# US 2019/0169962 A1 · Machine Learning Training Set Generation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0169962 A1
- Document ID: US20190169962A1
- Status: Published application
- Kind: A1
- Application number: 16/324,109
- Filed: 2016-09-09
- Published: 2019-06-06
- Earliest claimed: 2016-08-08
- Assignees: Schlumberger Technology Corporation
- Applicants: Schlumberger Technology Corporation
- Inventors: Ahmed Adnan Aqrawi; Nader Salman; Guido Johannes van der Hoff
- Web page: https://patentgrep.com/patent/US20190169962A1

## CPC

- G06F 18/214: Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- E21B 41/00: Equipment or details not covered by groups E21B15/00 - E21B40/00
- E21B 43/00: Methods or apparatus for obtaining oil, gas, water, soluble or meltable materials or a slurry of minerals from wells (applicable only to water E03B)
- G01V 1/302: {in 3D data cubes}
- G01V 1/50: Analysing data
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- E21B 2200/22: Fuzzy logic, artificial intelligence, neural networks or the like
- G01V 1/307: {for determining seismic attributes, e.g. amplitude, instantaneous phase or frequency, reflection strength or polarity}
- G01V 11/00: Prospecting or detecting by methods combining techniques covered by two or more of main groups G01V1/00 - G01V9/00
- G01V 2210/63: Seismic attributes, e.g. amplitude, polarity, instant phase
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- E21B: EARTH OR ROCK DRILLING; OBTAINING OIL, GAS, WATER, SOLUBLE OR MELTABLE MATERIALS OR A SLURRY OF MINERALS FROM WELLS
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Systems, computer-readable media, and methods for generating machine learning training data by obtaining reservoir data, determining subsections of the reservoir data, labeling the subsections of the reservoir data to generate labeled reservoir data, and feeding the labeled reservoir data into an artificial neural network. The reservoir data can be labeled using analysis data or based on interpretive input from an interpreter.

## Claims

### Claim 1

A method, comprising:
obtaining reservoir data;
determining subsections of the reservoir data;
labeling the subsections of the reservoir data to generate labeled reservoir data; and
feeding the labeled reservoir data into an artificial neural network.

### Claim 2 (depends on 1)

The method of claim 1, wherein:
the reservoir data comprises analysis data; and
labeling the subsections of the reservoir data comprises labeling the subsections of the reservoir data based on the analysis data, the method further comprising performing quality control on the labeled reservoir data using at least one of input from an interpreter or a machine learning process.

### Claim 3 (depends on 2)

The method of claim 2, wherein the analysis data is metadata incorporated with the reservoir data.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
presenting visualizations of the subsections to an interpreter; and
receiving interpretive input corresponding to the subsections, wherein labeling the subsections of the reservoir data comprises labeling the subsections of the reservoir data based on the interpretive input.

### Claim 5 (depends on 1)

The method of claim 1, wherein the artificial neural network can be used for one or more of interpreting seismic data, interpreting geophysical data, interpreting reservoir data, performing well correlations, building reservoir models suitable for simulation, generating visualizations of simulation results, calculating volumes, producing maps, or designing development strategies to maximize reservoir exploitation.

### Claim 6 (depends on 1)

The method of claim 1, wherein the reservoir data comprises a well log, and the subsections of the reservoir data comprise line segments corresponding to the well log.

### Claim 7 (depends on 1)

The method of claim 1, wherein the reservoir data comprises an image, and the subsections of the reservoir data comprise rectangular subsections of the image.

### Claim 8 (depends on 1)

The method of claim 1, wherein the reservoir data comprises a reservoir model, and the subsections of the reservoir data comprise voxels of the reservoir model.

### Claim 9 (depends on 1)

The method of claim 1, wherein the reservoir data comprises a simulated reservoir model, and the subsections of the reservoir data comprise sequences of voxels of the simulated reservoir model.

### Claim 10 (depends on 1)

The method of claim 1, wherein the labeled reservoir data comprises at least one of text labels, binary labels, or n-tuple labels corresponding to the subsections.

### Claim 11

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:
obtaining reservoir data;
determining subsections of the reservoir data;
labeling the subsections of the reservoir data to generate labeled reservoir data; and
feeding the labeled reservoir data into an artificial neural network.

### Claim 12 (depends on 11)

The computer system of claim 11, wherein:
the reservoir data comprises analysis data; and
labeling the subsections of the reservoir data comprises labeling the subsections of the reservoir data based on the analysis data, the operations further comprising performing quality control on the labeled reservoir data using at least one of input from an interpreter or a machine learning process.

### Claim 13 (depends on 12)

The computer system of claim 12, wherein the analysis data is metadata incorporated with the reservoir data.

### Claim 14 (depends on 11)

The computer system of claim 11, the operations further comprising:
presenting visualizations of the subsections to an interpreter; and
receiving interpretive input corresponding to the subsections, wherein labeling the subsections of the reservoir data comprises labeling the subsections of the reservoir data based on the interpretive input.

### Claim 15 (depends on 11)

The computer system of claim 11, wherein the artificial neural network can be used for one or more of interpreting seismic data, interpreting geophysical data, interpreting reservoir data, performing well correlations, building reservoir models suitable for simulation, generating visualizations of simulation results, calculating volumes, producing maps, or designing development strategies to maximize reservoir exploitation.

### Claim 16 (depends on 11)

The computer system of claim 11, wherein the reservoir data comprises an image, and the subsections of the reservoir data comprise rectangular subsections of the image.

### Claim 17 (depends on 11)

The computer system of claim 11, wherein the reservoir data comprises a reservoir model, and the subsections of the reservoir data comprise voxels of the reservoir model.

### Claim 18 (depends on 11)

The computer system of claim 11, wherein the reservoir data comprises a simulated reservoir model, and the subsections of the reservoir data comprise sequences of voxels of the simulated reservoir model.

### Claim 19 (depends on 11)

The computer system of claim 11, wherein the labeled reservoir data comprises at least one of text labels, binary labels, or n-tuple labels corresponding to the subsections.

### Claim 20

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:
obtaining reservoir data;
determining subsections of the reservoir data;
labeling the subsections of the reservoir data to generate labeled reservoir data; and
feeding the labeled reservoir data into an artificial neural network.