US 12,129,757 B2
Automatic well log correction
Vanessa Simoes, Houston, TX (US); Hiren Maniar, Houston, TX (US); Tao Zhao, Houston, TX (US); and Aria Abubakar, Houston, TX (US)
Assigned to SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
Appl. No. 18/706,186
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
PCT Filed Nov. 4, 2022, PCT No. PCT/US2022/048941
§ 371(c)(1), (2) Date Apr. 30, 2024,
PCT Pub. No. WO2023/081343, PCT Pub. Date May 11, 2023.
Claims priority of provisional application 63/263,555, filed on Nov. 4, 2021.
Prior Publication US 2024/0328309 A1, Oct. 3, 2024
Int. Cl. E21B 47/13 (2012.01); E21B 47/12 (2012.01); G01V 1/48 (2006.01); G06N 20/00 (2019.01)
CPC E21B 47/138 (2020.05) [G01V 1/48 (2013.01); G06N 20/00 (2019.01); G01V 2210/6169 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method, comprising:
receiving first training well logs;
generating second training well logs by injecting one or more types of systematic errors, random errors, or both into at least a portion of the first training well logs;
training a machine learning model to correct well logs by configuring the machine learning model to reduce a dissimilarity between at least a portion of the first training well logs and the second training well logs;
receiving one or more implementation well logs; and
generating one or more corrected well logs by correcting at least a portion of the one or more implementation well logs using the machine learning model that was trained.