公开(公告)号：US12013507B2

公开(公告)日：2024-06-18

申请号：US17556002

申请日：2021-12-20

Applicant: Chevron U.S.A. Inc.

Inventor： Zhao Zhang ,  Yijie Zhou ,  Sandra C. Saldana ,  David Bradly Christensen

IPC: G01V1/28 ,  G01V1/30

CPC classification number: G01V1/282 ,  G01V1/306 ,  G01V2210/614

Abstract: A neural network is utilized to improve the resolution of subsurface inversion. The neural network leverages posterior distribution of samples and adds high frequency components to the inversion by utilizing the data in both the time domain and the frequency domain. The improved resolution of the subsurface inversion enables more accurate prediction of subsurface characteristics (e.g., reservoir architecture).

公开(公告)号：US20230400598A1

公开(公告)日：2023-12-14

申请号：US17826400

申请日：2022-05-27

Applicant: Chevron U.S.A. Inc.

Inventor： Mason C. Edwards ,  Joshua S. Hoskinson ,  Sandra C. Saldana ,  Donald Neal Burch

IPC: G01V1/50 ,  G06N20/00

CPC classification number: G01V1/50 ,  G01V2210/60 ,  G06N20/00

Abstract: A reference curve may be used as the goal for alignment when depth shifting one or more target well logs. Traditionally the reference curve has been measured data, and is usually of the same measurement type as the well log for shifting when performed algorithmically. The reference curve may be generated by a weak learner machine learning model. The weak learner machine learning model may preserve shape characteristics and depth information of one or more input curves in the reference curve. Depth shifting of a target well log may be performed by iteratively using sliding correlation windows of differing sizes.

公开(公告)号：US20230194737A1

公开(公告)日：2023-06-22

申请号：US17556002

申请日：2021-12-20

Applicant: Chevron U.S.A. Inc.

Inventor： Zhao Zhang ,  Yijie Zhou ,  Sandra C. Saldana ,  David Bradly Christensen

IPC: G01V1/28 ,  G01V1/30

CPC classification number: G01V1/282 ,  G01V1/306 ,  G01V2210/614

Abstract: A neural network is utilized to improve the resolution of subsurface inversion. The neural network leverages posterior distribution of samples and adds high frequency components to the inversion by utilizing the data in both the time domain and the frequency domain. The improved resolution of the subsurface inversion enables more accurate prediction of subsurface characteristics (e.g., reservoir architecture).