# US 11,579,332 B2 · Dynamic engine for a cognitive reservoir system

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

- Number: US 11,579,332 B2
- Document ID: US11579332B2
- Status: Granted
- Kind: B2
- Application number: 16/157,757
- Filed: 2018-10-11
- Published: 2019-04-11
- Granted: 2023-02-14
- Earliest claimed: 2017-10-11
- Assignees: Beyond Limits, Inc.
- Applicants: Beyond Limits, Inc.
- Inventors: Shahram Farhadi Nia
- Web page: https://patentgrep.com/patent/US11579332B2

## CPC

- G01V 20/00: Geomodelling in general
- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06N 3/043: based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
- G06N 3/0499: Feedforward networks
- G06N 3/088: Non-supervised learning, e.g. competitive learning
- G06N 3/09: Supervised learning
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Implementations described and claimed herein provide systems and methods for developing a reservoir. In one implementation, a static model of the reservoir is received. The static model has one or more clusters of rock types. A reservoir graph is generated from the static model. The reservoir graph represents each of the one or more clusters as a vertex. A graph connectivity of the reservoir graph is defined through a nodal connectivity of neighboring vertices. Pressure values are propagated across three-dimensional space of the reservoir graph using the connectivity. A dynamic model of the reservoir is generated using the pressure values and fluid saturation values.

## Claims

### Claim 1

A method for developing a reservoir, the method comprising:
receiving a static model of the reservoir, the static model having one or more clusters of rock types;
generating a reservoir graph from the static model, the reservoir graph representing each of the one or more clusters as a vertex, wherein each cluster has at most one pressure observation point, one perforation passes through each cluster, and each cluster contains a spatially continuous voxel set;
post-processing on the one or more clusters in the reservoir graph to break discontinuous clusters into continuous blobs;
defining a graph connectivity of the reservoir graph through a nodal connectivity of neighboring vertices;
propagating pressure values across three-dimensional space of the reservoir graph using the nodal connectivity; and
transforming the static model into a dynamic model of the reservoir based on the pressure values and fluid saturation values.

### Claim 2 (depends on 1)

The method of claim 1, wherein the vertex of each of the one or more clusters has vertex properties including one or more of a location, a porosity, a permeability, and an initial saturation.

### Claim 3 (depends on 1)

The method of claim 1, wherein the reservoir graph includes at least one fault plane.

### Claim 4 (depends on 3)

The method of claim 3, wherein the at least one fault plane acts as a node with zero or reduced permeability.

### Claim 5 (depends on 1)

The method of claim 1, wherein the fluid saturation values are generated based on four-dimensional seismic data of the reservoir.

### Claim 6 (depends on 1)

The method of claim 1, wherein the dynamic model is automatically updated in response to any changes in the pressure values or the fluid saturation values.

### Claim 7 (depends on 1)

The method of claim 1, further comprising generating a recommendation by reasoning over the dynamic model of the reservoir and evaluating volumes against a set of one or more rules in one or more stages of fuzzy inference, wherein the set of one or more rules is used to relate values of a set of features to a drilling attractiveness of a node.

### Claim 8

One or more non-transitory tangible computer-readable storage media storing computer-executable instructions for performing a computer process on a computing system, the computer process comprising:
receiving a static model of a reservoir, the static model having one or more clusters of rock types;
generating a reservoir graph from the static model, the reservoir graph representing each of the one or more clusters as a vertex, wherein each cluster has at most one pressure observation point, one perforation passes through each cluster, and each cluster contains a spatially continuous voxel set;
post-processing on the one or more clusters in the reservoir graph to break discontinuous clusters into continuous blobs;
defining a graph connectivity of the reservoir graph through a nodal connectivity of neighboring vertices;
propagating pressure values across three-dimensional space of the reservoir graph using the nodal connectivity; and
transforming the static model into a dynamic model of the reservoir based on the pressure values and fluid saturation values.

### Claim 9 (depends on 8)

The one or more non-transitory tangible computer-readable storage media of claim 8, wherein the vertex of each of the one or more clusters has vertex properties including one or more of a location, a porosity, a permeability, and an initial saturation.

### Claim 10 (depends on 8)

The one or more non-transitory tangible computer-readable storage media of claim 8, wherein the reservoir graph includes at least one fault plane.

### Claim 11 (depends on 10)

The one or more non-transitory tangible computer-readable storage media of claim 10, wherein the at least one fault plane acts as a node with zero or reduced permeability.

### Claim 12 (depends on 8)

The one or more non-transitory tangible computer-readable storage media of claim 8, wherein the fluid saturation values are generated based on four-dimensional seismic data of the reservoir.

### Claim 13 (depends on 8)

The one or more non-transitory tangible computer-readable storage media of claim 8, wherein the dynamic model is automatically updated in response to any changes in the pressure values or the fluid saturation values.

### Claim 14

A system for developing a model of a reservoir, the system comprising:
one or more processors configured to execute:
a static modeler comprising one or more neural networks configured to generate a static model of the reservoir, the static model having one or more clusters of rock types; and
a dynamic modeler in communication with the static modeler, the dynamic modeler using artificial intelligence to:
generate a reservoir graph from the static model, the reservoir graph representing each of the one or more clusters as a vertex, wherein each cluster has at most one pressure observation point, one perforation passes through each cluster; and each cluster contains a spatially continuous voxel set;
post-process the one or more clusters in the reservoir graph to break discontinuous clusters into continuous blobs;
define a graph connectivity through a nodal connectivity of neighboring vertices,
propagate pressure values across three-dimensional space of the reservoir graph using the nodal connectivity; and
transform the static model into a dynamic model of the reservoir based on the pressure values and fluid saturation values.

### Claim 15 (depends on 14)

The system of claim 14, wherein the vertex of each of the one or more clusters has vertex properties including one or more of a location, a porosity, a permeability, and an initial saturation.

### Claim 16 (depends on 14)

The system of claim 14, wherein the reservoir graph includes at least one fault plane.

### Claim 17 (depends on 14)

The system of claim 14, wherein the fluid saturation values are generated based on four-dimensional seismic data of the reservoir.
