公开(公告)号：US20220413173A1

公开(公告)日：2022-12-29

申请号：US17359435

申请日：2021-06-25

Applicant: Landmark Graphics Corporation

Inventor： Fan Jiang ,  Philip Norlund

IPC: G01V1/30 ,  G01V1/18 ,  G06N3/08 ,  G06N3/04 ,  E21B49/00

Abstract: A system can receive seismic data that can correlate to a subterranean formation. The system can derive a set of seismic attributes from the seismic data. The seismic attributes can include discontinuity-along-dip. The system can determine parameterized results by analyzing the seismic data and the seismic attributes using a deep learning neural network. The deep learning neural network can include a dilation module. The system can determine one or more fault probabilities of the subterranean formation using the parameterized results. The system can output the fault probabilities for use in a hydrocarbon exploration operation.

公开(公告)号：US11971515B2

公开(公告)日：2024-04-30

申请号：US17359435

申请日：2021-06-25

Applicant: Landmark Graphics Corporation

Inventor： Fan Jiang ,  Philip Norlund

IPC: G01V1/30 ,  E21B49/00 ,  G01V1/18 ,  G06N3/04 ,  G06N3/08

CPC classification number: G01V1/307 ,  E21B49/00 ,  G01V1/181 ,  G06N3/04 ,  G06N3/08 ,  E21B2200/22 ,  G01V2210/63 ,  G01V2210/65

Abstract: A system can receive seismic data that can correlate to a subterranean formation. The system can derive a set of seismic attributes from the seismic data. The seismic attributes can include discontinuity-along-dip. The system can determine parameterized results by analyzing the seismic data and the seismic attributes using a deep learning neural network. The deep learning neural network can include a dilation module. The system can determine one or more fault probabilities of the subterranean formation using the parameterized results. The system can output the fault probabilities for use in a hydrocarbon exploration operation.

公开(公告)号：US20230152480A1

公开(公告)日：2023-05-18

申请号：US17527245

申请日：2021-11-16

Applicant: Landmark Graphics Corporation

Inventor： Satyan Singh ,  Philip Norlund ,  Adrian Sanchez Rodriguez ,  Eugene Wolfe ,  Steven Angelovich

IPC: G01V1/36 ,  G01V1/28

CPC classification number: G01V1/364 ,  G01V1/282 ,  G01V2210/324

Abstract: System and methods of random noise attenuation are provided. A first model may be trained to extract random noise from seismic datasets. A second model may be trained to reconstruct leaked signals from the random noise extracted by the first model. A seismic dataset corresponding to a subsurface reservoir formation and including random noise may be obtained. Using the trained first model, at least a portion of the random noise may be extracted from the first seismic dataset. Using the trained second model, a leaked signal, which includes a portion of the seismic dataset, may be reconstructed from the extracted random noise. A cleaned seismic dataset is generated based on the reconstructed leaked signal and the extracted random noise. The cleaned seismic dataset may include a quantity of random noise that is less than that of the original seismic dataset.