Granted Patent B2

US 12,360,272 · App. 17/252,484 · Granted Jul 15, 2025

Inventors: Anisha Kaul (Houston, TX); Cen Li (Missouri City, TX); Hiren Maniar (Houston, TX); Aria Abubakar (Sugar Land, TX)

Assignee: SCHLUMBERGER TECHNOLOGY CORPORATION

G01V1/302G01V1/50G06N20/00G01V2210/1234G01V2210/64

Abstract

Claims (82)

1. A method, comprising:

training a first machine learning model using data from a crossline direction and an inline direction of a seismic volume;

determining, using the first machine learning model, a top of salt (TOS) surface in the seismic volume based on crossline direction slices of the seismic volume and inline direction slices of the seismic volume;

determining a binary mask based upon the determined TOS surface;

initializing training data of the seismic volume based on output from the trained first machine learning model;

determining a depth in the seismic volume above which a predicted salt surface has a predetermined level of clarity;

sampling seismic data in the seismic volume in a depth direction to obtain a training seismic slice, wherein the training seismic slice includes information from the crossline direction, the inline direction, and the depth direction;

sampling the binary mask in the depth direction to obtain a mask slice;

selecting a first coordinate in the training seismic slice to produce a first tile;

selecting a second coordinate in the mask slice to produce a second tile;

updating the training data of the seismic volume based upon the first tile and the second tile;

training a second machine learning model using the updated training data;

determining, using the second machine learning model, a presence of a salt body in an evaluation seismic slice;

generating, by the second machine learning model, a three-dimensional (3D) model of a subterranean formation with the salt body delineated in the seismic volume;

displaying the 3D model of the subterranean formation with the salt body in the seismic volume;

determining, based on the 3D model of the subterranean formation, fluid flow characteristics of a reservoir in a field of the subterranean formation; and

controlling, based on the 3D model of the subterranean formation, drilling in the reservoir.

2. The method of claim 1 , wherein the seismic data is sampled in from a top of the seismic volume to the depth to obtain the training seismic slice.

3. The method of claim 2 , further comprising sampling the seismic data in the seismic volume to obtain the evaluation seismic slice, wherein the seismic data is sampled from the top of the seismic volume to a bottom of the seismic volume to obtain the evaluation seismic slice, and wherein the depth is between the top and the bottom.

4. The method of claim 1 , further comprising generating, by the second machine learning model, a three-dimensional (3D) matrix based upon the evaluation seismic slice, wherein the 3D matrix indicates the presence of the salt body.

5. The method of claim 4 , further comprising:

extracting, by the second machine learning model, a geobody from the 3D matrix; and

extracting, by the second machine learning model, a surface from the geobody.

6. The method of claim 5 , further comprising determining, by the second machine learning model, a presence of hydrocarbons in the seismic volume based upon the 3D matrix, the geobody, the surface, or a combination thereof.

7. The method of claim 1 , further comprising:

sending, using an acoustic energy source, sound vibrations into a subsurface in the field; and

receiving, in response to sending the sound vibrations, a seismic survey of the seismic volume with electric signals embedded with information of the subsurface captured and recorded from seismic wave reflections off the subsurface.

8. A method, comprising:

training a first machine learning model using data from a crossline direction and an inline direction of a seismic volume;

determining, using the first machine learning model, a top of salt (TOS) surface in the seismic volume based on crossline direction slices of the seismic volume and inline direction slices of the seismic volume;

determining a binary mask based upon the determined TOS surface;

initializing training data of the seismic volume based on output from the trained first machine learning model;

determining a depth in the seismic volume above which a predicted salt surface has a predetermined level of clarity;

sampling seismic data in the seismic volume in a depth direction to obtain a training seismic slice, wherein the training seismic slice includes information from the crossline direction, the inline direction, and the depth direction;

sampling the binary mask in the depth direction to obtain a mask slice;

selecting a first coordinate in the training seismic slice to produce a first tile;

selecting a second coordinate in the mask slice to produce a second tile;

updating the training data of the seismic volume based upon the first tile and the second tile

training a second machine learning model using the updated training data;

sampling, by the second machine learning model, the seismic data in the seismic volume to obtain an evaluation seismic slice;

determining, by the second machine learning model, a presence of a salt body in the evaluation seismic slice based upon the seismic data in the evaluation seismic slice;

generating, by the second machine learning model, a three-dimensional (3D) matrix based upon the evaluation seismic slice, wherein the 3D matrix indicates the presence of the salt body;

generating, by the second machine learning model, a 3D model of a subterranean formation with the salt body delineated in the seismic volume;

displaying the 3D model of the subterranean formation with the salt body identified in the evaluation seismic slice;

determining, based on the 3D model of the subterranean formation, fluid flow reservoir characteristics of a reservoir in a field of the subterranean formation; and

controlling, based on the 3D model of the subterranean formation, drilling in the reservoir.

