US 11,965,998 B2
Training a machine learning system using hard and soft constraints
Haibin Di, Houston, TX (US); Cen Li, Houston, TX (US); Aria Abubakar, Houston, TX (US); and Stewart Smith, Tananger (NO)
Assigned to SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
Appl. No. 17/595,021
Filed by Schlumberger Technology Corporation, Sugar Land, TX (US)
PCT Filed May 11, 2020, PCT No. PCT/US2020/032334
§ 371(c)(1), (2) Date Nov. 5, 2021,
PCT Pub. No. WO2020/231918, PCT Pub. Date Nov. 19, 2020.
Claims priority of provisional application 62/847,250, filed on May 13, 2019.
Prior Publication US 2022/0206175 A1, Jun. 30, 2022
Int. Cl. G01V 1/30 (2006.01); G06N 3/08 (2023.01); G01V 20/00 (2024.01); G06F 30/27 (2020.01)
CPC G01V 1/301 (2013.01) [G06N 3/08 (2013.01); G01V 20/00 (2024.01); G01V 2210/612 (2013.01); G01V 2210/6161 (2013.01); G01V 2210/642 (2013.01); G01V 2210/646 (2013.01); G06F 30/27 (2020.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
receiving a test seismic dataset associated with a known truth interpretation;
receiving one or more hard constraints;
training a machine learning system based on the test seismic dataset, the known truth interpretation, and the one or more hard constraints;
determining an error value based on the training the machine learning system;
adjusting the error value based on one or more soft constraints;
updating the training of the machine learning system based on the adjusted error value;
receiving a second seismic dataset after the updating the training;
applying the second seismic dataset to the machine learning system to generate an interpretation of the second seismic dataset;
generating a seismic image representing a subterranean domain based on the interpretation of the second seismic dataset; and
outputting the seismic image.