Determining a landing zone in a subterranean formation
Techniques for generating a geological model include identifying a plurality of well data for each of a plurality of wells drilled into a reservoir basin from a terranean surface. The reservoir basin includes a plurality of landing zones formed under the terranean surface, each of the landing zone including a discrete geological layer. The techniques further include comparing the plurality of well data for each well with a reservoir basin database that associates the well data with one of the plurality of landing zones; correlating each of the plurality of wells with a particular landing zone of the plurality of landing zones based on the comparison; and generating a geological model of the reservoir basin based on the correlated wells.
1. A computer-implemented method for generating a geological model, comprising:
identifying, with one or more hardware processors, a first plurality of wells drilled into a reservoir basin from a terranean surface, with each of the first plurality of wells associated with one of a plurality of landing zones formed under the terranean surface in the reservoir basin, each of the landing zones comprising a discrete geological layer, where each of the first plurality of wells is associated with the one landing zone based on a horizontal portion of the each well being formed within the one landing zone based on a known, digital trajectory of the each well;
identifying, with one or more hardware processors, a plurality of well data for each of a second plurality of wells drilled into the reservoir basin from the terranean surface;
comparing, with the one or more hardware processors and a machine learning process, the plurality of well data for each well of the second plurality of wells with a reservoir basin database that associates the well data with one of the plurality of landing zones;
correlating, with the one or more hardware processors and the machine learning process, each of the second plurality of wells with one landing zone of the plurality of landing zones based on the comparison, the machine learning process trained to derive a particular landing zone of the each of the second plurality of wells based at least in part on the plurality of well data for the each of the second plurality of wells;
generating, with the one or more hardware processors, a geological model of the reservoir basin based on the correlated wells of the second plurality of wells and the first plurality of wells;
identifying, at a server computing system that stores the generated geological model, a request from a client computing system that comprises an identification of one or more drilled wells in the reservoir basin;
determining, with the server computing system and based on the generated geological model, a particular landing zone for each of the identified one or more drilled wells; and
preparing, with the server computing system, a graphic that describes the determined particular landing zones for display at the client computing system.
2. The computer-implemented method of claim 1 , wherein the plurality of well data comprises surface latitude (Y), surface longitude (X), and true vertical depth (TVD).
3. The computer-implemented method of claim 2 , wherein the plurality of well data further comprise a distance-to-horizon value between the TVD and at least one of the discrete geological layers.
4. The computer-implemented method of claim 3 , further comprising determining, with the one or more hardware processors, the distance-to-horizon value between each of the discrete geological layers and the TVD.
5. The computer-implemented method of claim 1 , wherein the plurality of well data excludes complete directional surveys.
6. The computer-implemented method of claim 1 , wherein the steps of comparing and correlating comprise executing the machine learning process.
7. The computer-implemented method of claim 6 , wherein the machine learning process comprises a tree-based machine learning process.
8. The computer-implemented method of claim 1 , further comprising validating, with the one or more hardware processors, the generated geological model.
9. The computer-implemented method of claim 8 , wherein validating the generated geological model comprises:
determining, with the one or more hardware processors, a number of mis-correlations of the second plurality of wells with the one landing zone of the plurality of landing zones; and
determining, with the one or more hardware processors, that the number of mis-correlations are less than a threshold number.
10. The computer-implemented method of claim 8 , wherein validating the generated geological model comprises:
determining, with the one or more hardware processors, Shapley values for each of the second plurality of well data;
determining, with the one or more hardware processors, a greatest of the determined Shapley values; and
determining, with the one or more hardware processors, the particular well data that corresponds to the greatest Shapley value.
11. The computer-implemented method of claim 1 , further comprising:
identifying, at a server computing system that stores the generated geological model, a request from a client computing system that comprises an identification of the reservoir basin;
determining, with the server computing system and based on the generated geological model, a plurality of drilled wells formed in the identified reservoir basin and a particular landing zone for each of the plurality of wells; and
preparing, with the server computing system, a graphic that describes the determined plurality of drilled wells in the identified reservoir basin and the particular landing zone for each of the plurality of wells at the client computing system.
12. The computer-implemented method of claim 1 , further comprising:
identifying, at a server computing system that stores the generated geological model, a request from a client computing system that comprises an identification of a plurality of well data for a drilled well in the reservoir basin;
determining, with the server computing system and based on the generated geological model, a landing zone for the drilled well; and
preparing, with the server computing system, a graphic that describes the determined landing zone for the drilled well for display at the client computing system.
