Stratigraphic layer identification from seismic and well data with stratigraphic knowledge base

Patent metadata

Field	Value
Publication number	US-10990882-B2
Application number	US-201715662411-A
Country	US
Kind code	B2
Filing date	Jul 28, 2017
Priority date	Jul 28, 2017
Publication date	Apr 27, 2021
Grant date	Apr 27, 2021

Abstract

A system, method and program product for stratigraphic layer identification using a stratigraphic knowledge base for machine learning. Reservoir data includes seismic data and well log data for a reservoir area. The well log data is processed to identify well stratigraphic layer features and the seismic data is processed to identify seismic stratigraphic layer features. A feature matching algorithm based on a stratigraphic knowledge base is selected to match the well stratigraphic layer features to the seismic stratigraphic layer features. The matched features are used to define a stratigraphic layer interpretation for the reservoir area and the interpretation is presented to a user.

First claim

What is claimed is:

1. A computer system for stratigraphic layer identification, the computer system comprising:
one or more computer processors;
one or more computer readable storage devices; and
program instructions stored on at least one of the one or more computer readable storage devices for execution by at least one of the one or more computer processors, the program instructions comprising:
program instructions to access seismic data for a reservoir area and well log data for at least one well in the reservoir area;
program instructions to identify a plurality of well stratigraphic layer features utilizing at least a portion of the well log data;
program instructions to identify a plurality of seismic stratigraphic layer features utilizing at least a portion of the seismic data;
program instructions to match the plurality of well stratigraphic layer features to the plurality of seismic stratigraphic layer features by selecting a feature matching algorithm from a plurality of feature matching algorithms based on a stratigraphic knowledge base;
program instructions to define a stratigraphic layer interpretation for the reservoir area utilizing the plurality of well stratigraphic layer features matched to the plurality of seismic stratigraphic layer features;
program instructions to register the stratigraphic layer interpretation in the stratigraphic knowledge base, wherein the stratigraphic knowledge base includes at least one machine learning algorithm for integrating the stratigraphic layer interpretation into selection criteria for the plurality of feature matching algorithms, and wherein the stratigraphic layer interpretation is a visual map defining the locations of a plurality of horizons between strata having varying characteristics within a geological volume; and
program instructions to present a visualization of the stratigraphic layer interpretation to a user.

2. The computer system of claim 1 , further comprising:
program instructions to select a well-tie feature algorithm from a plurality of well-tie feature algorithms based on the stratigraphic knowledge base using at least one machine learning algorithm; and
program instructions to identify the plurality of well stratigraphic layer features utilizing the selected well-tie feature algorithm.

3. The computer system of claim 1 , further comprising:
program instructions to select a seismic trace feature algorithm from a plurality of seismic trace feature algorithms based on the stratigraphic knowledge base using at least one machine learning algorithm; and
program instructions to identify the plurality of seismic stratigraphic layer features utilizing the selected seismic trace feature algorithm.

4. The computer system of claim 1 , further comprising:
program instructions to select the feature matching algorithm from the plurality of feature matching algorithms using at least one machine learning algorithm and historical stratigraphic layer interpretations.

5. The computer system of claim 1 , further comprising:
program instructions to define at least one stratigraphic horizon using a sliding window to compare at least one matched well stratigraphic layer feature and seismic stratigraphic layer feature at a first layer of a geological volume originating at the at least one well to a seismic stratigraphic layer feature at an overlapping layer in the geographic volume to create the stratigraphic layer interpretation for the reservoir area utilizing the plurality of well stratigraphic layer features matched to the plurality of seismic stratigraphic layer features.

6. The computer system of claim 1 , further comprising:
program instructions to access a reservoir data source that includes a plurality of well logs for a plurality of wells at a plurality of well locations in the reservoir area;
program instructions to identify the plurality of well stratigraphic layer features for each of the plurality of well locations utilizing a well feature extraction module;
program instructions to identify the plurality of seismic layer features for each of the plurality of well locations utilizing a seismic feature extraction module;
program instructions to match at least a portion of the plurality of well stratigraphic layer features to a portion of the plurality of seismic stratigraphic layer features at each of the plurality of well locations utilizing a feature matching module; and
program instructions to define the stratigraphic layer interpretation between each of the plurality of well locations utilizing a layer propagation module.

7. The computer system of claim 1 , further comprising:
program instructions to modify the stratigraphic layer interpretation utilizing an interpretation interface that includes a user correction module and an interpretation visualizer.

8. The computer system of claim 1 , further comprising:
program instructions to compare the seismic data and well log data to historical stratigraphic layer interpretations in the stratigraphic knowledge base to select and use a machine learning algorithm.

9. The computer system of claim 7 , further comprising:
program instructions to display an explanation of similarities between historical stratigraphic layer interpretations and the stratigraphic layer interpretation using the machine learning algorithm utilizing the interpretation interface.

10. A computer program product stored on a computer readable storage medium, which when executed by a computing system, provides for stratigraphic layer identification, the computer program product comprising:
program code that accesses seismic data for a reservoir area and well log data for at least one well in the reservoir area;
program code that identifies a plurality of well stratigraphic layer features utilizing at least a portion of the well log data;
program code that identifies a plurality of seismic stratigraphic layer features utilizing at least a portion of the seismic data;
program code that matches the plurality of well stratigraphic layer features to the plurality of seismic stratigraphic layer features by selecting a feature matching algorithm from a plurality of feature matching algorithms based on a stratigraphic knowledge base;
program code that defines a stratigraphic layer interpretation for the reservoir area utilizing the plurality of well stratigraphic layer features matched to the plurality of seismic stratigraphic layer features;
program code that registers the stratigraphic layer interpretation in the stratigraphic knowledge base, wherein the stratigraphic knowledge base includes at least one machine learning algorithm for integrating the stratigraphic layer interpretation into selection criteria for the plurality of feature matching algorithms, and wherein the stratigraphic layer interpretation is a visual map defining the locations of a plurality of horizons between strata having varying characteristics within a geological volume; and
program code that presents a visualization of the stratigraphic layer interpretation to a user.

11. The computer program product of claim 10 , further comprising:
program code that selects a well-tie feature algorithm from a plurality of well-tie feature algorithms based on the stratigraphic knowledge base using at least one machine learning algorithm, the selected well-tie feature algorithm being used to identify the plurality of well stratigraphic layer features.

12. The computer program product of claim 10 , further comprising:
program code that selects a seismic trace feature algorithm from a plurality of seismic trace feature algorithms based on the stratigraphic knowledge base using at least one machine learning al

Assignees

• IBM

Inventors

• Borrel Paul
• Cavalin Paulo R
• Kormaksson Matthias
• Mena Paz Carmen N
• Raghib Michael

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/09

  Supervised learning · CPC title

• G01V1/50 Primary

  Analysing data · CPC title

• G01V2210/66

  Subsurface modeling · CPC title