# US 2024/0201404 A1 · Methods and systems for analyzing seismic amplitude

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

- Number: US 2024/0201404 A1
- Document ID: US20240201404A1
- Status: Published application
- Kind: A1
- Application number: 18/067,591
- Filed: 2022-12-16
- Published: 2024-06-20
- Earliest claimed: 2022-12-16
- Assignees: Saudi Arabian Oil Company
- Applicants: Saudi Arabian Oil Company
- Inventors: Mukarram AHMED; Hassan ALMOMIN
- Web page: https://patentgrep.com/patent/US20240201404A1

## 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 2210/64: Geostructures, e.g. in 3D data cubes
- 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

The identification of prospective hydrocarbon deposits within a subterranean formation suitable for exploration and production activities may be achieved with methods and systems that analyze seismic amplitude anomalies and identify prospective hydrocarbon deposits based on said analysis. For example, the methods and systems may generate and/or use a collection of seismic forward models that relate to the geological factors and seismic imaging artifacts that impact (or otherwise generate) seismic amplitude anomalies. The seismic forward models may be derived based on rock physics and petrophysics principles while also considering seismic imaging artifacts.

## Claims

### Claim 1

A method comprising:
identifying a seismic amplitude anomaly in seismic data of a portion of a subterranean formation;
associating geological-property data, geophysical-parameter data, or both corresponding to the seismic amplitude anomaly with the identified seismic amplitude anomaly;
producing a one or more seismic forward models each based on a scenario that accounts for an actual seismic amplitude response for the seismic amplitude anomaly and the geological-property data and/or geophysical-parameter data, wherein at least one of the one or more seismic forward models includes at least one seismic imaging artifact;
adjusting input parameters for each of the one or more seismic forward models so that a seismic amplitude response produced by the seismic forward model at least substantially matches the actual seismic amplitude response for the seismic amplitude anomaly;
training a supervised neural network using the one or more seismic forward models and corresponding adjusted input parameters; and
generating a synthetic seismic forward model with the trained neural network.

### Claim 2 (depends on 1)

The method of claim 1 further comprising:
validating the synthetic seismic forward model using a second seismic amplitude anomaly and geological-property data and/or geophysical-parameter data corresponding to the second seismic amplitude anomaly.

### Claim 3 (depends on 2)

The method of claim 2 further comprising:
analyzing a second portion of the subterranean formation with a validated, synthetic seismic forward model to identify one or more seismic amplitude anomalies corresponding to a prospective hydrocarbon deposit.

### Claim 4 (depends on 3)

The method of claim 3 further comprising:
outputting the prospective hydrocarbon deposit in a 3-dimensional model.

### Claim 5 (depends on 3)

The method of claim 3 further comprising:
performing a hydrocarbon exploration operation into the prospective hydrocarbon deposit.

### Claim 6 (depends on 1)

The method of claim 1, wherein the geological-property data is selected from the group consisting of a rock matrix, a porosity, a lithology, a pore fluid, and any combination thereof.

### Claim 7 (depends on 1)

The method of claim 1, wherein the geophysical-parameter data is selected from the group consisting of a signal-to-noise ratio, a seismic frequency, a wavelet, and any combination thereof.

### Claim 8 (depends on 1)

The method of claim 1, wherein the input parameters are selected from the group consisting of seismic velocity Vs, seismic velocity Vp, density, seismic frequency, tuning thickness, and any combination thereof.

### Claim 9 (depends on 1)

The method of claim 1, wherein the training uses a gradient-based method and back-propagation method.

### Claim 10 (depends on 1)

The method of claim 1, wherein the supervised neural network is a convolutional neural network.

### Claim 11

A machine-readable storage medium having stored thereon a computer program comprising a routine of set instructions for causing the machine to perform the steps of:
identifying a seismic amplitude anomaly in seismic data of a portion of a subterranean formation;
associating geological-property data and/or geophysical-parameter data corresponding to the seismic amplitude anomaly therewith;
producing one or more seismic forward models each based on a scenario that accounts for an actual seismic amplitude response for the seismic amplitude anomaly and the geological-property data and/or geophysical-parameter data, wherein at least one of the one or more seismic forward models includes at least one seismic imaging artifact;
adjusting input parameters for each of the one or more seismic forward models so that a seismic amplitude response produced by the seismic forward model at least substantially matches the actual seismic amplitude response for the seismic amplitude anomaly;
training a supervised neural network using the one or more seismic forward models and corresponding adjusted input parameters; and
generating a synthetic seismic forward model with the trained neural network.

### Claim 12 (depends on 11)

The machine-readable storage medium of claim 11, wherein the steps further comprise:
validating the synthetic seismic forward model using a second seismic amplitude anomaly and geological-property data and/or geophysical-parameter data corresponding to the second seismic amplitude anomaly.

### Claim 13 (depends on 12)

The machine-readable storage medium of claim 12, wherein the steps further comprise:
analyzing a second portion of the subterranean formation with a validated, synthetic seismic forward model to identify one or more seismic amplitude anomalies corresponding to a prospective hydrocarbon deposit.

### Claim 14 (depends on 13)

The machine-readable storage medium of claim 13, wherein the steps further comprise:
outputting the prospective hydrocarbon deposit in a 3-dimensional model.

### Claim 15 (depends on 13)

The machine-readable storage medium of claim 13, wherein the steps further comprise:
causing a drilling system to perform at least a portion of a hydrocarbon exploration operation into the prospective hydrocarbon deposit.

### Claim 16 (depends on 11)

The machine-readable storage medium of claim 11, wherein the geological-property data is selected from the group consisting of a rock matrix, a porosity, a lithology, a pore fluid, and any combination thereof.

### Claim 17 (depends on 11)

The machine-readable storage medium of claim 11, wherein the geophysical-parameter data is selected from the group consisting of a signal-to-noise ratio, a seismic frequency, a wavelet, and any combination thereof.

### Claim 18 (depends on 11)

The machine-readable storage medium of claim 11, wherein the input parameters are selected from the group consisting of seismic velocity Vs, seismic velocity Vp, density, seismic frequency, tuning thickness, and any combination thereof.

### Claim 19 (depends on 11)

The machine-readable storage medium of claim 11, wherein the training uses a gradient-based method and back-propagation method.

### Claim 20 (depends on 11)

The machine-readable storage medium of claim 11, wherein the supervised neural network is a convolutional neural network.
