公开(公告)号：US20220221609A1

公开(公告)日：2022-07-14

申请号：US17342799

申请日：2021-06-09

Applicant: CGG SERVICES SAS

Inventor： Hanyuan PENG ,  Jeremie MESSUD ,  Céline LACOMBE ,  Paulien JEUNESSE

IPC: G01V1/38 ,  G01V1/30 ,  G06N3/04

Abstract: A DUnet engine produces a processed image of seismic data acquired over an underground formation. The DUnet engine includes: a contractive path that performs multilayer convolutions and contraction to extract a code from the seismic data input to the DUnet, an expansive path configured to perform multilayer convolutions and expansion of the code, using features provided by the contractive path through skip connections, and a model level that performs multilayer convolutions on outputs of the contractive path and expansive paths to produce the processed image and/or an image that is a difference between the processed image and the seismic data. A fraction of the seismic data may be selected for training the DUnet engine using an anchor method that automatically extends an initial seismic data subset, based on similarity measurements. A reweighting layer may further combine inputs received from layers of the DUnet model to preserve signal amplitude trend.