Unconventional Hydrocarbon Resource Development

1 . A computer-implemented method comprising:

generating a synthetic database for unconventional hydrocarbon resources;

generating, based on the synthetic database, a machine learning model that models unconventional reservoirs;

determining, using the machine learning model, hydraulic fracturing stimulation performance of an unconventional reservoir; and

providing the hydraulic fracturing stimulation performance for unconventional hydrocarbon resource development of the unconventional reservoir.

2 . The computer-implemented method of claim 1 , wherein the synthetic database comprises simulated data generated from a physics model-based reservoir simulation tool.

3 . The computer-implemented method of claim 1 , wherein providing the hydraulic fracturing stimulation performance for the unconventional hydrocarbon resource development of the unconventional reservoir comprises increasing, based on the hydraulic fracturing stimulation performance, a flow rate of produced hydrocarbon fluid from the unconventional reservoir.

4 . The computer-implemented method of claim 1 , further comprising before generating the synthetic database for unconventional hydrocarbon resources:

determining a plurality of reservoir characteristics that affect the hydraulic fracturing stimulation performance, and wherein generating the synthetic database for unconventional hydrocarbon resources comprises generating, based on the plurality of reservoir characteristics, the synthetic database for unconventional hydrocarbon resources.

5 . The computer-implemented method of claim 4 , wherein the plurality of reservoir characteristics comprises at least one of formation permeability, in-situ stress distribution, reservoir fluid viscosity, skin factor, reservoir pressure, or reservoir depth.

6 . The computer-implemented method of claim 1 , further comprising before generating the synthetic database for unconventional hydrocarbon resources:

determining a plurality of stimulation parameters that affect the hydraulic fracturing stimulation performance, and wherein generating the synthetic database for unconventional hydrocarbon resources comprises generating, based on the plurality of stimulation parameters, the synthetic database for unconventional hydrocarbon resources.

7 . The computer-implemented method of claim 6 , wherein the plurality of stimulation parameters comprise at least one of a type of fractures, a size of fractures, a type of fluid for hydraulic fracturing, a type of proppant for hydraulic fracturing, or an injection pressure for hydraulic fracturing.

8 . The computer-implemented method of claim 1 , wherein generating the synthetic database comprises generating, using a physics-based fracture propagation model, the synthetic database.

9 . The computer-implemented method of claim 1 , wherein generating the synthetic database comprises generating, using a physics-based reservoir production model, the synthetic database.

10 . The computer-implemented method of claim 1 , wherein the synthetic database comprises fracture geometry and corresponding reservoir production data.

11 . The computer-implemented method of claim 1 , wherein the hydraulic fracturing stimulation performance of the unconventional reservoir comprises at least one of a fracture half length, a fracture height, a size of stimulated reservoir volume (SRV), or a permeability of the SRV.

12 . A non-transitory computer-readable medium storing one or more instructions executable by a computer system to perform operations comprising:

generating a synthetic database for unconventional hydrocarbon resources;

generating, based on the synthetic database, a machine learning model that models unconventional reservoirs;

determining, using the machine learning model, hydraulic fracturing stimulation performance of an unconventional reservoir; and

providing the hydraulic fracturing stimulation performance for unconventional hydrocarbon resource development of the unconventional reservoir.

13 . The non-transitory computer-readable medium of claim 12 , wherein the synthetic database comprises simulated data generated from a physics model-based reservoir simulation tool.

14 . The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise:

before generating the synthetic database for unconventional hydrocarbon resources, determining a plurality of reservoir characteristics that affect the hydraulic fracturing stimulation performance, and wherein generating the synthetic database for unconventional hydrocarbon resources comprises generating, based on the plurality of reservoir characteristics, the synthetic database for unconventional hydrocarbon resources.

15 . The non-transitory computer-readable medium of claim 12 , wherein the operations further comprise:

before generating the synthetic database for unconventional hydrocarbon resources, determining a plurality of stimulation parameters that affect the hydraulic fracturing stimulation performance, and wherein generating the synthetic database for unconventional hydrocarbon resources comprises generating, based on the plurality of stimulation parameters, the synthetic database for unconventional hydrocarbon resources.

16 . The non-transitory computer-readable medium of claim 12 , wherein the synthetic database comprises fracture geometry and corresponding reservoir production data.

17 . A computer-implemented system, comprising:

one or more computers; and

one or more computer memory devices interoperably coupled with the one or more computers and having tangible, non-transitory, machine-readable media storing one or more instructions that, when executed by the one or more computers, perform one or more operations comprising:

generating a synthetic database for unconventional hydrocarbon resources;

generating, based on the synthetic database, a machine learning model that models unconventional reservoirs;

determining, using the machine learning model, hydraulic fracturing stimulation performance of an unconventional reservoir; and

providing the hydraulic fracturing stimulation performance for unconventional hydrocarbon resource development of the unconventional reservoir.

18 . The computer-implemented system of claim 17 , wherein the synthetic database comprises simulated data generated from a physics model-based reservoir simulation tool.

19 . The computer-implemented system of claim 17 , wherein the one or more operations further comprise:

before generating the synthetic database for unconventional hydrocarbon resources, determining a plurality of reservoir characteristics that affect the hydraulic fracturing stimulation performance, and wherein generating the synthetic database for unconventional hydrocarbon resources comprises generating, based on the plurality of reservoir characteristics, the synthetic database for unconventional hydrocarbon resources.

20 . The computer-implemented system of claim 17 , wherein the one or more operations further comprise:

before generating the synthetic database for unconventional hydrocarbon resources, determining a plurality of stimulation parameters that affect the hydraulic fracturing stimulation performance, and wherein generating the synthetic database for unconventional hydrocarbon resources comprises generating, based on the plurality of stimulation parameters, the synthetic database for unconventional hydrocarbon resources.