Directional permeability upscaling of a discrete fracture network

1. A method for performing a borehole and/or subsurface formation-related action for a subsurface formation of interest, the method comprising:

receiving with a processor a plurality of sets of fracture data for a subsurface rock;

generating with the processor a discrete fracture network (DFN) for each set of fracture data;

determining with the processor a property of each DFN that corresponds to each set of fracture data;

mapping with the processor the plurality of sets of fracture data to the corresponding property using artificial intelligence (AI) to provide an AI model;

inputting with the processor a set of fracture data for the subsurface formation of interest into the AI model;

outputting with the processor a property of the subsurface formation of interest from the AI model; and

performing the borehole and/or subsurface formation-related action for the subsurface formation of interest using the property and equipment configured to perform the borehole and/or subsurface formation-related action, wherein the equipment configured to perform the borehole and/or subsurface formation-related action is controlled by a controller that receives the property of the subsurface formation of interest.

2. The method according to claim 1 , wherein the property comprises at least one of permeability and a property that is a function of permeability.

3. The method according to claim 1 , wherein each set of fracture data comprises at least one of fracture length, fracture orientation, strike angle, aperture size, and fracture density.

4. The method according to claim 1 , wherein at least one set of fracture data in the plurality of sets of fracture data comprises a distribution for each type of fracture data that is characterized by at least two number values.

5. The method according to claim 4 , wherein the two number values comprise mean and standard deviation.

6. The method according to claim 4 , further comprising calculating the distribution from the at least one set of fracture data.

7. The method according to claim 1 , wherein the AI model comprises an artificial neural network.

8. The method according to claim 1 , wherein the AI model comprises a model based on at least one of a regression method, multivariate statistics, a support vector machine, and a tree based scheme.

9. The method according to claim 1 , wherein at least one set of fracture data in the plurality of sets of fracture data is obtained from at least one of logging data, a core sample, a rock outcropping, an image of a borehole wall, and a deep shear-wave image.

10. The method according to claim 1 , wherein at least one set of fracture data in the plurality of sets of fracture data is obtained from analysis of synthetic fracture data.

11. The method according to claim 1 , wherein the borehole and/or subsurface formation-related action comprises perforating a casing lining the borehole at a location or based upon the property at that location or depth using a perforation tool.

12. The method according to claim 1 , wherein the borehole and/or subsurface formation-related action comprises controlling a flow rate of fluids extracted from a borehole using a controller.

13. The method according to claim 1 , wherein the borehole and/or subsurface formation-related action comprises stimulating the formation using a reservoir stimulation system.

14. The method according to claim 1 , wherein the borehole and/or subsurface formation-related action comprises drilling a borehole with a trajectory that leads to a location in the subsurface formation having a maximum directional permeability value using a drill rig.

15. A system for performing a borehole and/or subsurface formation-related action, the system comprising:

a processor for executing the computer-readable instructions, the computer-readable instructions comprising:

receiving a plurality of sets of fracture data for a subsurface rock;

generating a discrete fracture network (DFN) for each set of fracture data;

determining a property of each DFN that corresponds to each set of fracture data;

mapping the plurality of sets of fracture data to the corresponding property using artificial intelligence (AI) to provide an AI model;

inputting a set of fracture data for a subsurface formation of interest into the AI model; and

outputting a property of the subsurface formation of interest from the AI model;

a controller in communication with the processor and configured to receive the property; and

equipment configured to perform the borehole and/or subsurface formation-related action using the property, wherein operation of the equipment configured to perform the borehole and/or subsurface formation-related action is controlled by the controller.

16. The system according to claim 15 , wherein the property comprises at least one of permeability and a property that is a function of permeability.

17. The system according to claim 16 , wherein the computer-readable instructions further comprise determining a distribution of at least one type of fracture data for at least one set of fracture data in the plurality of sets of fracture data.

18. The system according to claim 15 , wherein the equipment comprises a drill rig for drilling a borehole penetrating the subsurface formation of interest at a location or having a trajectory based on the property.

19. The system according to claim 15 , wherein the equipment comprises a reservoir stimulation system configured for stimulating the subsurface formation of interest in a depth interval to increase a rate of production of hydrocarbons at that depth interval.

20. The system according to claim 15 , wherein the equipment comprises a perforation tool configured to perforate a casing lining a borehole penetrating the subsurface formation of interest based on property having a desired value for the economic production of hydrocarbons.