IP Library › Granted Patent US 12,747,661
Granted Patent B2
US 12,747,661 · App. 19/233,497 · Granted Sep 29, 2026

Logging tool inversion integration

Inventors: Kent Harms (Sugar Land, TX); Volodymyr Puzyrov (Cambridge, MA); Lin Liang (Cambridge, MA)
Assignee: Schlumberger Technology Corporation
E21B44/00E21B7/04E21B47/026E21B49/00G05B13/0265E21B2200/22
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,747,661
App. No.
19/233,497
Granted
Sep 29, 2026
Kind
B2
Abstract

A method and system to implement a technique including receiving at least one drilling parameter corresponding to an attribute related to a well in a formation as measured data, performing a first inversion operation (e.g., using machine learning methods) utilizing the measured data to generate first inversion result, determining whether the first inversion result meets a predetermined criteria related to quality of the first inversion result, and performing a geosteering operation based on the first inversion result when the first inversion result is determined to meet the predetermined criteria. If the first inversion result is determined not to meet the predetermined criteria, a second inversion operation (e.g., traditional methods) is used to invert the measured data to generate second inversion result, which is used for performing a geosteering operation.

Claims (34)

1 . A method comprising:

receiving at least one drilling parameter corresponding to an attribute related to a well in a formation as measured data;

performing a first inversion operation utilizing the measured data to generate a first inversion result, wherein the first inversion operation is a first type of inversion operation performed downhole utilizing a first amount of computational resources;

determining whether the first inversion result meets a predetermined criteria related to quality of the first inversion result;

performing a first geosteering operation based on the first inversion result in response to determining that the first inversion result meets the predetermined criteria;

performing a second inversion operation utilizing the measured data to generate a second inversion result subsequent to determining that the first inversion result does not meet the predetermined criteria, wherein the second inversion operation is a second type of inversion operation differing from the first type of inversion operation, wherein the second inversion operation is performed by surface equipment utilizing a second amount of computational resources that is greater than the first amount of computational resources; and

performing a second geosteering operation based on the second inversion result in response to generation of the second inversion result.

2 . The method of claim 1 , further comprising performing the first inversion operation utilizing a machine learning model.

3 . The method of claim 1 , further comprising performing the second inversion operation utilizing a Gauss-Newton method or a machine learning model.

4 . The method of claim 1 , further comprising performing the first inversion operation in a logging tool disposed in the well.

5 . The method of claim 1 , further comprising performing the second inversion operation in a data processing system at a surface above the formation.

6 . The method of claim 1 , wherein performing the first geosteering operation comprises transmitting at least one control signal to downhole equipment to control directionality of the well.

7 . A tangible and non-transitory machine readable medium comprising instructions to cause at least one processor to:

receive at least one drilling parameter corresponding to an attribute related to a well in a formation as measured data;

perform a first inversion operation utilizing the measured data to generate a first inversion result, wherein the first inversion operation is a first type of inversion operation performed downhole utilizing a first amount of computational resources;

determine whether the first inversion result meets a predetermined criteria related to quality of the first inversion result, wherein the predetermined criteria comprises a data misfit corresponding to a measure of fit between the first inversion result and the measured data or wherein the predetermined criteria comprises a machine learning uncertainty measurement;

generate at least one first control signal utilized to perform a first geosteering operation based on the first inversion result in response to determining that the first inversion result meets the predetermined criteria;

perform a second inversion operation utilizing the measured data to generate a second inversion result subsequent to determining that the first inversion result does not meet the predetermined criteria, wherein the second inversion operation is a second type of inversion operation differing from the first type of inversion operation, wherein the second inversion operation is performed by surface equipment utilizing a second amount of computational resources that is greater than the first amount of computational resources; and

generate at least one second control signal utilized to perform a second geosteering operation based on the second inversion result in response to generation of the second inversion result.

8 . The tangible and non-transitory machine readable medium of claim 7 , wherein the instructions further cause the at least one processor to perform the first inversion operation utilizing a machine learning model.

