公开(公告)号：US20240210584A1

公开(公告)日：2024-06-27

申请号：US18069865

申请日：2022-12-21

Applicant: Chevron U.S.A. Inc.

Inventor： Ke Wang ,  Jinsong Chen ,  Yijie Zhou

IPC: G01V1/30 ,  G01V1/28 ,  G01V1/34 ,  G06N3/091

CPC classification number: G01V1/30 ,  G01V1/282 ,  G01V1/345 ,  G06N3/091

Abstract: A method is described for seismic inversion with uncertainty quantification including performing low frequency Markov Chain Monte Carlo (MCMC) processes on rock physics models to generate low frequency models (LFMs) of rock properties and training a deep neural network using the low frequency models and synthetic seismograms to generate a trained neural network. Given a seismic dataset, the trained neural network can generate a high frequency rock property model and then broad-band MCMC processes can be performed on the high frequency rock property model for uncertainty quantification. The method is executed by a computer system.

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：US20240241278A1

公开(公告)日：2024-07-18

申请号：US18156229

申请日：2023-01-18

Applicant: Chevron U.S.A. Inc.

Inventor： Yijie Zhou

IPC: G01V1/34 ,  G01V1/28

CPC classification number: G01V1/34 ,  G01V1/282

Abstract: A method is described for reservoir structure characterization including obtaining well logs and seismic data; performing facies classification and stratigraphic sequencing on the well logs to identify a plurality of layers; estimating wavelets from the seismic data and using the wavelets to tie synthetic seismograms from well logs to the seismic data; determining a mean value for each elastic property in each layer of the well logs and assigning the mean value to each layer to generate blocky well logs; using the wavelets to attempt to tie synthetic seismograms from the blocky well logs to the seismic data; defining facies-dependent properties based on the blocky well logs; performing global optimization using the facies-dependent properties and the seismic data to find thicknesses of the layers across the volume of interest; and mapping the reservoir structure based on the global optimization to generate a graphical representation of the reservoir structure.

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).