# US 2023/0266491 A1 · Method and system for predicting hydrocarbon reservoir information from raw seismic data

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

- Number: US 2023/0266491 A1
- Document ID: US20230266491A1
- Status: Published application
- Kind: A1
- Application number: 17/651,682
- Filed: 2022-02-18
- Published: 2023-08-24
- Earliest claimed: 2022-02-18
- Assignees: Saudi Arabian Oil Company
- Applicants: Saudi Arabian Oil Company
- Inventors: Saleh Al-Saleh; Jianwu Jiao; Ewenet Gashawbeza; Husain Shakhs
- Web page: https://patentgrep.com/patent/US20230266491A1

## CPC

- G01V 1/282: {Application of seismic models, synthetic seismograms}
- G01V 1/301: {for determining seismic cross-sections or geostructures}
- G01V 1/306: {for determining physical properties of the subsurface, e.g. impedance, porosity or attenuation profiles}
- G01V 2210/614: Synthetically generated data
- G01V 2210/6169: using well-logging
- G01V 2210/64: Geostructures, e.g. in 3D data cubes
- G01V 2210/66: Subsurface modeling
- G01V 2210/673: Finite-element; Finite-difference
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)

## Abstract

Systems and methods of identifying a drilling target are disclosed. The method includes obtaining a training set of base subsurface models and generating, using a first artificial intelligence neural network, a plurality of subsurface model realizations based on the base subsurface models. The method further includes simulating, for each subsurface model realization, a synthetic seismic dataset and training a second artificial intelligence neural network, using the plurality of subsurface model realizations and the corresponding synthetic seismic dataset for each subsurface model realization, to predict an inferred subsurface model from a seismic dataset. The method still further includes obtaining an observed seismic dataset for a subterranean region of interest, predicting, using the trained second artificial intelligence neural network, an inferred subsurface model from the observed seismic dataset, and identifying the drilling target based on the inferred subsurface model.

## Claims

### Claim 1

A method of identifying a drilling target, comprising:
obtaining a training set of base subsurface models;
generating, using a first artificial intelligence neural network, a plurality of subsurface model realizations based, at least in part on the base subsurface models;
simulating, for each subsurface model realization, a synthetic seismic dataset;
training a second artificial intelligence neural network, using the plurality of subsurface model realizations and the synthetic seismic dataset for each subsurface model realization, to predict an inferred subsurface model from a seismic dataset;
obtaining an observed seismic dataset for a subterranean region of interest;
predicting, using the trained second artificial intelligence neural network, an inferred subsurface model from the observed seismic dataset; and
identifying the drilling target based, at least in part, on the inferred subsurface model.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
determining a wellbore path to intersect the drilling target; and
drilling a wellbore guided by the wellbore path.

### Claim 3 (depends on 1)

The method of claim 1, wherein the base subsurface model comprises:
a base background model; and
a plurality of base canonical geological structures.

### Claim 4 (depends on 3)

The method of claim 3, wherein a canonical geological structure may be chosen from an archaic sand dune, a wadi, and a karst.

### Claim 5 (depends on 1)

The method of claim 1, wherein the first artificial intelligence network comprises a Generative Adversarial Neural Network.

### Claim 6 (depends on 1)

The method of claim 1, wherein the second artificial intelligence network comprises a Deep Neural Network.

### Claim 7 (depends on 1)

The method of claim 1, wherein the simulation of a synthetic seismic dataset is performed using a finite-difference solution to an elastic wave equation.

### Claim 8

A non-transitory computer readable medium storing instructions executable by a computer processor, the instructions comprising functionality for:
receiving a training set of base subsurface models;
generating, using a first artificial intelligence network, a plurality of subsurface model realizations based, at least in part on the base subsurface models;
simulating, for each subsurface model realization, a synthetic seismic dataset;
training, using the plurality of subsurface model realizations and the synthetic seismic dataset for each subsurface model realization, a second artificial intelligence network to predict an inferred subsurface model from a seismic dataset;
receiving an observed seismic dataset for a subterranean region of interest;
predicting, using the trained second artificial intelligence seismic dataset, an inferred subsurface model from the observed seismic dataset; and
identifying a drilling target based, at least in part, on the inferred subsurface model.

### Claim 9 (depends on 8)

The non-transitory computer readable medium of claim 8, the instructions further comprising functionality for:
determining a wellbore path to intersect the drilling target.

### Claim 10 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein the training set base subsurface models comprises a plurality of base canonical subsurface structures.

### Claim 11 (depends on 10)

The non-transitory computer readable medium of claim 10, wherein a canonical geological structure may be chosen from an archaic sand dune, a wadi, and a karst.

### Claim 12 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein the first artificial intelligence network comprises a Generative Adversarial Neural Network.

### Claim 13 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein the second artificial intelligence network comprises a Deep Neural Network.

### Claim 14 (depends on 8)

The non-transitory computer readable medium of claim 8, wherein the simulation of a synthetic seismic dataset is performed using a finite-difference solution to an elastic wave equation.

### Claim 15

A system, comprising:
a memory; and
a computer processor configured to:
receive a training set of base subsurface models, the training set being stored in the memory;
generate, using a first artificial intelligence network, a plurality of subsurface model realizations based, at least in part on the base subsurface models;
simulate, for each subsurface model realization, a synthetic seismic dataset;
train, using the plurality of subsurface model realizations and the synthetic seismic dataset for each subsurface model realization, a second artificial intelligence network to predict an inferred subsurface model from a seismic dataset;
receive an observed seismic dataset for a subterranean region of interest,
predict, using the trained second artificial intelligence seismic dataset, an inferred subsurface model from the observed seismic dataset;
identify a drilling target based, at least in part, on the inferred subsurface model; and
determine a wellbore path to intersect the drilling target.

### Claim 16 (depends on 15)

The system of claim 15, further comprising a drilling system to drill the wellbore guided by the wellbore path.

### Claim 17 (depends on 15)

The system of claim 15, wherein the base subsurface models each comprises:
a base background model; and
a plurality of base canonical subsurface structures.

### Claim 18 (depends on 16)

The system of claim 16, wherein a canonical geological structure may be chosen from archaic sand dune, a wadi, and a karst.

### Claim 19 (depends on 15)

The system of claim 15, wherein:
the first artificial intelligence network comprises a Generative Adversarial Neural Network (GANN); and
the second artificial intelligence network comprises a Deep Neural Network (DNN).

### Claim 20 (depends on 15)

The system of claim 15, wherein the simulation of a synthetic seismic dataset is performed using a finite-difference solution to an elastic wave equation.
