US 12,085,686 B2
Seismic interference noise attenuation using DNN
Song Hou, Crawley (GB); and Jing Sun, Oslo (NO)
Assigned to CGG SERVICES SAS, Massy (FR)
Filed by CGG SERVICES SAS, Massy (FR)
Filed on May 23, 2022, as Appl. No. 17/750,467.
Claims priority of provisional application 63/252,895, filed on Oct. 6, 2021.
Prior Publication US 2023/0105075 A1, Apr. 6, 2023
Int. Cl. G01V 1/36 (2006.01); G01V 1/28 (2006.01); G06F 30/27 (2020.01)
CPC G01V 1/364 (2013.01) [G01V 1/282 (2013.01); G06F 30/27 (2020.01); G01V 2210/324 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A seismic exploration method, the method comprising:
selecting a representative subset of a seismic data acquired during a survey;
extracting a seismic interference, SI, model from the representative subset using a conventional method;
combining the SI model with SI free shots and simulated random noise to generate a training dataset;
training a deep neural network, DNN, using the training data so that the DNN to output the SI model and a sum of the SI free shots and the simulated random noise; and
using the trained DNN to process the seismic data in order to generate an image of subsurface formation for detecting presence and/or location of sought-after natural resources.