Automatic geosteering and evolutionary algorithm for use with same
A method, apparatus, and computer-readable medium provide automatic geosteering by automatically updating a geosteering structure model based upon observed data gathered during a drilling operation. In some embodiments, automatic updates may be used to introduce vertical shifts into a geosteering structure model to match synthetic log data with observed log data. In addition, in some embodiments an evolutionary algorithm may be used to introduce such vertical shifts and thereby provide an optimal match between the synthetic and observed log data.
1. A method, comprising:
accessing synthetic log data based on a model of a geological formation;
accessing observed log data collected from a drilling operation in the geological formation;
iterating, using one or more processors, an evolutionary algorithm to update a geosteering structure model, each iteration including:
generating a plurality of updated models based on a set of shifts of geological structures represented by the geosteering structure model, the set of shifts including at least one of a vertical shift, or a variance of a vertical shift of geological structures represented by the geosteering structure model;
generating updated synthetic log data using at least one of the updated models; and
selecting a candidate solution from the plurality of updated models for a next evolutionary generation based on a comparison of the observed log data and the updated synthetic log data; and
updating a well plan for a drilling operation based upon the candidate solution of a last iteration of the evolutionary algorithm.
2. The method of claim 1 , wherein the evolutionary algorithm comprises performing at least one of a crossover operation or a mutation operation.
3. The method of claim 1 , wherein the selecting the candidate solution comprises selecting an updated model for which the comparison produces a fitness function measure between the observed data log and the updated synthetic log data.
4. The method of claim 1 , wherein the synthetic log data comprises at least one of:
a synthetic gamma ray (GR) log, or
a synthetic resistivity log.
5. The method of claim 1 , wherein the observed log data comprises at least one of:
an observed gamma ray (GR) log, or
an observed resistivity log.
6. The method of claim 1 , wherein the iterating the evolutionary algorithm comprises a plurality of generations of updated models each based on an updated data log.
7. A system, comprising:
one or more processors; and
a memory comprising one or more computer-readable media storing synthetic log data based on a model of a geological formation, observed log data collected from a drilling operation in the geological formation, and instructions that, when executed by at least one of the one or more processors, cause the system to perform operations, the operations comprising:
iterating an evolutional algorithm to update a geosteering structure model, each iteration including:
generating a plurality of updated models based on a set of shifts of geological structures represented by the geosteering structure model, the set of shifts including at least one of a vertical shift, or a variance of a vertical shift of geological structures represented by the geosteering structure model;
generating updated synthetic log data using at least one of the plurality of updated models; and
selecting a candidate solution from the plurality of updated models for a next evolutionary generation based on a comparison of the observed log data, and the updated synthetic log data; and
updating a well plan for a drilling operation based upon the candidate solution of a last iteration of the evolutionary algorithm.
8. The system of claim 7 , wherein the evolutionary algorithm comprises performing at least one of a crossover operation or a mutation operation.
9. The system of claim 7 , wherein the selecting the candidate solution comprises selecting an updated model for which the comparison produces a fitness function measure between the observed data log and the updated synthetic log data.
10. The system of claim 7 , wherein the synthetic log data comprises at least one of:
a synthetic gamma ray (GR) log, or
a synthetic resistivity log.
11. The system of claim 7 , wherein the observed log data comprises at least one of:
an observed gamma ray (GR) log, or
an observed resistivity log.
12. The system of claim 7 , wherein the iterating the evolutionary algorithm comprises a plurality of generations of updated models each based on an updated data log.
13. A non-transitory computer-readable medium storing instructions that, when executed, cause a processor system to perform operations, the operations comprising:
accessing synthetic log data based on a model of a geological formation;
accessing observed log data collected from a drilling operation in the geological formation;
iterating an evolutional algorithm to update a geosteering structure model, each iteration including:
generating a plurality of updated models based on a set of shifts of geological structures represented by the geosteering structure model, the set of shifts including at least one of a vertical shift, or a variance of a vertical shift of geological structures represented by the geosteering structure model;
generating updated synthetic log data using at least one of the plurality of updated models;
selecting a candidate solution from the plurality of updated models for a next evolutionary generation based on a comparison of the observed log data and the updated synthetic log data; and
updating a well plan for a drilling operation based upon the candidate solution of a last iteration of the evolutionary algorithm.
14. The medium of claim 13 , wherein the evolutionary algorithm comprises performing at least one of a crossover operation or a mutation operation.
15. The medium of claim 13 , wherein the selecting the candidate solution comprises selecting an updated model for which the comparison produces a fitness function measure between the observed data log and each of the updated synthetic log data.
16. The medium of claim 13 , wherein:
the synthetic log data comprises at least one of a synthetic gamma ray (GR) log, or a synthetic resistivity log; and
the observed log data comprises at least one of an observed gamma ray (GR) log, or an observed resistivity log.
17. The medium of claim 13 , wherein the iterating the evolutionary algorithm comprises a plurality of generations of updated models each based on an updated data log.
18. The method of any of claims 3 - 6 , wherein the evolutionary algorithm comprises performing at least one of a crossover operation or a mutation operation.
19. The method of any of claims 2 and 4 - 6 , wherein the selecting the candidate solution comprises selecting an updated model for which the comparison produces a fitness function measure between the observed data log and the updated synthetic log data.
20. The method of any of claims 2 , 3 , 5 , and 6 , wherein the synthetic log data comprises at least one of:
a synthetic gamma ray (GR) log, or
a synthetic resistivity log.
21. The method of any of claims 2 , 3 , 4 , and 6 , wherein the observed log data comprises at least one of:
an observed gamma ray (GR) log, or
an observed resistivity log.
22. The system of any of claims 9 - 12 , wherein generating the plurality of updated models using the evolutionary algorithm comprises performing at least one of a crossover operation or a mutation operation.
23. The system of any of claims 8 and 10 - 12 , wherein the selecting the candidate solution comprises selecting an updated model for which the comparison produces a fitness function measure between the observed data log and the updated synthetic log data.
24. The system of any of claims 8 , 9 , 11 and 12 , wherein
the synthetic log data comprises at least one of:
a synthetic gamma ray (GR) log, or
a synthetic resistivity log; and
the observed log data comprises at least one of:
an observed gamma ray (GR) log, or
an observed resistivity log.
25. The medium of any of claims 15 - 17 , wherein the evolutionary algorithm comprises performing at least one of a crossover operation or a mutation operation.
26. The medium of any of claims 14 , 16 and 17 , wherein the selecting the candidate solution comprises selecting an updated model for which the comparison produces a fitness function measure between the observed data log and each of the updated synthetic log data.
27. The medium of any of claims 14 , 15 and 17 , wherein:
the synthetic log data comprises at least one of a synthetic gamma ray (GR) log, or a synthetic resistivity log; and
the observed log data comprises at least one of an observed gamma ray (GR) log, or an observed resistivity log.