic image volumes from a given set that are consistent and similar to each other. Some or all of the input seismic image volumes can be stacked together as they would be with a conventional stack. However, the signal-to-noise ratio can be enhanced by only stacking those volumes that contain consistent and relevant information. Optimal stacking can utilize an algorithm that can be implemented in a moving window fashion.

Systems and methods for optimal stacking of seismic data

A technique includes processing first data indicative of a first image of a subsurface region of interest on a machine to generate second data indicative of a second image. The first image is derived from measurements of seismic waves, which propagate in a plurality of directions, and the second image is generated by partitioning the first image based on the directions. The technique includes processing the second data to determine a dip decomposition for each of the directions; and based on the dip decompositions and the directions, generating an angle domain common image gather.

Generating an angle domain common image gather

A method to correct errors in a conversion from time gather to angle gather using slant stacks wherein the slant stacking is performed along a direction that is normal to a dip or along three orthogonal directions. The slant stacking is performed in various domains.

Growing community of inventors

Houston, TX, United States of America

Madhav Vyas