Cognitive screening of EOR additives

1. A method, comprising:

performing a machine learning process using one or more sources of information for enhanced oil recovery (EOR) materials to be used for an EOR process on a defined oil reservoir, where performance of the machine learning process produces an output comprising an indication of one or more EOR materials and their corresponding concentrations to be used in the EOR process;

where performing the machine learning process uses multiple sources of information for the EOR materials to be used for the defined oil reservoir, where the machine learning process uses defined weights to weight EOR efficiencies from the multiple sources of information; and

outputting the indication of the one or more EOR materials and their corresponding concentrations to be used in the EOR process.

2. The method of claim 1 , further comprising converting the indication of the one or more EOR materials and their corresponding concentrations to be used in the EOR process into information defined to cause one or more actuators or one or more mixers or both to provide the one or more EOR materials at their corresponding concentrations at the defined oil reservoir for use by the EOR process.

3. The method of claim 1 , wherein the one or more EOR materials are in a list, and wherein the method further comprises allowing a user to modify EOR efficiencies associated with the EOR materials in the list.

4. The method of claim 1 , where the defined oil reservoir is defined based on information comprising physical and chemical conditions at the oil reservoir.

5. The method of claim 1 , where the EOR process is defined from a selected one of multiple options, and wherein the one or more EOR materials are materials corresponding to the selected option.

6. The method of claim 1 , where the multiple sources of information for the EOR materials to be used for a defined oil reservoir comprises two or more of the following sources: (i) World Wide Web (WWW) search analyses, (ii) microfluidics experiments, (iii) artificial intelligence analyses; and (iv) user feedback.

7. A computer system, comprising:

one or more memories having computer readable code;

one or more processors, wherein the one or more processors, in response to retrieving and executing the computer readable code, cause the computer system to perform the following:

performing a machine learning process using one or more sources of information for enhanced oil recovery (EOR) materials to be used for an EOR process on a defined oil reservoir, where performance of the machine learning process produces an output comprising an indication of one or more EOR materials and their corresponding concentrations to be used in the EOR process; and

outputting the indication of the one or more EOR materials and their corresponding concentrations to be used in the EOR process; and

converting the indication of the one or more EOR materials and their corresponding concentrations to be used in the EOR process into information defined to cause one or more actuators or one or more mixers or both to provide the one or more EOR materials at their corresponding concentrations at the defined oil reservoir for use by the EOR process.

8. The computer system of claim 7 , wherein:

the one or more EOR materials are in a list;

the one or more processors, in response to retrieving and executing the computer readable code, cause the computer system to perform the following: allowing a user to modify EOR efficiencies associated with the EOR materials in the list; and

converting further comprises converting, based on the modified EOR efficiencies, the indication of the one or more EOR materials and their corresponding concentrations to be used in the EOR process into information defined to cause one or more actuators or one or more mixers or both to provide the one or more EOR materials at their corresponding concentrations at the defined oil reservoir for use by the EOR process.

9. The computer system of claim 7 , wherein the one or more EOR materials are in a list, and wherein the one or more processors, in response to retrieving and executing the computer readable code, cause the computer system to perform the following: allowing a user to modify EOR efficiencies associated with the EOR materials in the list.

10. The computer system of claim 7 , where the defined oil reservoir is defined based on information comprising physical and chemical conditions at the oil reservoir.

11. The computer system of claim 7 , where performing the machine learning process uses multiple sources of information for the EOR materials to be used for the defined oil reservoir, where the machine learning process uses defined weights to weight EOR efficiencies from the multiple sources of information.

12. The computer system of claim 11 , where the multiple sources of information for the EOR materials to be used for a defined oil reservoir comprises two or more of the following sources: (i) World Wide Web (WWW) search analyses, (ii) microfluidics experiments, (iii) artificial intelligence analyses; and (iv) user feedback.

13. A computer system, comprising:

one or more memories having computer readable code;

one or more processors, wherein the one or more processors, in response to retrieving and executing the computer readable code, cause the computer system to perform the following:

performing a machine learning process using one or more sources of information for enhanced oil recovery (EOR) materials to be used for an EOR process on a defined oil reservoir, where performance of the machine learning process produces an output comprising an indication of one or more EOR materials and their corresponding concentrations to be used in the EOR process, where the EOR process is defined from a selected one of multiple options, and wherein the one or more EOR materials are materials corresponding to the selected option;

allowing a user to select one of the multiple options and performing the machine learning process based on the selected option; and

outputting the indication of the one or more EOR materials and their corresponding concentrations to be used in the EOR process.

14. The computer system of claim 13 , wherein the multiple options comprise one or more of the following options: polymer flooding; hydrogels; surfactants; alkalines; or nanoparticles.

15. The computer system of claim 14 , wherein information from the one or more sources of information is stored in a database.

16. The computer system of claim 15 , wherein the one or more processors, in response to retrieving and executing the computer readable code, cause the computer system to perform determining the information in the database by performing operations comprising:

searching a world-wide web for EOR materials for each of the multiple options;

assigning properties to EOR materials found during the searching;

establishing reservoir parameters;

establishing effectiveness of EOR materials based on the reservoir parameters, the multiple options, the EOR materials found for each of the multiple options, and the properties of the EOR materials found for each of the multiple options; and

defining, based on the established effectiveness, EOR efficiencies for the EOR materials, each EOR efficiency proportional to an incremental oil production after the EOR process is employed using a corresponding EOR material for a reservoir with the established reservoir parameters.

17. The computer system of claim 15 , wherein the one or more processors, in response to retrieving and executing the computer readable code, cause the computer system to perform determining the information in the database by performing operations comprising:

defining a concentration for each of the multiple options;

assigning properties to EOR materials;

defining physical, chemical and topological parameters of rock and fluid properties;

establishing an effectiveness of EOR materials by performing chip tests using one of microfluidic or nanofluidic chips, wherein the chip tests use two identical chips, where one chip is tested with water flooding and the other chip is tested with water flooding and a specific EOR material and the effectiveness of the specific EOR material is established by comparing incremental oil extraction between the two identical chips; and

defining, based on the established effectiveness, EOR efficiencies for the EOR materials, each EOR efficiency proportional to an incremental oil production after the EOR process is employed using a corresponding EOR material for a reservoir with the established reservoir parameters.