System and method for simulating reservoir models

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 the one or more reservoir models;
• 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.

A computer program product comprising a non-transitory computer readable storage medium having a plurality of instructions stored thereon, which, when executed by a processor, cause the processor to perform operations comprising:

• defining, via a generative adversarial network (GAN), a plurality of injector completions and a plurality of producer completions in one or more reservoir models;
• defining, via the GAN, 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 GAN, 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;
• simulating, via the GAN, 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 segmented reservoir model simulator, wherein the one-dimensional behavior of the one or more reservoir models is modeled, via the GAN, by treating each of the plurality of injector-producer pairs as a respective sub-network;
• and
• defining, via the GAN, 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.