Three-dimensional inversion of multi-component electromagnetic measurements using a fast proxy model
Described herein are systems and techniques for monitoring for monitoring and evaluating conditions associated with a wellbore and wellbore operations that use neural operators instead of computationally intensive iterative differential equations. Such systems and techniques allow for determinations to be made as operations associated with a wellbore are performed. Instead of having to wait for computationally intensive tasks to be performed or take risks of proceeding with a wellbore operation without real-time evaluations being performed, these wellbore operations may be continued while determinations are timely made, thus improving operation of computing systems that perform evaluations and that make decisions regarding safely and efficiently performing wellbore operations such as drilling a wellbore, cementing wellbore casings in place, or injecting fluids into formations of the Earth.
1. A method comprising:
identifying a set of values included in a set of wellbore log data, the set of values associated with material characteristics of a wellbore;
generating a first spatial domain function associated with the set of values when preparing to convert the first spatial domain function into a frequency domain function based on a neural operator;
converting the first spatial domain function into the frequency domain function based on the neural operator;
converting the frequency domain function into a second spatial domain function; and
identifying the material characteristics of the wellbore based on application of the second spatial domain function.
2. The method of claim 1 , further comprising:
applying the first spatial domain function to identify an estimate of the material characteristics of the wellbore; and
identifying that the estimate of the material characteristics does not correspond to a physical response associated with the set of values within a threshold level.
3. The method of claim 1 , further comprising:
identifying a direction to steer a drill that is drilling the wellbore based on a determination associated with the identified material characteristics.
4. The method of claim 1 , further comprising:
identifying a corrective action that should be performed to a wellbore operation based on the identified material characteristics of the wellbore; and
initiating execution of the corrective action based on near-real time assessments made by application of the neural operator.
5. The method of claim 1 , further comprising:
identifying adjustments to make to one or more values of the first spatial domain function thereby generating a plurality of variations of the first spatial domain function, wherein one of the variations of the spatial domain function is converted into the frequency domain function and another variation of the spatial domain function is converted into a second frequency domain function based on application of the neural operator or a second neural operator.
6. The method of claim 5 , wherein at least one value of the adjustments made to the one or more values of the first spatial domain function is a coefficient.
7. The method of claim 5 , wherein at least one value of the adjustments made to the one or more values of the first spatial domain function is a wellbore log value.
8. A non-transitory computer-readable storage medium having embodied thereon instructions executable by one or more processors for performing a method comprising:
identifying a set of values included in a set of wellbore log data, the set of values associated with material characteristics of a wellbore;
generating a first spatial domain function associated with the set of values when preparing to convert the first spatial domain function into a frequency domain function based on a neural operator;
converting the first spatial domain function into the frequency domain function based on the neural operator;
converting the frequency domain function into a second spatial domain function; and
identifying the material characteristics of the wellbore based on application of the second spatial domain function.
9. The non-transitory computer-readable storage medium of claim 8 , the instructions further executable by the one or more processors to:
apply the first spatial domain function to identify an estimate of the material characteristics of the wellbore; and
identify that the estimate of the material characteristics does not correspond to a physical response associated with the set of values within a threshold level.
10. The non-transitory computer-readable storage medium of claim 8 , the instructions further executable by the one or more processors to:
Identify a direction to steer a drill that is drilling the wellbore based on a determination associated with the identified material characteristics.
11. The non-transitory computer-readable storage medium of claim 8 , the instructions further executable by the one or more processors to:
identify a corrective action that should be performed to a wellbore operation based on the identified material characteristics of the wellbore; and
initiate execution of the corrective action based on near-real time assessments made by application of the neural operator.
12. The non-transitory computer-readable storage medium of claim 8 , the instructions further executable by the one or more processors to:
identify adjustments to make to one or more values of the first spatial domain function thereby generating a plurality of variations of the first spatial domain function, wherein one of the variations of the spatial domain function is converted into the frequency domain function and another variation of the spatial domain function is converted into a second frequency domain function based on application of the neural operator or a second neural operator.
13. The non-transitory computer-readable storage medium of claim 12 , wherein at least one value of the adjustments made to the one or more values of the first spatial domain function is a coefficient.
14. The non-transitory computer-readable storage medium of claim 12 , wherein at least one value of the adjustments made to the one or more values of the first spatial domain function is a wellbore log value.
15. An apparatus comprising:
a memory; and
one or more processors that execute instructions out of the memory to:
identify a set of values included in a set of wellbore log data, the set of values associated with material characteristics of a wellbore,
generate a first spatial domain function associated with the set of values when preparing to convert the first spatial domain function into a frequency domain function based on a neural operator,
convert the first spatial domain function into the frequency domain function based on the neural operator,
convert the frequency domain function into a second spatial domain function, and
identify the material characteristics of the wellbore based on application of the second spatial domain function.
16. The apparatus of claim 15 , wherein the one or more processors execute the instructions out of the memory to:
apply the first spatial domain function to identify an estimate of the material characteristics of the wellbore; and
identify that the estimate of the material characteristics does not correspond to a physical response associated with the set of values within a threshold level.
17. The apparatus of claim 15 , the one or more processors execute the instructions out of the memory to:
identify a direction to steer a drill that is drilling the wellbore based on a determination associated with the identified material characteristics.
18. The apparatus of claim 15 , the one or more processors execute the instructions out of the memory to:
identify a corrective action that should be performed to a wellbore operation based on the identified material characteristics of the wellbore; and
initiate execution of the corrective action based on near-real time assessments made by application of the neural operator.
19. The apparatus of claim 15 , the one or more processors execute the instructions out of the memory to:
identify adjustments to make to one or more values of the first spatial domain function thereby generating a plurality of variations of the first spatial domain function, wherein one of the variations of the spatial domain function is converted into the frequency domain function and another variation of the spatial domain function is converted into a second frequency domain function based on application of the neural operator or a second neural operator.
20. The apparatus of claim 19 , wherein at least one value of the adjustments made to the one or more values of the first spatial domain function is a coefficient.