US 12,333,430 B2
Super resolution machine learning model for seismic visualization generation
Suhas Suresha, Menlo Park, CA (US); Emilien Dupont, Los Altos, CA (US); and Joseph Matthew Chalupsky, Houston, TX (US)
Assigned to SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
Appl. No. 17/904,160
Filed by SCHLUMBERGER TECHNOLOGY CORPORATION, Sugar Land, TX (US)
PCT Filed Feb. 12, 2020, PCT No. PCT/US2020/017820
§ 371(c)(1), (2) Date Aug. 12, 2022,
PCT Pub. No. WO2021/162683, PCT Pub. Date Aug. 19, 2021.
Prior Publication US 2023/0082567 A1, Mar. 16, 2023
Int. Cl. G06N 3/00 (2023.01); G01V 1/34 (2006.01); G06N 3/08 (2023.01); G06T 3/4046 (2024.01); G06T 3/4053 (2024.01); G06V 10/82 (2022.01)
CPC G06N 3/08 (2013.01) [G01V 1/345 (2013.01); G06T 3/4046 (2013.01); G06T 3/4053 (2013.01); G06V 10/82 (2022.01); G01V 2210/74 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method of rendering a seismic visualization, the method comprising:
receiving high resolution seismic data at a visualization engine running in a virtual machine (VM) on a cloud server, the high resolution seismic data representative of a portion of a subsurface formation;
generating, at the visualization engine running in the VM on the cloud server, a high resolution seismic visualization of the subsurface formation from the high resolution seismic data, wherein the generating includes rendering of the high resolution seismic data;
compressing, at the visualization engine running in the VM on the cloud server, the high resolution seismic visualization to generate a low resolution seismic visualization;
communicating the low resolution seismic visualization from the cloud server to a remote visualization client;
processing, at the remote visualization client, the low resolution seismic visualization with a super resolution machine learning model to reconstruct the high resolution seismic visualization; and
displaying, via the remote visualization client, the high resolution seismic visualization to a user.