9 . The tangible and non-transitory machine readable medium of claim 7 , wherein the instructions further cause the at least one processor to perform the second inversion operation utilizing a Gauss-Newton method or a machine learning model.

10 . The tangible and non-transitory machine readable medium of claim 7 , wherein the instructions further cause the at least one processor to transmit the at least one control signal to downhole equipment to control directionality of the well.

11 . A system, comprising:

an acquisition system configured to measure at least one drilling parameter corresponding to an attribute related to a well in a formation as measured data;

memory comprising executable instructions; and

at least one processor coupled to the acquisition system and the memory, wherein the at least one processor is configured to execute the executable instructions to:

perform a first inversion operation utilizing the measured data to generate a first inversion result, wherein the first inversion operation is a first type of inversion operation performed downhole utilizing a first amount of computational resources;

determine whether the first inversion result meets a predetermined criteria related to quality of the first inversion result, wherein the predetermined criteria comprises a data misfit corresponding to a measure of fit between the first inversion result and the measured data or wherein the predetermined criteria comprises a machine learning uncertainty measurement;

generate at least one first control signal utilized to perform a first geosteering operation based on the first inversion result in response to determining that the first inversion result meets the predetermined criteria, wherein the at least one first control signal controls a directionality of a drill or other drilling equipment to facilitate creation of the well along a first directionality;

perform a second inversion operation utilizing the measured data to generate a second inversion result subsequent to determining that the first inversion result does not meet the predetermined criteria, wherein the second inversion operation is a second type of inversion operation differing from the first type of inversion operation, wherein the second inversion operation is performed by surface equipment utilizing a second amount of computational resources that is greater than the first amount of computational resources; and

generate at least one second control signal utilized to perform a second geosteering operation based on the second inversion result in response to generation of the second inversion result.

12 . The system of claim 11 , wherein the at least one processor is configured to execute the executable instructions to perform the first inversion operation utilizing a machine learning model.

13 . The system of claim 11 , wherein the at least one processor is configured to execute the executable instructions to perform the second inversion operation utilizing a Gauss-Newton method or a machine learning model.

14 . The system of claim 11 , wherein the at least one processor comprises a first processor disposed in a logging tool disposed in the well to execute the executable instructions to perform the first inversion operation and a second processor disposed in a data processing system at a surface above the formation to execute the executable instructions to perform the second inversion operation.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 15, 2026
From: HARMS, KENT; PUZYROV, VOLODYMYR; LIANG, LIN
To: SCHLUMBERGER TECHNOLOGY CORPORATION
Reel/Frame 073789/0737 →
Continuity (2)
Provisional Application 63727230 · Dec 3, 2024
Related Publication 20260153022A1 · Jun 4, 2026
References Cited (17)
US 6799117B1 · Proett · 2004 [cited by examiner]
US 12428946B2 · Pournazari · 2025 [cited by examiner]
US 12448879B2 · Li · 2025 [cited by examiner]
US 12481900B2 · Keller · 2025 [cited by examiner]
US 20180321415A1 · Thiel · 2018 [cited by examiner]
US 20190302310A1 · Fox · 2019 [cited by examiner]
US 20190390542A1 · Song · 2019 [cited by examiner]
US 20200011158A1 · Xu · 2020 [cited by examiner]
US 20220090481A1 · Aljedaani · 2022 [cited by examiner]
US 20220170359A1 · Boualleg · 2022 [cited by examiner]
US 20240247580A1 · Wang · 2024 [cited by examiner]
US 20240411041A1 · Kulkarni · 2024 [cited by examiner]
US 20250116177A1 · Li · 2025 [cited by examiner]
US 20250225411A1 · Gutierrez Gonzalez · 2025 [cited by examiner]
US 20250284866A1 · Puzyrov · 2025 [cited by examiner]
US 20250382867A1 · Xu · 2025 [cited by examiner]
WO 2024123722A1 · 2024 [cited by applicant]