13. A computing system, comprising:
one or more memory modules that stores or references a plurality of well data; and
one or more hardware processors configured to execute instructions stored on the one or more memory modules to perform operations comprising:
identifying a first plurality of wells drilled into a reservoir basin from a terranean surface, with each of the first plurality of wells associated with one of a plurality of landing zones formed under the terranean surface in the reservoir basin, each of the landing zones comprising a discrete geological layer, where each of the first plurality of wells is associated with the one landing zone based on a horizontal portion of the each well being formed within the one landing zone based on a known, digital trajectory of the each well;
identifying a plurality of well data for each of a second plurality of wells drilled into the reservoir basin from the terranean surface;
comparing, with a machine learning process, the plurality of well data for each well of the second plurality of wells with a reservoir basin database that associates the well data with one of the plurality of landing zones;
correlating, with the machine learning process, each of the second plurality of wells with one landing zone of the plurality of landing zones based on the comparison, the machine learning process trained to derive a particular landing zone of the each of the second plurality of wells based at least in part on the plurality of well data for the each of the second plurality of wells;
generating a geological model of the reservoir basin based on the correlated wells of the second plurality of wells and the first plurality of wells;
identifying or receiving a request from a client computing system that comprises an identification of one or more drilled wells in the reservoir basin;
determining a particular landing zone for each of the identified one or more drilled wells based on the generated geological model; and
preparing a graphic that describes the determined particular landing zone for display at the client computing system.
14. The computing system of claim 13 , wherein the plurality of well data comprises surface latitude (Y), surface longitude (X), and true vertical depth (TVD).
15. The computing system of claim 14 , wherein the plurality of well data further comprise a distance-to-horizon value between the TVD and at least one of the discrete geological layers.
16. The computing system of claim 15 , wherein the operations further comprise determining the distance-to-horizon value between each of the discrete geological layers and the TVD.
17. The computing system of claim 13 , wherein the plurality of well data excludes complete directional surveys.
18. The computing system of claim 13 , wherein the operations of comparing and correlating comprise executing the machine learning process.
19. The computing system of claim 18 , wherein the machine learning process comprises a tree-based machine learning process.
20. The computing system of claim 13 , wherein the operations further comprise validating the generated geological model.
21. The computing system of claim 20 , wherein validating the generated geological model comprises:
determining, with the one or more hardware processors, a number of mis-correlations of the second plurality of wells with the one landing zone of the plurality of landing zones; and
determining, with the one or more hardware processors, that the number of mis-correlations are less than a threshold number.
22. The computing system of claim 20 , wherein validating the generated geological model comprises:
determining, with the one or more hardware processors, Shapley values for each of the plurality of well data;
determining, with the one or more hardware processors, a greatest of the determined Shapley values; and
determining, with the one or more hardware processors, the particular well data that corresponds to the greatest Shapley value.
23. The computing system of claim 13 , wherein the operations further comprise:
identifying a request from a client computing system that comprises an identification of the reservoir basin;
determining a plurality of drilled wells formed in the identified reservoir basin and a particular landing zone for each of the plurality of drilled wells based on the generated geological model; and
preparing a graphic that describes the determined plurality of drilled wells in the identified reservoir basin and the particular landing zone for each of the plurality of drilled wells at the client computing system.
24. The computing system of claim 13 , wherein the operations further comprise:
identifying a request from a client computing system that comprises an identification of a plurality of well data for a drilled well in the reservoir basin;
determining a landing zone for the drilled well based on the generated geological model; and
preparing a graphic that describes the determined landing zone for the drilled well for display at the client computing system.
25. The computer-implemented method of claim 1 , wherein the known, digital trajectory of the each well comprises a complete digital trajectory of the each well.
26. The computer-implemented method of claim 25 , wherein the plurality of well data for each of the second plurality of wells comprises an incomplete digital trajectory of the each of the second plurality of wells.
27. The computer-implemented method of claim 26 , wherein the machine learning process is trained to derive a particular landing zone of the each of the second plurality of wells based at least in part on the incomplete digital trajectory of the each of the second plurality of wells.
28. The computing system of claim 13 , wherein the known, digital trajectory of the each well comprises a complete digital trajectory of the each well.
29. The computing system of claim 28 , wherein the plurality of well data for each of the second plurality of wells comprises an incomplete digital trajectory of the each of the second plurality of wells.
30. The computing system of claim 29 , wherein the machine learning process is trained to derive a particular landing zone of the each of the second plurality of wells based at least in part on the incomplete digital trajectory of the each of the second plurality of wells.