Schlumberger Technology Corporation

Cen Li

Aria Abubakar

Haibin Di

Hiren Maniar

Bruce Edward Cornish

Anisha Kaul

Leigh Truelove

Sunil Manikani

Zhenghan Deng

Stewart Smith

A method includes determining a top of salt (TOS) surface in a seismic volume based on a crossline direction of the seismic volume and an inline direction of the seismic volume. The method also includes determining a binary mask based upon the TOS surface. The method also includes sampling seismic data in the seismic volume to obtain a training seismic slice. The method also includes sampling the binary mask to obtain a mask slice. The method also includes selecting a first coordinate in the training seismic slice to produce a first tile. The method also includes selecting a second coordinate in the mask slice to produce a second tile. The method also includes generating or updating a model of the seismic volume based upon the first tile and the second tile.

Cascaded machine-learning workflow for salt seismic interpretation

A method includes receiving a seismic survey that includes a plurality of seismic slices. The method also includes converting the seismic slices into an embedding. The embedding includes one or more vectors. Each of the vectors includes more than 3 dimensions. The method also includes generating a plot based at least partially upon the embedding.

Quantifying diversity in seismic datasets

A computer-implemented method includes receiving a test seismic dataset associated with a known truth interpretation, receiving one or more hard constraints, training a machine learning system based on the test seismic dataset, the known truth interpretation, and the one or more hard constraints, determining an error value based on the training the machine learning system, adjusting the error value based on one or more soft constraints, updating the training of the machine learning system based on the adjusted error value, receiving a second seismic dataset after the updating the training; applying the second seismic dataset to the machine learning system to generate an interpretation of the second seismic dataset, generating a seismic image representing a subterranean domain based on the interpretation of the second seismic dataset, and outputting the seismic image.

Training a machine learning system using hard and soft constraints

A method is disclosed for determining a fault surface in a formation, comprising: determining a first plurality of crosscorrelation values for a 3D Volume associated, respectively, with a corresponding first plurality of 3D Volumes, and selecting a first minimum one of the first plurality of crosscorrelation values, a first derived fault segment corresponding to the first minimum one of the first plurality of crosscorrelation values, the first derived fault segment approximately lying on the fault surface and tending to determine the fault surface in the formation.

Method for producing underground deposits of hydrocarbon from an earth formation using fault interpretation including spline fault tracking

A volume rendering process is disclosed. Data including a plurality of voxels are recorded. Each voxel includes an opacity-adjusted value representative of a value of a parameter at a location within the volume adjusted by applying an opacity curve to the value. A computer is used to process such data. The process includes partitioning the plurality of voxels among a plurality of slices. Each slice corresponds to a respective region of the volume. For each slice, the process apportions the plurality of voxels associated with that slice among a plurality of cells associated with that slice. Each cell corresponds to a respective sub-region of the region associated with that slice. For each cell, the process determines that the cell is nontransparent if more than a predetermined number of the voxels associated with that cell have an opacity-adjusted value greater than a predetermined value. Otherwise the cell is determined to be transparent. The process stores a texture value for each voxel for only nontransparent cells and renders the stored texture values.

Growing community of inventors

Missouri City, TX, United States of America

Cen Li