9. The method of claim 8 , wherein the binary mask comprises a binary two-dimensional (2D) matrix.

10. The method of claim 8 , wherein the seismic data is sampled in a downward direction from a top of the seismic volume to the depth to obtain the training seismic slice, and wherein the seismic data is sampled in the downward direction from the top of the seismic volume to a bottom of the seismic volume to obtain the evaluation seismic slice, wherein the depth is between the top and the bottom.

11. The method of claim 8 , wherein the first coordinate and the second coordinate have a common X value and a common Y value.

12. The method of claim 11 , further comprising performing a plurality of recursions on the first tile and the second tile for a plurality of X values and a plurality of Y values.

13. The method of claim 8 , further comprising performing a plurality of recursions on the training seismic slice and the mask slice.

14. The method of claim 8 , wherein the 3D matrix has a same size and shape as the seismic volume.

15. The method of claim 8 , further comprising performing a plurality of recursions on the evaluation seismic slice.

16. The method of claim 8 , further comprising extracting, by the second machine learning model, a geobody from the 3D matrix.

17. The method of claim 16 , further comprising extracting, by the second machine learning model, a surface from the geobody.

18. The method of claim 17 , further comprising determining, by the second machine learning model, a presence of hydrocarbons in the seismic volume based upon the 3D matrix, the geobody, the surface, or a combination thereof.

19. A computing system comprising:

one or more processors; and

a memory system comprising one or more non-transitory computer-readable media storing instructions that, when executed by at least one of the one or more processors, cause the computing system to perform operations, the operations comprising:

training a first machine learning model using data from a crossline direction and an inline direction of a seismic volume;

determining, using the first machine learning model, a top of salt (TOS) surface in the seismic volume based upon crossline direction slices of the seismic volume and inline direction slices of the seismic volume;

determining a binary mask based upon the determined TOS surface, wherein the binary mask comprises a binary two-dimensional (2D) matrix;

initializing training data of the seismic volume based on output of the trained first machine learning model;

sampling seismic data in the seismic volume to a first depth in the seismic volume above which a predicted salt surface has a predetermined level of clarity to obtain a training seismic slice, wherein the training seismic slice includes information from the crossline direction, the inline direction, and a depth direction;

sampling the binary mask to obtain a mask slice;

selecting a first coordinate in the training seismic slice to produce a first tile;

selecting a second coordinate in the mask slice to produce a second tile;

updating the training data of the seismic volume based upon the first tile and the second tile;

training a second machine learning model using the updated training data;

sampling, by the second machine learning model, the seismic data in the seismic volume to a second depth to obtain an evaluation seismic slice, wherein the second depth is greater than the first depth;

determining, by the second machine learning model, a presence of a salt body in the evaluation seismic slice based upon the seismic data in the evaluation seismic slice;

generating, by the second machine learning model, a three-dimensional (3D) matrix based upon the evaluation seismic slice, wherein the 3D matrix indicates the presence of the salt body;

extracting, by the second machine learning model, a geobody from the 3D matrix;

extracting, by the second machine learning model, a surface from the geobody;

determining, by the second machine learning model, a presence of hydrocarbons in the seismic volume based upon the 3D matrix, the geobody, the surface, or a combination thereof;

generating, by the second machine learning model, a three-dimensional (3D) model of a subterranean formation with the hydrocarbons in the seismic volume;

displaying the 3D model of the subterranean formation with the hydrocarbons;

determining, based on the 3D model of the subterranean formation, fluid flow characteristics of a reservoir in a field of the subterranean formation; and

controlling, based on the 3D model of the subterranean formation, drilling in the reservoir.

20. The computing system of claim 19 , wherein the operations comprise:

sending, using an acoustic energy source, sound vibrations into a subsurface in the field; and

receiving, in response to sending the sound vibrations, a seismic survey of the seismic volume with electric signals embedded with information of the subsurface captured and recorded from seismic wave reflections off the subsurface.

Assignments (1)

Continuity (2)

References Cited (25)