System and method for simulating reservoir models

Patent metadata

Field	Value
Publication number	US-12387019-B2
Application number	US-201816772794-A
Country	US
Kind code	B2
Filing date	Dec 13, 2018
Priority date	Dec 14, 2017
Publication date	Aug 12, 2025
Grant date	Aug 12, 2025

Abstract

A method, computer program product, and computing system are provided for defining one or more injector completions and one or more producer completions in one or more reservoir models. One or more edges between the one or more injector completions and the one or more producer completions in the one or more reservoir models may be defined. The one or more edges between the one or more injector completions and the one or more producer completions may define a graph network representative of the one or more reservoir models. The one or more reservoir models may be simulated along the one or more edges between the one or more injector completions and the one or more producer completions.

First claim

What is claimed is:

1. A method comprising:
defining, via a neural network, a plurality of injector completions and a plurality of producer completions in one or more reservoir models;
defining a plurality of injector-producer pairs based upon, at least in part, spatial proximity between the plurality of injector completions and the plurality of producer completions;
defining, via the neural network, a plurality of directed ed 0 ges between the plurality of injector completions and the plurality of producer completions in the one or more reservoir models based upon, at least in part, the plurality of injector-producer pairs, wherein the plurality of directed edges comprise local static and dynamic reservoir properties, wherein the plurality of directed edges between the plurality of injector completions and the plurality of producer completions define a graph network representative of the one or more reservoir models, wherein each directed edge represents a volume of interest between an injector completion and a producer completion in an injector-producer pair of the plurality of injector-producer pairs, wherein the volume of interest is determined based upon, at least in part, the local static and dynamic reservoir properties of the directed edges, and wherein each directed edge is associated with;
simulating, via the neural network, a one-dimensional behavior of the one or more reservoir models along each directed edge in the plurality of directed edges between the plurality of injector completions and the plurality of producer completions with a one-dimensional simulator, wherein the one-dimensional behavior of the one or more reservoir models is modeled, via the neural network, by treating each of the plurality of injector-producer pairs as a respective sub-network; and
defining, via the neural network, a three-dimensional graph network representative of the one or more reservoir models by aggregating each of the one-dimensional behaviors of the plurality of directed edges between the plurality of injector completions and the plurality of producer completions to determine an effective three-dimensional behavior of the one or more reservoir models, wherein the effective three-dimensional behavior of the one or more reservoir models is represented by a degree of interaction between each respective sub-network of each injector-producer pair of the plurality of injector-producer pairs.

2. The method of claim 1 , further comprising:
determining total oil production for the one or more reservoir models based upon, at least in part, determining oil production for each directed edge that terminates at each of the plurality of producer completions in the one or more reservoir models.

3. The method of claim 1 , wherein simulating the one or more reservoir models along each directed edge in the plurality of directed edges between the plurality of injector completions and the plurality of producer completions includes:
receiving a plurality of injector rates associated with the plurality of injector completions; and
determining one or more of oil production rates and water production rates for the plurality of producer completions based upon, at least in part, simulating the plurality of injector rates associated with the plurality of injector completions.

4. The method of claim 1 , wherein simulating the one or more reservoir models along each directed edge in the plurality of directed edges between the plurality of injector completions and the plurality of producer completions includes:
receiving one or more of oil production rates and water production rates associated with the plurality of producer completions; and
determining water injection rates for the plurality of injector completions based upon, at least in part, simulating one or more of the oil production rates and the water production rates associated with the plurality of producer completions.

5. The method of claim 1 , further comprising:
monitoring an inflow control device; and
controlling the inflow control device by reducing or increasing a flow area through the inflow control device, wherein the control of the inflow control device is based upon, at least in part, the simulation of the one or more reservoir models.

6. The method of claim 1 , wherein the one-dimensional simulator is a segmented reservoir model simulator (SRMS).

7. The method of claim 1 , further comprising:
receiving one or more training images; and
training the neural network based on the one or more training images to generate a trained neural network, wherein the trained neural network generates fake data indistinguishable from real data.

8. The method of claim 7 , wherein the neural network comprises a discriminator and a generator, wherein the generator is configured to generate the fake data, and wherein the discriminator is configured to distinguish the fake data from the real data.

9. The method of claim 1 , wherein the effective three-dimensional behavior of the one or more reservoir models is represented by fluid dynamics defined by the one-dimensional behavior of the one or more reservoir models.

10. The method of claim 1 , wherein the degree of interaction prior to water breakthrough between each respective sub-network of each injector-producer pair of the plurality of injector-producer pairs is defined by a sum of flowrates along each directed edge that terminates at each of the plurality of producer completions in the one or more reservoir models.

11. The method of claim 1 , wherein the degree of interaction at or after water breakthrough between each respective sub-network of each injector-producer pair of the plurality of injector-producer pairs is defined by a sum of flowrates along each directed edge that terminates at each of the plurality of producer completions in the one or more reservoir models corrected for an average saturation between each respective injector-producer pair.

12. The method of claim 1 , wherein the neural network is a generative adversarial network (GAN).

13. A computing system including one or more processors and one or more memories configured to perform operations comprising:
defining, via a neural network, a plurality of injector completions and a plurality of producer completions in one or more reservoir models;
defining, via the neural network, a plurality of injector-producer pairs based upon, at least in part, spatial proximity between the plurality of injector completions and the plurality of producer completions;
defining, via the neural network, a plurality of directed edges between the plurality of injector completions and the plurality of producer completions in the one or more reservoir models based upon, at least in part, the plurality of injector-producer pairs, wherein the plurality of directed edges comprise local static and dynamic reservoir properties, wherein the plurality of directed edges between the plurality of injector completions and the plurality of producer completions define a graph network representative of the one or more reservoir models, wherein each directed edge represents a volume of interest between an injector completion and a producer completion in an injector-producer pair of the plurality of injector-producer pairs, wherein the volume of interest is determined based upon, at least in part, the local static and dynamic reservoir properties of the directed edges, and wherein each directed edge is associated with;
determining, via the neural network, total oil production for the one or more reservoir models based upon, at least in part, determining oil production for each directed edge that terminates at the plurality of producer completions in

Assignees

• Schlumberger Technology Corp

Inventors

• Bailey William J
• Tilke Peter G

Classifications

• G06N3/0442

  characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU] · CPC title

• G06N3/094

  Adversarial learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06N3/0475

  Generative networks · CPC title

• G01V20/00

  Geomodelling in general · CPC title