Automatic Feature Extraction from Seismic Cubes

Patent metadata

Field	Value
Publication number	US-2021109242-A1
Application number	US-201816499317-A
Country	US
Kind code	A1
Filing date	Jun 22, 2018
Priority date	Jun 26, 2017
Publication date	Apr 15, 2021
Grant date	—

Abstract

Methods, computing systems, and computer-readable media for interpreting seismic data, of which the method includes receiving seismic data representing a subterranean volume, and determining a feature-likelihood attribute of at least a portion of a section of the seismic data. The feature-likelihood attribute comprises a value for elements of the section, the value being based on a likelihood that the element represents part of a subterranean feature. The method also includes identifying contours of the subterranean feature based in part on the feature-likelihood attribute of the section, and determining a polygonal line that approximates the subterranean feature.

First claim

What is claimed is:

1 . A method for interpreting seismic data, comprising:
receiving seismic data representing a subterranean volume; determining a feature-likelihood attribute of at least a portion of a section of the seismic data, wherein the feature-likelihood attribute comprises a value for elements of the section, the value being based on a likelihood that the element represents part of a subterranean feature; identifying contours of the subterranean feature based in part on the feature-likelihood attribute of the section; and determining a polygonal line that approximates the subterranean feature.

2 . The method of claim 1 , further comprising causing a visualization of the polygonal line representing the subterranean feature to be displayed to a user

3 . The method of claim 1 , wherein determining the feature-likelihood attribute comprises processing the section using a neural network to determine the values for the elements.

4 . The method of claim 1 , further comprising applying a filter to the seismic image prior to identifying the contours.

5 . The method of claim 1 , wherein determining the polygonal line comprises:
identifying edges of the subterranean feature; generating a Voronoi diagram of the edges to determine Voronoi vertices representing the subterranean feature; and connecting at least a portion of the Voronoi vertices to form the polygonal line.

6 . The method of claim 5 , wherein connecting the at least a portion of the Voronoi vertices to form the polygonal line comprises:
determining unidirectional sticks extending between two or more of the Voronoi vertices; merging the unidirectional sticks using a clustering algorithm to form a segment; and simplifying the segment by approximating a shape of the merged unidirectional sticks.

7 . The method of claim 1 , further comprising:
transmitting the section to a thin client device for display to the user; and receiving an indication of an area in the section from the thin client device, wherein determining the feature-likelihood attribute of at least a portion of a section of the seismic data comprises determining the feature-likelihood attribute for the indicated area, and wherein causing the visualization of the polygonal line to be displayed comprises transmitting a representation of the polygonal line in the section to the thin client device for display.

8 . The method of claim 1 , wherein the subterranean feature comprises quasi-linear feature.

9 . The method of claim 1 , further comprising:
receiving, from the thin client device, an indication of a feature in the section that was not represented by the polygonal line; adjusting the fault-likelihood attribute based on the indication; and determine a polygonal line representing the feature in the section based on the adjusted fault-likelihood attribute.

10 . 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:
receiving seismic data representing a subterranean volume;
determining a feature-likelihood attribute of at least a portion of a section of the seismic data, wherein the feature-likelihood attribute comprises a value for elements of the section, the value being based on a likelihood that the element represents part of a subterranean feature;
identifying contours of the subterranean feature based in part on the feature-likelihood attribute of the section; and
determining a polygonal line that approximates the subterranean feature.

11 . The system of claim 10 , wherein the operations further comprise causing a visualization of the polygonal line representing the subterranean feature to be displayed to a user

12 . The system of claim 10 , wherein determining the feature-likelihood attribute comprises processing the section using a neural network to determine the values for the elements.

13 . The system of claim 10 , wherein determining the polygonal line comprises:
identifying edges of the subterranean feature; generating a Voronoi diagram of the edges to determine Voronoi vertices representing the subterranean feature; and connecting at least a portion of the Voronoi vertices to form the polygonal line.

14 . The system of claim 13 , wherein connecting the at least a portion of the Voronoi vertices to form the polygonal line comprises:
determining unidirectional sticks extending between two or more of the Voronoi vertices; merging the unidirectional sticks using a clustering algorithm to form a segment; and simplifying the segment by approximating a shape of the merged unidirectional sticks.

15 . The system of claim 10 , wherein the operations further comprise:
transmitting the section to a thin client device for display to the user; and receiving an indication of an area in the section from the thin client device, wherein determining the feature-likelihood attribute of at least a portion of a section of the seismic data comprises determining the feature-likelihood attribute for the indicated area, and wherein causing the visualization of the polygonal line to be displayed comprises transmitting a representation of the polygonal line in the section to the thin client device for display.

16 . The system of claim 10 , wherein the operations further comprise:
receiving, from the thin client device, an indication of a feature in the section that was not represented by the polygonal line; adjusting the fault-likelihood attribute based on the indication; and determine a polygonal line representing the feature in the section based on the adjusted fault-likelihood attribute.

17 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors of a computing system, cause the computing system to perform operations, the operations comprising:
receiving seismic data representing a subterranean volume; determining a feature-likelihood attribute of at least a portion of a section of the seismic data, wherein the feature-likelihood attribute comprises a value for elements of the section, the value being based on a likelihood that the element represents part of a subterranean feature; identifying contours of the subterranean feature based in part on the feature-likelihood attribute of the section; and determining a polygonal line that approximates the subterranean feature.

18 . The system of claim 10 , wherein the operations further comprise causing a visualization of the polygonal line representing the subterranean feature to be displayed to a user

19 . The system of claim 10 , wherein determining the feature-likelihood attribute comprises processing the section using a neural network to determine the values for the elements.

20 . The system of claim 10 , wherein determining the polygonal line comprises:
identifying edges of the subterranean feature; generating a Voronoi diagram of the edges to determine Voronoi vertices representing the subterranean feature; and connecting at least a portion of the Voronoi vertices to form the polygonal line, comprising:
determining unidirectional sticks extending between two or more of the Voronoi vertices;
merging the unidirectional sticks using a clustering algorithm to form a segment; and
simplifying the segment by approximating a shape of the merged unidirectional sticks

Assignees

• Schlumberger Technology Corp

Inventors

• Salman Nader
• Najm Matthieu Georges Maroun

Classifications

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G01V20/00

  Geomodelling in general · CPC title

• G01V2210/74

  Visualisation of seismic data · CPC title

• G01V2210/62

  Physical property of subsurface · CPC title